Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.4"
+}

latest

@@ -0,0 +1 @@
+global_step179

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e2425215597484c88d1ed9575e711402c9cc3bf813103ba11743cfd1d4da3db
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7469bcaedf2118d7fc31f6a8cb4617af75100f26ce4e3906f6589d4b83d4de06
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:835f869ea325fd6edf27b48b589309fb66641cb92b45f2fc13d1bb6e8814106c
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:707c86685b9e1f735b18dc919713ae2cd51daab0a09a029c367289ebc04c3592
+size 1064

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1294 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 180,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0055768560474032764,
+      "grad_norm": 46.09545673843412,
+      "learning_rate": 0.0,
+      "loss": 1.7007,
+      "step": 1
+    },
+    {
+      "epoch": 0.011153712094806553,
+      "grad_norm": 44.46037462061874,
+      "learning_rate": 2.7777777777777776e-07,
+      "loss": 1.6776,
+      "step": 2
+    },
+    {
+      "epoch": 0.01673056814220983,
+      "grad_norm": 40.73202594632966,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 1.5002,
+      "step": 3
+    },
+    {
+      "epoch": 0.022307424189613106,
+      "grad_norm": 42.88149317876023,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 1.6238,
+      "step": 4
+    },
+    {
+      "epoch": 0.027884280237016383,
+      "grad_norm": 42.513311455243326,
+      "learning_rate": 1.111111111111111e-06,
+      "loss": 1.678,
+      "step": 5
+    },
+    {
+      "epoch": 0.03346113628441966,
+      "grad_norm": 43.24081118630191,
+      "learning_rate": 1.3888888888888892e-06,
+      "loss": 1.7263,
+      "step": 6
+    },
+    {
+      "epoch": 0.03903799233182294,
+      "grad_norm": 25.77384950516741,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.272,
+      "step": 7
+    },
+    {
+      "epoch": 0.04461484837922621,
+      "grad_norm": 24.137113597713526,
+      "learning_rate": 1.944444444444445e-06,
+      "loss": 1.1886,
+      "step": 8
+    },
+    {
+      "epoch": 0.050191704426629485,
+      "grad_norm": 11.629783818575346,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.2781,
+      "step": 9
+    },
+    {
+      "epoch": 0.055768560474032766,
+      "grad_norm": 8.00658343314912,
+      "learning_rate": 2.5e-06,
+      "loss": 1.0554,
+      "step": 10
+    },
+    {
+      "epoch": 0.06134541652143604,
+      "grad_norm": 7.16421136479377,
+      "learning_rate": 2.7777777777777783e-06,
+      "loss": 1.172,
+      "step": 11
+    },
+    {
+      "epoch": 0.06692227256883931,
+      "grad_norm": 4.137822360489128,
+      "learning_rate": 3.055555555555556e-06,
+      "loss": 1.0006,
+      "step": 12
+    },
+    {
+      "epoch": 0.0724991286162426,
+      "grad_norm": 2.9965048555106204,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 0.8589,
+      "step": 13
+    },
+    {
+      "epoch": 0.07807598466364588,
+      "grad_norm": 3.1452698509974435,
+      "learning_rate": 3.6111111111111115e-06,
+      "loss": 1.0973,
+      "step": 14
+    },
+    {
+      "epoch": 0.08365284071104914,
+      "grad_norm": 2.8688258039939702,
+      "learning_rate": 3.88888888888889e-06,
+      "loss": 1.2093,
+      "step": 15
+    },
+    {
+      "epoch": 0.08922969675845242,
+      "grad_norm": 2.0484453697226055,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.9244,
+      "step": 16
+    },
+    {
+      "epoch": 0.0948065528058557,
+      "grad_norm": 2.4395289504901303,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 0.9074,
+      "step": 17
+    },
+    {
+      "epoch": 0.10038340885325897,
+      "grad_norm": 3.3112350184991084,
+      "learning_rate": 4.722222222222222e-06,
+      "loss": 0.9056,
+      "step": 18
+    },
+    {
+      "epoch": 0.10596026490066225,
+      "grad_norm": 2.2238505337460017,
+      "learning_rate": 5e-06,
+      "loss": 0.9156,
+      "step": 19
+    },
+    {
+      "epoch": 0.11153712094806553,
+      "grad_norm": 1.6023122355959452,
+      "learning_rate": 4.999529926121254e-06,
+      "loss": 0.7145,
+      "step": 20
+    },
+    {
+      "epoch": 0.1171139769954688,
+      "grad_norm": 1.5747014721624342,
+      "learning_rate": 4.998119881260576e-06,
+      "loss": 0.9797,
+      "step": 21
+    },
+    {
+      "epoch": 0.12269083304287208,
+      "grad_norm": 1.3008124678483608,
+      "learning_rate": 4.995770395678171e-06,
+      "loss": 0.8005,
+      "step": 22
+    },
+    {
+      "epoch": 0.12826768909027536,
+      "grad_norm": 1.3341513132245302,
+      "learning_rate": 4.99248235291948e-06,
+      "loss": 0.9707,
+      "step": 23
+    },
+    {
+      "epoch": 0.13384454513767863,
+      "grad_norm": 1.2836163377989422,
