(Trained with Unsloth)

config.json

@@ -1,74 +1,74 @@
 {
-  "architectures": [
-    "Lfm2ForCausalLM"
-  ],
-  "block_auto_adjust_ff_dim": false,
-  "block_dim": 2048,
-  "block_ff_dim": 10752,
-  "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": 2048,
-  "conv_dim_out": 2048,
-  "conv_use_xavier_init": true,
-  "eos_token_id": 7,
-  "hidden_size": 2048,
-  "initializer_range": 0.02,
-  "intermediate_size": 10752,
-  "layer_types": [
-    "conv",
-    "conv",
-    "full_attention",
-    "conv",
-    "conv",
-    "full_attention",
-    "conv",
-    "conv",
-    "conv",
-    "full_attention",
-    "conv",
-    "conv",
-    "conv",
-    "full_attention",
-    "conv",
-    "conv",
-    "conv",
-    "full_attention",
-    "conv",
-    "conv",
-    "conv",
-    "full_attention",
-    "conv",
-    "conv",
-    "full_attention",
-    "conv",
-    "conv",
-    "full_attention",
-    "conv",
-    "conv"
-  ],
-  "max_position_embeddings": 128000,
-  "model_type": "lfm2",
-  "norm_eps": 1e-05,
-  "num_attention_heads": 32,
-  "num_heads": 32,
-  "num_hidden_layers": 30,
-  "num_key_value_heads": 8,
-  "pad_token_id": 0,
-  "rope_theta": 1000000.0,
-  "theta": 1000000.0,
-  "tie_embedding": true,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.55.4",
-  "unsloth_version": "2025.10.4",
-  "use_cache": true,
-  "use_pos_enc": true,
-  "vocab_size": 65536
-}
+    "architectures": [
+        "Lfm2ForCausalLM"
+    ],
+    "block_auto_adjust_ff_dim": false,
+    "block_dim": 2048,
+    "block_ff_dim": 10752,
+    "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": 2048,
+    "conv_dim_out": 2048,
+    "conv_use_xavier_init": true,
+    "eos_token_id": 7,
+    "hidden_size": 2048,
+    "initializer_range": 0.02,
+    "intermediate_size": 10752,
+    "layer_types": [
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv",
+        "full_attention",
+        "conv",
+        "conv"
+    ],
+    "max_position_embeddings": 128000,
+    "model_type": "lfm2",
+    "norm_eps": 1e-05,
+    "num_attention_heads": 32,
+    "num_heads": 32,
+    "num_hidden_layers": 30,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "rope_theta": 1000000.0,
+    "theta": 1000000.0,
+    "tie_embedding": true,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.55.4",
+    "unsloth_version": "2025.10.7",
+    "use_cache": true,
+    "use_pos_enc": true,
+    "vocab_size": 65536
+}

tokenizer_config.json

@@ -4064,22 +4064,17 @@
   "eos_token": "<|im_end|>",
   "extra_special_tokens": {},
   "legacy": true,
-  "max_length": 128,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
-  "pad_to_multiple_of": null,
   "pad_token": "<|pad|>",
-  "pad_token_type_id": 0,
   "padding_side": "right",
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
-  "stride": 0,
   "tokenizer_class": "PreTrainedTokenizerFast",
-  "truncation_side": "right",
-  "truncation_strategy": "longest_first",
   "use_default_system_prompt": false,
-  "use_fast": true
-}
+  "use_fast": true,
+  "chat_template": "{{- 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 -%}"
+}