GRPO model: ROUGE-L 0.891 — matches prompted 2B

config.json

@@ -1,62 +1,63 @@
 {
-    "architectures": [
-        "Lfm2ForCausalLM"
-    ],
-    "block_auto_adjust_ff_dim": true,
-    "block_dim": 1024,
-    "block_ff_dim": 6656,
-    "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": 1024,
-    "conv_use_xavier_init": true,
-    "torch_dtype": "bfloat16",
-    "eos_token_id": 7,
-    "hidden_size": 1024,
-    "initializer_range": 0.02,
-    "intermediate_size": 6656,
-    "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_name": "LiquidAI/LFM2.5-350M-Base",
-    "model_type": "lfm2",
-    "norm_eps": 1e-05,
-    "num_attention_heads": 16,
-    "num_heads": 16,
-    "num_hidden_layers": 16,
-    "num_key_value_heads": 8,
-    "pad_token_id": 0,
-    "rope_parameters": {
-        "rope_theta": 1000000.0,
-        "rope_type": "default"
-    },
-    "tie_embedding": true,
-    "tie_word_embeddings": true,
-    "unsloth_version": "2026.3.18",
-    "use_cache": false,
-    "use_pos_enc": true,
-    "vocab_size": 65536
-}
+  "architectures": [
+    "Lfm2ForCausalLM"
+  ],
+  "block_auto_adjust_ff_dim": true,
+  "block_dim": 1024,
+  "block_ff_dim": 6656,
+  "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": 1024,
+  "conv_use_xavier_init": true,
+  "dtype": "bfloat16",
+  "eos_token_id": 7,
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 6656,
+  "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_name": "LiquidAI/LFM2.5-350M-Base",
+  "model_type": "lfm2",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 16,
+  "num_heads": 16,
+  "num_hidden_layers": 16,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "tie_embedding": true,
+  "tie_word_embeddings": true,
+  "transformers_version": "5.3.0",
+  "unsloth_version": "2026.3.18",
+  "use_cache": false,
+  "use_pos_enc": true,
+  "vocab_size": 65536
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:93c9ad95a97e816d22da4bdc2a8de79b554dbdcf910687502769403bd38ba839
+oid sha256:2cab7fee9107d3f698a2c5c1567638ab8d31427327303325ed7d34070c1a7bd2
 size 708984464

tokenizer_config.json

@@ -4,7 +4,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|im_end|>",
   "extra_special_tokens": [],
-  "is_local": false,
+  "is_local": true,
   "legacy": false,
   "model_input_names": [
     "input_ids",
@@ -17,6 +17,5 @@
   "spaces_between_special_tokens": false,
   "tokenizer_class": "TokenizersBackend",
   "use_default_system_prompt": false,
-  "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 -%}"
-}
+  "use_fast": true
+}