+      "learning_rate": 4.9882569894829146e-06,
+      "loss": 0.8303,
+      "step": 24
+    },
+    {
+      "epoch": 0.13942140118508192,
+      "grad_norm": 1.5625132921969171,
+      "learning_rate": 4.983095894354858e-06,
+      "loss": 1.012,
+      "step": 25
+    },
+    {
+      "epoch": 0.1449982572324852,
+      "grad_norm": 1.3279470446330688,
+      "learning_rate": 4.977001008412113e-06,
+      "loss": 0.8311,
+      "step": 26
+    },
+    {
+      "epoch": 0.15057511327988846,
+      "grad_norm": 1.1984169005450507,
+      "learning_rate": 4.969974623692023e-06,
+      "loss": 0.701,
+      "step": 27
+    },
+    {
+      "epoch": 0.15615196932729175,
+      "grad_norm": 1.2333632916915551,
+      "learning_rate": 4.962019382530521e-06,
+      "loss": 0.8799,
+      "step": 28
+    },
+    {
+      "epoch": 0.16172882537469502,
+      "grad_norm": 1.1133972779802328,
+      "learning_rate": 4.953138276568462e-06,
+      "loss": 0.75,
+      "step": 29
+    },
+    {
+      "epoch": 0.16730568142209828,
+      "grad_norm": 1.0517214425691086,
+      "learning_rate": 4.943334645626589e-06,
+      "loss": 0.7046,
+      "step": 30
+    },
+    {
+      "epoch": 0.17288253746950158,
+      "grad_norm": 0.9434629605801058,
+      "learning_rate": 4.93261217644956e-06,
+      "loss": 0.6824,
+      "step": 31
+    },
+    {
+      "epoch": 0.17845939351690485,
+      "grad_norm": 1.1847049987820477,
+      "learning_rate": 4.9209749013195155e-06,
+      "loss": 0.8257,
+      "step": 32
+    },
+    {
+      "epoch": 0.1840362495643081,
+      "grad_norm": 1.0458338052848428,
+      "learning_rate": 4.908427196539701e-06,
+      "loss": 0.8103,
+      "step": 33
+    },
+    {
+      "epoch": 0.1896131056117114,
+      "grad_norm": 1.0107452620708213,
+      "learning_rate": 4.894973780788722e-06,
+      "loss": 0.8077,
+      "step": 34
+    },
+    {
+      "epoch": 0.19518996165911467,
+      "grad_norm": 1.0732542601644082,
+      "learning_rate": 4.8806197133460385e-06,
+      "loss": 0.83,
+      "step": 35
+    },
+    {
+      "epoch": 0.20076681770651794,
+      "grad_norm": 1.111873065908315,
+      "learning_rate": 4.865370392189377e-06,
+      "loss": 0.8261,
+      "step": 36
+    },
+    {
+      "epoch": 0.20634367375392124,
+      "grad_norm": 0.9469124459097857,
+      "learning_rate": 4.849231551964771e-06,
+      "loss": 0.7354,
+      "step": 37
+    },
+    {
+      "epoch": 0.2119205298013245,
+      "grad_norm": 0.9890209354758053,
+      "learning_rate": 4.832209261830002e-06,
+      "loss": 0.7614,
+      "step": 38
+    },
+    {
+      "epoch": 0.21749738584872777,
+      "grad_norm": 0.9617476508331165,
+      "learning_rate": 4.814309923172227e-06,
+      "loss": 0.6634,
+      "step": 39
+    },
+    {
+      "epoch": 0.22307424189613106,
+      "grad_norm": 0.8693853556809209,
+      "learning_rate": 4.7955402672006855e-06,
+      "loss": 0.6524,
+      "step": 40
+    },
+    {
+      "epoch": 0.22865109794353433,
+      "grad_norm": 1.1164427987030467,
+      "learning_rate": 4.775907352415367e-06,
+      "loss": 0.9437,
+      "step": 41
+    },
+    {
+      "epoch": 0.2342279539909376,
+      "grad_norm": 1.0342203325734225,
+      "learning_rate": 4.755418561952595e-06,
+      "loss": 0.7833,
+      "step": 42
+    },
+    {
+      "epoch": 0.2398048100383409,
+      "grad_norm": 1.0381130170634878,
+      "learning_rate": 4.734081600808531e-06,
+      "loss": 0.8537,
+      "step": 43
+    },
+    {
+      "epoch": 0.24538166608574416,
+      "grad_norm": 0.980064465437933,
+      "learning_rate": 4.711904492941644e-06,
+      "loss": 0.7711,
+      "step": 44
+    },
+    {
+      "epoch": 0.25095852213314745,
+      "grad_norm": 2.4464904323304255,
+      "learning_rate": 4.688895578255228e-06,
+      "loss": 0.8071,
+      "step": 45
+    },
+    {
+      "epoch": 0.2565353781805507,
+      "grad_norm": 0.9568068666237374,
+      "learning_rate": 4.665063509461098e-06,
+      "loss": 0.7486,
+      "step": 46
+    },
+    {
+      "epoch": 0.262112234227954,
+      "grad_norm": 0.9773834471749688,
+      "learning_rate": 4.640417248825667e-06,
+      "loss": 0.6626,
+      "step": 47
+    },
+    {
+      "epoch": 0.26768909027535726,
+      "grad_norm": 0.9467873226243072,
+      "learning_rate": 4.614966064799603e-06,
+      "loss": 0.7737,
+      "step": 48
+    },
+    {
+      "epoch": 0.2732659463227605,
+      "grad_norm": 0.929090416098371,
+      "learning_rate": 4.588719528532342e-06,
+      "loss": 0.7288,
+      "step": 49
+    },
+    {
+      "epoch": 0.27884280237016384,
+      "grad_norm": 0.9558116358409616,
+      "learning_rate": 4.561687510272767e-06,
+      "loss": 0.7173,
+      "step": 50
+    },
+    {
+      "epoch": 0.2844196584175671,
