Upload merged model and tokenizer

chat_template.jinja

@@ -1,37 +1,4 @@
-{{- bos_token -}}
-{%- set system_prompt = "" -%}
-{%- set ns = namespace(system_prompt="") -%}
-{%- if messages[0]["role"] == "system" -%}
-	{%- set ns.system_prompt = messages[0]["content"] -%}
-	{%- set messages = messages[1:] -%}
-{%- endif -%}
-{%- if tools -%}
-	{%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: <|tool_list_start|>[" -%}
-	{%- for tool in tools -%}
-		{%- if tool is not string -%}
-            {%- set tool = tool | tojson -%}
-		{%- endif -%}
-		{%- set ns.system_prompt = ns.system_prompt + tool -%}
-        {%- if not loop.last -%}
-            {%- set ns.system_prompt = ns.system_prompt + ", " -%}
-        {%- endif -%}
-	{%- endfor -%}
-	{%- set ns.system_prompt = ns.system_prompt + "]<|tool_list_end|>" -%}
-{%- endif -%}
-{%- if ns.system_prompt -%}
-	{{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
-{%- endif -%}
-{%- for message in messages -%}
-	{{- "<|im_start|>" + message["role"] + "\n" -}}
-	{%- set content = message["content"] -%}
-	{%- if content is not string -%}
-		{%- set content = content | tojson -%}
-	{%- endif -%}
-	{%- if message["role"] == "tool" -%}
-		{%- set content = "<|tool_response_start|>" + content + "<|tool_response_end|>" -%}
-	{%- endif -%}
-	{{- content + "<|im_end|>\n" -}}
-{%- endfor -%}
-{%- if add_generation_prompt -%}
-	{{- "<|im_start|>assistant\n" -}}
-{%- endif -%}
+{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -40,7 +40,7 @@
     "full_attention",
     "conv"
   ],
-  "max_position_embeddings": 128000,
+  "max_position_embeddings": 32768,
   "model_type": "lfm2",
   "norm_eps": 1e-05,
   "num_attention_heads": 24,
@@ -48,9 +48,33 @@
   "num_hidden_layers": 16,
   "num_key_value_heads": 8,
   "pad_token_id": 0,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": [
+      "embed_tokens",
+      "embedding",
+      "lm_head",
+      "multi_modal_projector",
+      "merger",
+      "modality_projection",
+      "conv"
+    ],
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
   "rope_theta": 1000000.0,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.56.0.dev0",
+  "unsloth_fixed": true,
   "use_cache": true,
   "use_pos_enc": true,
   "vocab_size": 65536

generation_config.json

@@ -2,6 +2,7 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 7,
+  "max_length": 32768,
   "pad_token_id": 0,
   "transformers_version": "4.56.0.dev0"
 }

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b587caa19bb77cfb9d5ca99c17a0ec883dab378b53270735566e388302bcfc83
-size 1484995328
+oid sha256:7faf70029ed5c2b0a717819593f7b44502c60729e12e3b9bfff6b75fc520ab08
+size 672779705

tokenizer_config.json

@@ -4064,15 +4064,13 @@
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
   "legacy": false,
-  "model_input_names": [
-    "input_ids",
-    "attention_mask"
-  ],
-  "model_max_length": 1000000000000000019884624838656,
+  "model_max_length": 32768,
   "pad_token": "<|pad|>",
+  "padding_side": "left",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": null,
   "use_default_system_prompt": false,
   "use_fast": true
 }