Upload 11 files

.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 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.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 +1,38 @@
+{
+  "architectures": [
+    "Qwen3MoeForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "decoder_sparse_step": 1,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 28,
+  "mlp_only_layers": [],
+  "model_type": "qwen3_moe",
+  "moe_intermediate_size": 3072,
+  "norm_topk_prob": true,
+  "num_attention_heads": 16,
+  "num_experts": 3,
+  "num_experts_per_tok": 1,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "transformers_version": "4.52.4"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e893bd29c30948c66b7bb6da4ede05684aa35eea99c8b2a07bfd8a9aa56e1b17
+size 2249296512

model_params.txt

@@ -0,0 +1,510 @@
+Model Parameter Distribution:
+------------------------------------------------------------
+model.embed_tokens.weight: 155,582,464 parameters, device cuda:0
+model.layers.0.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.0.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.0.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.0.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.0.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.0.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.0.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.0.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.0.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.0.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.0.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.0.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.0.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.0.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.0.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.0.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.0.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.0.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.1.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.1.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.1.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.1.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.1.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.1.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.1.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.1.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.1.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.1.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.1.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.1.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.1.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.1.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.1.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.1.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.1.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.1.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.2.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.2.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.2.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.2.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.2.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.2.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.2.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.2.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.2.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.2.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.2.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.2.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.2.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.2.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.2.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.2.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.2.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.2.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.3.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.3.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.3.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.3.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.3.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.3.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.3.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.3.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.3.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.3.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.3.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.3.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.3.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.3.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.3.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.3.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.3.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.3.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.4.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.4.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.4.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.4.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.4.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.4.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.4.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.4.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.4.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.4.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.4.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.4.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.4.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.4.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.4.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.4.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.4.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.4.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.5.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.5.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.5.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.5.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.5.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.5.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.5.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.5.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.5.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.5.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.5.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.5.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.5.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.5.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.5.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.5.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.5.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.5.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.6.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.6.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.6.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.6.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.6.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.6.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.6.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.6.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.6.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.6.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.6.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.6.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.6.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.6.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.6.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.6.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.6.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.6.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.7.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.7.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.7.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.7.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.7.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.7.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.7.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.7.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.7.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.7.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.7.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.7.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.7.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.7.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.7.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.7.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.7.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.7.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.8.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.8.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.8.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.8.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.8.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.8.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.8.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.8.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.8.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.8.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.8.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.8.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.8.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.8.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.8.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.8.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.8.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.8.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.9.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.9.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.9.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.9.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.9.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.9.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.9.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.9.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.9.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.9.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.9.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.9.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.9.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.9.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.9.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.9.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.9.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.9.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.10.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.10.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.10.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.10.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.10.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.10.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.10.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.10.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.10.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.10.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.10.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.10.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.10.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.10.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.10.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.10.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.10.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.10.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.11.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.11.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.11.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.11.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.11.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.11.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.11.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.11.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.11.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.11.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.11.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.11.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.11.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.11.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.11.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.11.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.11.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.11.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.12.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.12.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.12.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.12.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.12.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.12.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.12.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.12.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.12.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.12.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.12.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.12.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.12.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.12.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.12.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.12.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.12.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.12.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.13.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.13.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.13.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.13.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.13.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.13.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.13.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.13.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.13.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.13.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.13.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.13.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.13.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.13.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.13.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.13.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.13.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.13.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.14.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.14.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.14.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.14.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.14.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.14.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.14.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.14.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.14.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.14.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.14.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.14.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.14.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.14.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.14.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.14.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.14.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.14.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.15.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.15.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.15.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.15.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.15.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.15.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.15.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.15.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.15.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.15.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.15.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.15.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.15.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.15.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.15.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.15.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.15.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.15.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.16.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.16.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.16.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.16.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.16.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.16.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.16.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.16.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.16.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.16.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.16.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.16.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.16.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.16.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.16.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.16.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.16.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.16.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.17.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.17.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.17.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.17.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.17.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.17.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.17.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.17.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.17.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.17.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.17.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.17.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.17.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.17.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.17.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.17.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.17.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.17.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.18.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.18.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.18.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.18.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.18.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.18.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.18.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.18.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.18.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.18.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.18.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.18.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.18.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.18.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.18.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.18.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.18.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.18.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.19.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.19.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.19.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.19.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.19.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.19.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.19.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.19.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.19.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.19.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.19.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.19.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.19.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.19.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.19.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.19.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.19.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.19.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.20.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.20.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.20.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.20.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.20.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.20.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.20.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.20.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.20.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.20.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.20.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.20.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.20.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.20.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.20.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.20.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.20.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.20.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.21.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.21.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.21.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.21.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.21.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.21.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.21.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.21.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.21.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.21.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.21.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.21.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.21.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.21.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.21.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.21.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.21.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.21.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.22.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.22.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.22.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.22.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.22.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.22.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.22.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.22.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.22.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.22.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.22.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.22.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.22.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.22.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.22.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.22.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.22.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.22.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.23.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.23.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.23.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.23.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.23.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.23.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.23.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.23.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.23.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.23.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.23.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.23.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.23.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.23.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.23.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.23.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.23.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.23.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.24.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.24.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.24.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.24.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.24.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.24.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.24.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.24.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.24.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.24.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.24.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.24.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.24.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.24.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.24.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.24.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.24.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.24.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.25.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.25.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.25.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.25.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.25.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.25.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.25.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.25.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.25.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.25.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.25.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.25.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.25.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.25.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.25.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.25.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.25.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.25.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.26.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.26.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.26.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.26.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.26.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.26.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.26.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.26.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.26.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.26.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.26.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.26.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.26.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.26.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.26.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.26.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.26.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.26.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.27.self_attn.q_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.27.self_attn.k_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.27.self_attn.v_proj.weight: 1,048,576 parameters, device cuda:0
+model.layers.27.self_attn.o_proj.weight: 2,097,152 parameters, device cuda:0
+model.layers.27.self_attn.q_norm.weight: 128 parameters, device cuda:0
+model.layers.27.self_attn.k_norm.weight: 128 parameters, device cuda:0
+model.layers.27.mlp.gate.weight: 3,072 parameters, device cuda:0
+model.layers.27.mlp.experts.0.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.27.mlp.experts.0.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.27.mlp.experts.0.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.27.mlp.experts.1.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.27.mlp.experts.1.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.27.mlp.experts.1.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.27.mlp.experts.2.gate_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.27.mlp.experts.2.up_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.27.mlp.experts.2.down_proj.weight: 3,145,728 parameters, device cuda:0
+model.layers.27.input_layernorm.weight: 1,024 parameters, device cuda:0
+model.layers.27.post_attention_layernorm.weight: 1,024 parameters, device cuda:0
+model.norm.weight: 1,024 parameters, device cuda:0
+------------------------------------------------------------
+Total Model Parameter Count:1,124,618,240

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 +1,239 @@
+{
+  "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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}