+      "grad_norm": 1.0358016086386252,
+      "learning_rate": 4.533880175657419e-06,
+      "loss": 0.8558,
+      "step": 51
+    },
+    {
+      "epoch": 0.2899965144649704,
+      "grad_norm": 0.9268356298097264,
+      "learning_rate": 4.50530798188761e-06,
+      "loss": 0.6913,
+      "step": 52
+    },
+    {
+      "epoch": 0.29557337051237365,
+      "grad_norm": 0.9026491423974176,
+      "learning_rate": 4.475981673796899e-06,
+      "loss": 0.6573,
+      "step": 53
+    },
+    {
+      "epoch": 0.3011502265597769,
+      "grad_norm": 0.9341984552378991,
+      "learning_rate": 4.445912279810401e-06,
+      "loss": 0.7178,
+      "step": 54
+    },
+    {
+      "epoch": 0.3067270826071802,
+      "grad_norm": 0.963698636099554,
+      "learning_rate": 4.415111107797445e-06,
+      "loss": 0.672,
+      "step": 55
+    },
+    {
+      "epoch": 0.3123039386545835,
+      "grad_norm": 1.0123866280188825,
+      "learning_rate": 4.3835897408191515e-06,
+      "loss": 0.7958,
+      "step": 56
+    },
+    {
+      "epoch": 0.31788079470198677,
+      "grad_norm": 1.0536090394015367,
+      "learning_rate": 4.351360032772512e-06,
+      "loss": 0.8384,
+      "step": 57
+    },
+    {
+      "epoch": 0.32345765074939004,
+      "grad_norm": 1.005997664037765,
+      "learning_rate": 4.318434103932622e-06,
+      "loss": 0.8511,
+      "step": 58
+    },
+    {
+      "epoch": 0.3290345067967933,
+      "grad_norm": 0.9082165011415732,
+      "learning_rate": 4.284824336394748e-06,
+      "loss": 0.6731,
+      "step": 59
+    },
+    {
+      "epoch": 0.33461136284419657,
+      "grad_norm": 0.9309889749980601,
+      "learning_rate": 4.250543369417921e-06,
+      "loss": 0.7276,
+      "step": 60
+    },
+    {
+      "epoch": 0.34018821889159984,
+      "grad_norm": 1.7819442287605565,
+      "learning_rate": 4.215604094671835e-06,
+      "loss": 0.7831,
+      "step": 61
+    },
+    {
+      "epoch": 0.34576507493900316,
+      "grad_norm": 0.9434498292744896,
+      "learning_rate": 4.180019651388807e-06,
+      "loss": 0.7503,
+      "step": 62
+    },
+    {
+      "epoch": 0.3513419309864064,
+      "grad_norm": 1.0424541071897502,
+      "learning_rate": 4.14380342142266e-06,
+      "loss": 0.9153,
+      "step": 63
+    },
+    {
+      "epoch": 0.3569187870338097,
+      "grad_norm": 0.9753148306326342,
+      "learning_rate": 4.106969024216348e-06,
+      "loss": 0.6555,
+      "step": 64
+    },
+    {
+      "epoch": 0.36249564308121296,
+      "grad_norm": 0.964467277240988,
+      "learning_rate": 4.069530311680247e-06,
+      "loss": 0.7372,
+      "step": 65
+    },
+    {
+      "epoch": 0.3680724991286162,
+      "grad_norm": 1.1418604292487458,
+      "learning_rate": 4.031501362983007e-06,
+      "loss": 0.7585,
+      "step": 66
+    },
+    {
+      "epoch": 0.3736493551760195,
+      "grad_norm": 0.9125259121774503,
+      "learning_rate": 3.992896479256966e-06,
+      "loss": 0.6934,
+      "step": 67
+    },
+    {
+      "epoch": 0.3792262112234228,
+      "grad_norm": 0.9183210408388318,
+      "learning_rate": 3.953730178220067e-06,
+      "loss": 0.6741,
+      "step": 68
+    },
+    {
+      "epoch": 0.3848030672708261,
+      "grad_norm": 0.9841348365534922,
+      "learning_rate": 3.914017188716347e-06,
+      "loss": 0.7713,
+      "step": 69
+    },
+    {
+      "epoch": 0.39037992331822935,
+      "grad_norm": 0.9397953829688301,
+      "learning_rate": 3.8737724451770155e-06,
+      "loss": 0.6898,
+      "step": 70
+    },
+    {
+      "epoch": 0.3959567793656326,
+      "grad_norm": 0.9360968357631917,
+      "learning_rate": 3.833011082004229e-06,
+      "loss": 0.7356,
+      "step": 71
+    },
+    {
+      "epoch": 0.4015336354130359,
+      "grad_norm": 1.0490874310335498,
+      "learning_rate": 3.7917484278796578e-06,
+      "loss": 0.8834,
+      "step": 72
+    },
+    {
+      "epoch": 0.40711049146043915,
+      "grad_norm": 0.8729992951101984,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.6581,
+      "step": 73
+    },
+    {
+      "epoch": 0.4126873475078425,
+      "grad_norm": 0.8526096559762923,
+      "learning_rate": 3.7077814982415966e-06,
+      "loss": 0.6796,
+      "step": 74
+    },
+    {
+      "epoch": 0.41826420355524574,
+      "grad_norm": 0.9123193201559427,
+      "learning_rate": 3.665108799256348e-06,
+      "loss": 0.6747,
+      "step": 75
+    },
+    {
+      "epoch": 0.423841059602649,
+      "grad_norm": 0.8692473859121223,
+      "learning_rate": 3.621997950501156e-06,
+      "loss": 0.6573,
+      "step": 76
+    },
+    {
+      "epoch": 0.4294179156500523,
+      "grad_norm": 0.9141140630813748,
+      "learning_rate": 3.578465164203134e-06,
+      "loss": 0.6013,
+      "step": 77
+    },
+    {
+      "epoch": 0.43499477169745554,
