Upload merged model and tokenizer

chat_template.jinja

@@ -1,4 +1,37 @@
-{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
-' + message['content'] + '<|im_end|>' + '
-'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
-' }}{% endif %}
+{{- 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 -%}

config.json

@@ -1,59 +1,57 @@
 {
-    "architectures": [
-        "Lfm2ForCausalLM"
-    ],
-    "block_auto_adjust_ff_dim": true,
-    "block_dim": 1536,
-    "block_ff_dim": 10240,
-    "block_ffn_dim_multiplier": 1.0,
-    "block_mlp_init_scale": 1.0,
-    "block_multiple_of": 256,
-    "block_norm_eps": 1e-05,
-    "block_out_init_scale": 1.0,
-    "block_use_swiglu": true,
-    "block_use_xavier_init": true,
-    "bos_token_id": 1,
-    "conv_L_cache": 3,
-    "conv_bias": false,
-    "conv_dim": 1536,
-    "conv_dim_out": 1536,
-    "conv_use_xavier_init": true,
-    "eos_token_id": 7,
-    "hidden_size": 1536,
-    "initializer_range": 0.02,
-    "intermediate_size": 10240,
-    "layer_types": [
-        "conv",
-        "conv",
-        "full_attention",
-        "conv",
-        "conv",
-        "full_attention",
-        "conv",
-        "conv",
-        "full_attention",
-        "conv",
-        "full_attention",
-        "conv",
-        "full_attention",
-        "conv",
-        "full_attention",
-        "conv"
-    ],
-    "max_position_embeddings": 32768,
-    "model_type": "lfm2",
-    "norm_eps": 1e-05,
-    "num_attention_heads": 24,
-    "num_heads": 24,
-    "num_hidden_layers": 16,
-    "num_key_value_heads": 8,
-    "pad_token_id": 0,
-    "rope_theta": 1000000.0,
-    "torch_dtype": "float16",
-    "transformers_version": "4.56.0.dev0",
-    "unsloth_fixed": true,
-    "unsloth_version": "2025.8.9",
-    "use_cache": true,
-    "use_pos_enc": true,
-    "vocab_size": 65536
-}
+  "architectures": [
+    "Lfm2ForCausalLM"
+  ],
+  "block_auto_adjust_ff_dim": true,
+  "block_dim": 1536,
+  "block_ff_dim": 10240,
+  "block_ffn_dim_multiplier": 1.0,
+  "block_mlp_init_scale": 1.0,
+  "block_multiple_of": 256,
+  "block_norm_eps": 1e-05,
+  "block_out_init_scale": 1.0,
+  "block_use_swiglu": true,
+  "block_use_xavier_init": true,
+  "bos_token_id": 1,
+  "conv_L_cache": 3,
+  "conv_bias": false,
+  "conv_dim": 1536,
+  "conv_dim_out": 1536,
+  "conv_use_xavier_init": true,
+  "eos_token_id": 7,
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 10240,
+  "layer_types": [
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv",
+    "full_attention",
+    "conv"
+  ],
+  "max_position_embeddings": 128000,
+  "model_type": "lfm2",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 24,
+  "num_heads": 24,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_theta": 1000000.0,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.56.0.dev0",
+  "use_cache": true,
+  "use_pos_enc": true,
+  "vocab_size": 65536
+}

generation_config.json

@@ -1,10 +1,7 @@
 {
   "_from_model_config": true,
   "bos_token_id": 1,
-  "eos_token_id": [
-    7
-  ],
-  "max_length": 32768,
+  "eos_token_id": 7,
   "pad_token_id": 0,
   "transformers_version": "4.56.0.dev0"
 }

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b587caa19bb77cfb9d5ca99c17a0ec883dab378b53270735566e388302bcfc83
+size 1484995328

tokenizer_config.json

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