+      "grad_norm": 1.0607296974506348,
+      "learning_rate": 3.5345268112628485e-06,
+      "loss": 0.897,
+      "step": 78
+    },
+    {
+      "epoch": 0.44057162774485886,
+      "grad_norm": 1.027907705537933,
+      "learning_rate": 3.4901994150978926e-06,
+      "loss": 0.8139,
+      "step": 79
+    },
+    {
+      "epoch": 0.44614848379226213,
+      "grad_norm": 0.8964908897959806,
+      "learning_rate": 3.4454996454291066e-06,
+      "loss": 0.682,
+      "step": 80
+    },
+    {
+      "epoch": 0.4517253398396654,
+      "grad_norm": 0.9696808820116304,
+      "learning_rate": 3.400444312011776e-06,
+      "loss": 0.7677,
+      "step": 81
+    },
+    {
+      "epoch": 0.45730219588706866,
+      "grad_norm": 0.9538347785493502,
+      "learning_rate": 3.3550503583141726e-06,
+      "loss": 0.7707,
+      "step": 82
+    },
+    {
+      "epoch": 0.46287905193447193,
+      "grad_norm": 0.8834434922285562,
+      "learning_rate": 3.3093348551458033e-06,
+      "loss": 0.7254,
+      "step": 83
+    },
+    {
+      "epoch": 0.4684559079818752,
+      "grad_norm": 0.9664583802329054,
+      "learning_rate": 3.2633149942377835e-06,
+      "loss": 0.6009,
+      "step": 84
+    },
+    {
+      "epoch": 0.4740327640292785,
+      "grad_norm": 0.9989900249921821,
+      "learning_rate": 3.217008081777726e-06,
+      "loss": 0.7277,
+      "step": 85
+    },
+    {
+      "epoch": 0.4796096200766818,
+      "grad_norm": 0.9641224372984417,
+      "learning_rate": 3.1704315319015936e-06,
+      "loss": 0.7693,
+      "step": 86
+    },
+    {
+      "epoch": 0.48518647612408505,
+      "grad_norm": 0.8563738741272415,
+      "learning_rate": 3.1236028601449534e-06,
+      "loss": 0.5502,
+      "step": 87
+    },
+    {
+      "epoch": 0.4907633321714883,
+      "grad_norm": 0.9814456923681252,
+      "learning_rate": 3.0765396768561005e-06,
+      "loss": 0.7591,
+      "step": 88
+    },
+    {
+      "epoch": 0.4963401882188916,
+      "grad_norm": 1.0031797145449588,
+      "learning_rate": 3.0292596805735275e-06,
+      "loss": 0.7336,
+      "step": 89
+    },
+    {
+      "epoch": 0.5019170442662949,
+      "grad_norm": 1.0307972932412588,
+      "learning_rate": 2.9817806513702247e-06,
+      "loss": 0.8728,
+      "step": 90
+    },
+    {
+      "epoch": 0.5074939003136981,
+      "grad_norm": 0.9121639360068265,
+      "learning_rate": 2.9341204441673267e-06,
+      "loss": 0.7234,
+      "step": 91
+    },
+    {
+      "epoch": 0.5130707563611014,
+      "grad_norm": 0.9266082791067043,
+      "learning_rate": 2.8862969820196017e-06,
+      "loss": 0.6637,
+      "step": 92
+    },
+    {
+      "epoch": 0.5186476124085047,
+      "grad_norm": 0.9817424775807924,
+      "learning_rate": 2.8383282493753282e-06,
+      "loss": 0.818,
+      "step": 93
+    },
+    {
+      "epoch": 0.524224468455908,
+      "grad_norm": 0.9290655450825701,
+      "learning_rate": 2.7902322853130758e-06,
+      "loss": 0.7372,
+      "step": 94
+    },
+    {
+      "epoch": 0.5298013245033113,
+      "grad_norm": 0.9630341129207757,
+      "learning_rate": 2.742027176757948e-06,
+      "loss": 0.786,
+      "step": 95
+    },
+    {
+      "epoch": 0.5353781805507145,
+      "grad_norm": 0.8736837998218376,
+      "learning_rate": 2.6937310516798276e-06,
+      "loss": 0.6546,
+      "step": 96
+    },
+    {
+      "epoch": 0.5409550365981178,
+      "grad_norm": 0.970695862336814,
+      "learning_rate": 2.6453620722761897e-06,
+      "loss": 0.6716,
+      "step": 97
+    },
+    {
+      "epoch": 0.546531892645521,
+      "grad_norm": 0.9311590205600201,
+      "learning_rate": 2.5969384281420425e-06,
+      "loss": 0.6955,
+      "step": 98
+    },
+    {
+      "epoch": 0.5521087486929244,
+      "grad_norm": 0.9022156745489164,
+      "learning_rate": 2.548478329429561e-06,
+      "loss": 0.6765,
+      "step": 99
+    },
+    {
+      "epoch": 0.5576856047403277,
+      "grad_norm": 0.9321595225209163,
+      "learning_rate": 2.5e-06,
+      "loss": 0.7459,
+      "step": 100
+    },
+    {
+      "epoch": 0.5632624607877309,
+      "grad_norm": 0.8642803835512484,
+      "learning_rate": 2.4515216705704396e-06,
+      "loss": 0.6295,
+      "step": 101
+    },
+    {
+      "epoch": 0.5688393168351342,
+      "grad_norm": 0.8770432551457372,
+      "learning_rate": 2.403061571857958e-06,
+      "loss": 0.5756,
+      "step": 102
+    },
+    {
+      "epoch": 0.5744161728825374,
+      "grad_norm": 0.986644075495802,
+      "learning_rate": 2.3546379277238107e-06,
+      "loss": 0.7433,
+      "step": 103
+    },
+    {
+      "epoch": 0.5799930289299408,
+      "grad_norm": 0.9151759455914666,
+      "learning_rate": 2.3062689483201732e-06,
+      "loss": 0.6835,
+      "step": 104
+    },
+    {
+      "epoch": 0.585569884977344,
+      "grad_norm": 1.0566592626672804,
+      "learning_rate": 2.2579728232420524e-06,
+      "loss": 0.7049,
+      "step": 105
+    },
+    {
+      "epoch": 0.5911467410247473,
+      "grad_norm": 0.8911833907323385,
+      "learning_rate": 2.2097677146869242e-06,
+      "loss": 0.6252,
+      "step": 106
+    },
+    {
+      "epoch": 0.5967235970721506,
+      "grad_norm": 3.583992947348307,
+      "learning_rate": 2.161671750624673e-06,
+      "loss": 0.7175,
+      "step": 107
+    },
+    {
+      "epoch": 0.6023004531195538,
+      "grad_norm": 0.8470926199178831,
+      "learning_rate": 2.113703017980399e-06,
+      "loss": 0.6039,
+      "step": 108
+    },
+    {
+      "epoch": 0.6078773091669571,
+      "grad_norm": 0.9202011923092919,
+      "learning_rate": 2.0658795558326745e-06,
+      "loss": 0.675,
+      "step": 109
+    },
+    {
+      "epoch": 0.6134541652143604,
+      "grad_norm": 0.991676719260929,
+      "learning_rate": 2.0182193486297757e-06,
+      "loss": 0.8416,
+      "step": 110
+    },
+    {
+      "epoch": 0.6190310212617637,
+      "grad_norm": 0.9920121314417771,
+      "learning_rate": 1.970740319426474e-06,
+      "loss": 0.7869,
+      "step": 111
+    },
+    {
+      "epoch": 0.624607877309167,
+      "grad_norm": 0.9147914111270489,
+      "learning_rate": 1.9234603231439e-06,
+      "loss": 0.6715,
+      "step": 112
+    },
+    {
+      "epoch": 0.6301847333565702,
+      "grad_norm": 0.9960901454429568,
+      "learning_rate": 1.876397139855047e-06,
+      "loss": 0.8459,
+      "step": 113
+    },
+    {
+      "epoch": 0.6357615894039735,
+      "grad_norm": 0.8398771049626784,
+      "learning_rate": 1.8295684680984064e-06,
+      "loss": 0.6327,
+      "step": 114
+    },
+    {
+      "epoch": 0.6413384454513767,
+      "grad_norm": 0.8848277584910325,
+      "learning_rate": 1.7829919182222752e-06,
+      "loss": 0.6674,
+      "step": 115
+    },
+    {
+      "epoch": 0.6469153014987801,
+      "grad_norm": 0.9599403253441103,
+      "learning_rate": 1.7366850057622176e-06,
+      "loss": 0.7381,
+      "step": 116
+    },
+    {
+      "epoch": 0.6524921575461834,
+      "grad_norm": 0.8633918886732347,
+      "learning_rate": 1.6906651448541977e-06,
+      "loss": 0.5713,
+      "step": 117
+    },
+    {
+      "epoch": 0.6580690135935866,
+      "grad_norm": 0.9564730887800509,
+      "learning_rate": 1.6449496416858285e-06,
+      "loss": 0.7964,
+      "step": 118
+    },
+    {
+      "epoch": 0.6636458696409899,
+      "grad_norm": 0.9220167090814314,
+      "learning_rate": 1.5995556879882246e-06,
+      "loss": 0.7074,
+      "step": 119
+    },
+    {
+      "epoch": 0.6692227256883931,
+      "grad_norm": 0.9412177200866909,
+      "learning_rate": 1.5545003545708942e-06,
+      "loss": 0.6798,
+      "step": 120
+    },
+    {
+      "epoch": 0.6747995817357965,
+      "grad_norm": 0.8799708797193134,
+      "learning_rate": 1.509800584902108e-06,
+      "loss": 0.636,
+      "step": 121
+    },
+    {
+      "epoch": 0.6803764377831997,
+      "grad_norm": 0.8746008313087483,
+      "learning_rate": 1.4654731887371524e-06,
+      "loss": 0.6517,
+      "step": 122
+    },
+    {
+      "epoch": 0.685953293830603,
+      "grad_norm": 0.8622866280586909,
+      "learning_rate": 1.421534835796867e-06,
+      "loss": 0.5685,
+      "step": 123
+    },
+    {
+      "epoch": 0.6915301498780063,
+      "grad_norm": 0.9161469277312331,
+      "learning_rate": 1.3780020494988447e-06,
+      "loss": 0.7142,
+      "step": 124
+    },
+    {
+      "epoch": 0.6971070059254095,
+      "grad_norm": 0.8834589774119394,
+      "learning_rate": 1.3348912007436538e-06,
+      "loss": 0.6794,
+      "step": 125
+    },
+    {
+      "epoch": 0.7026838619728129,
+      "grad_norm": 0.8420150113363432,
+      "learning_rate": 1.2922185017584038e-06,
+      "loss": 0.5548,
+      "step": 126
+    },
+    {
+      "epoch": 0.7082607180202161,
+      "grad_norm": 0.9186571271373966,
+      "learning_rate": 1.2500000000000007e-06,
+      "loss": 0.7093,
+      "step": 127
+    },
+    {
+      "epoch": 0.7138375740676194,
+      "grad_norm": 0.9024224044680166,
+      "learning_rate": 1.2082515721203429e-06,
+      "loss": 0.601,
+      "step": 128
+    },
+    {
+      "epoch": 0.7194144301150227,
+      "grad_norm": 0.8730115171814332,
+      "learning_rate": 1.1669889179957725e-06,
+      "loss": 0.6485,
+      "step": 129
+    },
+    {
+      "epoch": 0.7249912861624259,
+      "grad_norm": 2.560680193595368,
+      "learning_rate": 1.1262275548229852e-06,
+      "loss": 0.681,
+      "step": 130
+    },
+    {
+      "epoch": 0.7305681422098292,
+      "grad_norm": 0.8433376742578463,
+      "learning_rate": 1.085982811283654e-06,
+      "loss": 0.6025,
+      "step": 131
+    },
+    {
+      "epoch": 0.7361449982572325,
+      "grad_norm": 0.9000811460890688,
+      "learning_rate": 1.0462698217799333e-06,
+      "loss": 0.7098,
+      "step": 132
+    },
+    {
+      "epoch": 0.7417218543046358,
+      "grad_norm": 0.9015484414513791,
+      "learning_rate": 1.0071035207430352e-06,
+      "loss": 0.6939,
+      "step": 133
+    },
+    {
+      "epoch": 0.747298710352039,
+      "grad_norm": 0.924647234962446,
+      "learning_rate": 9.68498637016993e-07,
+      "loss": 0.7219,
+      "step": 134
+    },
+    {
+      "epoch": 0.7528755663994423,
+      "grad_norm": 0.9622683692067883,
+      "learning_rate": 9.304696883197542e-07,
+      "loss": 0.7445,
+      "step": 135
+    },
+    {
+      "epoch": 0.7584524224468456,
+      "grad_norm": 1.0018020723323282,
+      "learning_rate": 8.930309757836517e-07,
+      "loss": 0.7285,
+      "step": 136
+    },
+    {
+      "epoch": 0.7640292784942488,
+      "grad_norm": 1.0034101578791559,
+      "learning_rate": 8.561965785773413e-07,
+      "loss": 0.647,
+      "step": 137
+    },
+    {
+      "epoch": 0.7696061345416522,
+      "grad_norm": 0.865650213772322,
+      "learning_rate": 8.19980348611194e-07,
+      "loss": 0.6588,
+      "step": 138
+    },
+    {
+      "epoch": 0.7751829905890554,
+      "grad_norm": 0.9237880174335488,
+      "learning_rate": 7.843959053281663e-07,
+      "loss": 0.738,
+      "step": 139
+    },
+    {
+      "epoch": 0.7807598466364587,
+      "grad_norm": 0.992180072952141,
+      "learning_rate": 7.494566305820788e-07,
+      "loss": 0.7533,
+      "step": 140
+    },
+    {
+      "epoch": 0.786336702683862,
+      "grad_norm": 0.8845919723729968,
+      "learning_rate": 7.151756636052529e-07,
+      "loss": 0.6062,
+      "step": 141
+    },
+    {
+      "epoch": 0.7919135587312652,
+      "grad_norm": 0.9575278544789321,
+      "learning_rate": 6.815658960673782e-07,
+      "loss": 0.7661,
+      "step": 142
+    },
+    {
+      "epoch": 0.7974904147786686,
+      "grad_norm": 1.060097465810906,
+      "learning_rate": 6.48639967227489e-07,
+      "loss": 0.7093,
+      "step": 143
+    },
+    {
+      "epoch": 0.8030672708260718,
+      "grad_norm": 1.1137158210751135,
+      "learning_rate": 6.164102591808482e-07,
+      "loss": 0.6516,
+      "step": 144
+    },
+    {
+      "epoch": 0.8086441268734751,
+      "grad_norm": 0.9467474421643487,
+      "learning_rate": 5.848888922025553e-07,
+      "loss": 0.7106,
+      "step": 145
+    },
+    {
+      "epoch": 0.8142209829208783,
+      "grad_norm": 0.977712019438005,
+      "learning_rate": 5.540877201896e-07,
+      "loss": 0.6485,
+      "step": 146
+    },
+    {
+      "epoch": 0.8197978389682816,
+      "grad_norm": 1.2725548643418227,
+      "learning_rate": 5.240183262031021e-07,
+      "loss": 0.7106,
+      "step": 147
+    },
+    {
+      "epoch": 0.825374695015685,
+      "grad_norm": 0.9531375340902994,
+      "learning_rate": 4.946920181123904e-07,
+      "loss": 0.6352,
+      "step": 148
+    },
+    {
+      "epoch": 0.8309515510630882,
+      "grad_norm": 0.8239496228158747,
+      "learning_rate": 4.661198243425813e-07,
+      "loss": 0.5812,
+      "step": 149
+    },
+    {
+      "epoch": 0.8365284071104915,
+      "grad_norm": 1.4768742600927571,
+      "learning_rate": 4.383124897272331e-07,
+      "loss": 0.825,
+      "step": 150
+    },
+    {
+      "epoch": 0.8421052631578947,
+      "grad_norm": 0.8936174846742114,
+      "learning_rate": 4.1128047146765936e-07,
+      "loss": 0.7137,
+      "step": 151
+    },
+    {
+      "epoch": 0.847682119205298,
+      "grad_norm": 0.868290680328461,
+      "learning_rate": 3.8503393520039734e-07,
+      "loss": 0.646,
+      "step": 152
+    },
+    {
+      "epoch": 0.8532589752527013,
+      "grad_norm": 0.9170777878398306,
+      "learning_rate": 3.595827511743341e-07,
+      "loss": 0.6338,
+      "step": 153
+    },
+    {
+      "epoch": 0.8588358313001045,
+      "grad_norm": 0.8709479986895221,
+      "learning_rate": 3.3493649053890325e-07,
+      "loss": 0.6942,
+      "step": 154
+    },
+    {
+      "epoch": 0.8644126873475079,
+      "grad_norm": 1.015273029250277,
+      "learning_rate": 3.111044217447731e-07,
+      "loss": 0.8455,
+      "step": 155
+    },
+    {
+      "epoch": 0.8699895433949111,
+      "grad_norm": 1.8953728977728321,
+      "learning_rate": 2.880955070583555e-07,
+      "loss": 0.8089,
+      "step": 156
+    },
+    {
+      "epoch": 0.8755663994423144,
+      "grad_norm": 1.0266628340926212,
+      "learning_rate": 2.6591839919146963e-07,
+      "loss": 0.6747,
+      "step": 157
+    },
+    {
+      "epoch": 0.8811432554897177,
+      "grad_norm": 1.0638475327851682,
+      "learning_rate": 2.445814380474057e-07,
+      "loss": 0.6979,
+      "step": 158
+    },
+    {
+      "epoch": 0.8867201115371209,
+      "grad_norm": 0.9287481759641896,
+      "learning_rate": 2.240926475846336e-07,
+      "loss": 0.7963,
+      "step": 159
+    },
+    {
+      "epoch": 0.8922969675845243,
+      "grad_norm": 0.8785430203193436,
+      "learning_rate": 2.044597327993153e-07,
+      "loss": 0.6534,
+      "step": 160
+    },
+    {
+      "epoch": 0.8978738236319275,
+      "grad_norm": 0.953415594296327,
+      "learning_rate": 1.8569007682777417e-07,
+      "loss": 0.7474,
+      "step": 161
+    },
+    {
+      "epoch": 0.9034506796793308,
+      "grad_norm": 0.9294478803532011,
+      "learning_rate": 1.6779073816999864e-07,
+      "loss": 0.7906,
+      "step": 162
+    },
+    {
+      "epoch": 0.909027535726734,
+      "grad_norm": 0.8384613909869523,
+      "learning_rate": 1.507684480352292e-07,
+      "loss": 0.6377,
+      "step": 163
+    },
+    {
+      "epoch": 0.9146043917741373,
+      "grad_norm": 0.8835908163025235,
+      "learning_rate": 1.3462960781062433e-07,
+      "loss": 0.6392,
+      "step": 164
+    },
+    {
+      "epoch": 0.9201812478215406,
+      "grad_norm": 0.8449058090284122,
+      "learning_rate": 1.1938028665396172e-07,
+      "loss": 0.5656,
+      "step": 165
+    },
+    {
+      "epoch": 0.9257581038689439,
+      "grad_norm": 0.9392723321505706,
+      "learning_rate": 1.0502621921127776e-07,
+      "loss": 0.7239,
+      "step": 166
+    },
+    {
+      "epoch": 0.9313349599163472,
+      "grad_norm": 0.8758199104024277,
+      "learning_rate": 9.157280346029918e-08,
+      "loss": 0.6666,
+      "step": 167
+    },
+    {
+      "epoch": 0.9369118159637504,
+      "grad_norm": 0.8830370044979928,
+      "learning_rate": 7.902509868048552e-08,
+      "loss": 0.6846,
+      "step": 168
+    },
+    {
+      "epoch": 0.9424886720111537,
+      "grad_norm": 0.8870739682602913,
+      "learning_rate": 6.738782355044048e-08,
+      "loss": 0.7071,
+      "step": 169
+    },
+    {
+      "epoch": 0.948065528058557,
+      "grad_norm": 0.8732031194960946,
+      "learning_rate": 5.6665354373411085e-08,
+      "loss": 0.7037,
+      "step": 170
+    },
+    {
+      "epoch": 0.9536423841059603,
+      "grad_norm": 0.9251119129299412,
+      "learning_rate": 4.6861723431538273e-08,
+      "loss": 0.6949,
+      "step": 171
+    },
+    {
+      "epoch": 0.9592192401533636,
+      "grad_norm": 0.8254069704702977,
+      "learning_rate": 3.798061746947995e-08,
+      "loss": 0.5747,
+      "step": 172
+    },
+    {
+      "epoch": 0.9647960962007668,
+      "grad_norm": 0.8556828230063313,
+      "learning_rate": 3.0025376307977474e-08,
+      "loss": 0.6367,
+      "step": 173
+    },
+    {
+      "epoch": 0.9703729522481701,
+      "grad_norm": 0.8964787284563904,
+      "learning_rate": 2.299899158788671e-08,
+      "loss": 0.6943,
+      "step": 174
+    },
+    {
+      "epoch": 0.9759498082955733,
+      "grad_norm": 0.8529908965639459,
+      "learning_rate": 1.6904105645142443e-08,
+      "loss": 0.6373,
+      "step": 175
+    },
+    {
+      "epoch": 0.9815266643429766,
+      "grad_norm": 0.8934738534392561,
+      "learning_rate": 1.1743010517085428e-08,
+      "loss": 0.6968,
+      "step": 176
+    },
+    {
+      "epoch": 0.98710352039038,
+      "grad_norm": 0.9302061985515149,
+      "learning_rate": 7.517647080519941e-09,
+      "loss": 0.7773,
+      "step": 177
+    },
+    {
+      "epoch": 0.9926803764377832,
+      "grad_norm": 0.9858177539703182,
+      "learning_rate": 4.229604321829561e-09,
+      "loss": 0.7393,
+      "step": 178
+    },
+    {
+      "epoch": 0.9982572324851865,
+      "grad_norm": 0.9326264974645483,
+      "learning_rate": 1.8801187394248966e-09,
+      "loss": 0.7246,
+      "step": 179
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.9326264974645483,
+      "learning_rate": 4.700738787466463e-10,
+      "loss": 0.9,
+      "step": 180
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 180,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 27643248377856.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e527706eb629c68e33b0663c67e6d43111ad105b3f92d26bc491f29fe51f24a0
+size 7480

zero_to_fp32.py

@@ -0,0 +1,760 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import gc
+import json
+import numpy as np
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device, weights_only=False)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in tqdm(files, desc='Loading checkpoint shards'):
+        state_dict = torch.load(f, map_location=device, mmap=True, weights_only=False)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+class GatheredTensor:
+    """
+    A pseudo tensor that collects partitioned weights.
+    It is more memory efficient when there are multiple groups.
+    """
+
+    def __init__(self, flat_groups, flat_groups_offset, offset, partitioned_numel, shape):
+        self.flat_groups = flat_groups
+        self.flat_groups_offset = flat_groups_offset
+        self.offset = offset
+        self.partitioned_numel = partitioned_numel
+        self.shape = shape
+        self.dtype = self.flat_groups[0][0].dtype
+
+    def contiguous(self):
+        """
+        Merge partitioned weights from flat_groups into a single tensor.
+        """
+        end_idx = self.offset + self.partitioned_numel
+        world_size = len(self.flat_groups)
+        pad_flat_param_chunks = []
+
+        for rank_i in range(world_size):
+            # for each rank, we need to collect weights from related group/groups
+            flat_groups_at_rank_i = self.flat_groups[rank_i]
+            start_group_id = None
+            end_group_id = None
+            for group_id in range(len(self.flat_groups_offset)):
+                if self.flat_groups_offset[group_id] <= self.offset < self.flat_groups_offset[group_id + 1]:
+                    start_group_id = group_id
+                if self.flat_groups_offset[group_id] < end_idx <= self.flat_groups_offset[group_id + 1]:
+                    end_group_id = group_id
+                    break
+            # collect weights from related group/groups
+            for group_id in range(start_group_id, end_group_id + 1):
+                flat_tensor = flat_groups_at_rank_i[group_id]
+                start_offset = self.offset - self.flat_groups_offset[group_id]
+                end_offset = min(end_idx, self.flat_groups_offset[group_id + 1]) - self.flat_groups_offset[group_id]
+                pad_flat_param_chunks.append(flat_tensor[start_offset:end_offset])
+
+        # collect weights from all ranks
+        pad_flat_param = torch.cat(pad_flat_param_chunks, dim=0)
+        param = pad_flat_param[:self.shape.numel()].view(self.shape).contiguous()
+        return param
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = sum([flat_group.numel() for flat_group in fp32_flat_groups[0]]) * world_size
+
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    flat_groups_offset = [0] + list(np.cumsum([flat_tensor.numel() for flat_tensor in fp32_flat_groups[0]]))
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering sharded weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # memory efficient tensor
+        tensor = GatheredTensor(fp32_flat_groups, flat_groups_offset, offset, partitioned_numel, shape)
+        state_dict[name] = tensor
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def to_torch_tensor(state_dict, return_empty_tensor=False):
+    """
+    Convert state_dict of GatheredTensor to torch tensor
+    """
+    torch_state_dict = {}
+    converted_tensors = {}
+    for name, tensor in state_dict.items():
+        tensor_id = id(tensor)
+        if tensor_id in converted_tensors:  # shared tensors
+            shared_tensor = torch_state_dict[converted_tensors[tensor_id]]
+            torch_state_dict[name] = shared_tensor
+        else:
+            converted_tensors[tensor_id] = name
+            if return_empty_tensor:
+                torch_state_dict[name] = torch.empty(tensor.shape, dtype=tensor.dtype)
+            else:
+                torch_state_dict[name] = tensor.contiguous()
+    return torch_state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                             tag=None,
+                                             exclude_frozen_parameters=False,
+                                             lazy_mode=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+        - ``lazy_mode``: get state_dict in lazy mode. It returns a dict of pesduo tensor instead of torch tensor, which is more memory efficient.
+          Convert the pesduo tensor to torch tensor by ``.contiguous()``
+
+    Returns:
+        - pytorch ``state_dict``
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    Note: the above usage may not work if your application doesn't have sufficient free CPU memory.
+    You may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint. Or you can load state_dict in lazy mode ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, lazy_mode=True) # not on cpu
+        for name, lazy_tensor in state_dict.item():
+            tensor = lazy_tensor.contiguous()  # to cpu
+            print(name, tensor)
+            # del tensor to release memory if it no longer in use
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    state_dict = _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+    if lazy_mode:
+        return state_dict
+    else:
+        return to_torch_tensor(state_dict)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir,
+                                                          tag,
+                                                          exclude_frozen_parameters,
+                                                          lazy_mode=True)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        # an memory-efficient approach for sharding
+        empty_state_dict = to_torch_tensor(state_dict, return_empty_tensor=True)
+        state_dict_split = split_torch_state_dict_into_shards(empty_state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model by shard
+    os.makedirs(output_dir, exist_ok=True)
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard_state_dict = {tensor_name: state_dict[tensor_name] for tensor_name in tensors}
+        shard_state_dict = to_torch_tensor(shard_state_dict)
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard_state_dict, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard_state_dict, output_path)
+        # release the memory of current shard
+        for tensor_name in list(shard_state_dict.keys()):
+            del state_dict[tensor_name]
+            del shard_state_dict[tensor_name]
+        del shard_state_dict
+        gc.collect()
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)