Upload final SFT model

README.md

@@ -0,0 +1,83 @@
+---
+library_name: transformers
+pipeline_tag: text-generation
+base_model: LiquidAI/LFM2.5-350M
+tags:
+- causal-lm
+- sft
+- math
+- chatml
+- transformers
+---
+
+# Math Curated SFT
+
+This is a full-model SFT checkpoint trained from `LiquidAI/LFM2.5-350M` on
+`User01110/math-curated-dataset`.
+
+## Training
+
+- Method: TRL `SFTTrainer`
+- Dataset split: `train`
+- Training rows: 39040
+- Epochs: 1
+- Max sequence length: 1024
+- Target style: full generated response
+- Format: the base tokenizer chat template via `tokenizer.apply_chat_template`
+- System prompt: `You are a math-focused assistant. Solve the user's math problem and follow the training format: Understanding Query, Drafting Answer, Refining The Answer, and Final Response.`
+
+## Format
+
+Each row is formatted with:
+
+```python
+messages = [
+    {"role": "system", "content": SYSTEM_PROMPT},
+    {"role": "user", "content": prompt},
+]
+prompt_text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+training_text = prompt_text + response + (tokenizer.eos_token or "")
+```
+
+## Important limitation
+
+This model is trained on generated math-style data. Responses may contain
+incorrect arithmetic or flawed reasoning, and should not be treated as reliable
+mathematical answers without independent verification.
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "User01110/LFM-2.5-350M-MathMini"
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+messages = [
+    {"role": "system", "content": "You are a math-focused assistant. Solve the user's math problem and follow the training format: Understanding Query, Drafting Answer, Refining The Answer, and Final Response."},
+    {"role": "user", "content": "John has 22 apples, he eats 10 of them, now john has"},
+]
+prompt = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True,
+)
+inputs = tokenizer(prompt, return_tensors="pt")
+outputs = model.generate(
+    **inputs,
+    max_new_tokens=128,
+    do_sample=True,
+    temperature=0.7,
+    top_k=40,
+    top_p=0.95,
+    repetition_penalty=1.1,
+    pad_token_id=tokenizer.pad_token_id,
+    eos_token_id=tokenizer.eos_token_id,
+)
+print(tokenizer.decode(outputs[0], skip_special_tokens=False))
+```

chat_template.jinja

@@ -0,0 +1,64 @@
+{{- bos_token -}}
+{%- set keep_past_thinking = keep_past_thinking | default(false) -%}
+{%- set ns = namespace(system_prompt="") -%}
+{%- if messages[0]["role"] == "system" -%}
+    {%- set sys_content = messages[0]["content"] -%}
+    {%- if sys_content is not string -%}
+        {%- for item in sys_content -%}
+            {%- if item["type"] == "text" -%}
+                {%- set ns.system_prompt = ns.system_prompt + item["text"] -%}
+            {%- endif -%}
+        {%- endfor -%}
+    {%- else -%}
+        {%- set ns.system_prompt = sys_content -%}
+    {%- endif -%}
+    {%- set messages = messages[1:] -%}
+{%- endif -%}
+{%- if tools -%}
+    {%- set ns.system_prompt = ns.system_prompt + ("\n" if ns.system_prompt else "") + "List of tools: [" -%}
+    {%- 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 + "]" -%}
+{%- endif -%}
+{%- if ns.system_prompt -%}
+    {{- "<|im_start|>system\n" + ns.system_prompt + "<|im_end|>\n" -}}
+{%- endif -%}
+{%- set ns.last_assistant_index = -1 -%}
+{%- for message in messages -%}
+    {%- if message["role"] == "assistant" -%}
+        {%- set ns.last_assistant_index = loop.index0 -%}
+    {%- endif -%}
+{%- endfor -%}
+{%- for message in messages -%}
+    {{- "<|im_start|>" + message["role"] + "\n" -}}
+    {%- set content = message["content"] -%}
+    {%- if content is not string -%}
+        {%- set ns.content = "" -%}
+        {%- for item in content -%}
+            {%- if item["type"] == "image" -%}
+                {%- set ns.content = ns.content + "<image>" -%}
+            {%- elif item["type"] == "text" -%}
+                {%- set ns.content = ns.content + item["text"] -%}
+            {%- else -%}
+                {%- set ns.content = ns.content + item | tojson -%}
+            {%- endif -%}
+        {%- endfor -%}
+        {%- set content = ns.content -%}
+    {%- endif -%}
+    {%- if message["role"] == "assistant" and not keep_past_thinking and loop.index0 != ns.last_assistant_index -%}
+        {%- if "</think>" in content -%}
+            {%- set content = content.split("</think>")[-1] | trim -%}
+        {%- endif -%}
+    {%- endif -%}
+    {{- content + "<|im_end|>\n" -}}
+{%- endfor -%}
+{%- if add_generation_prompt -%}
+    {{- "<|im_start|>assistant\n" -}}
+{%- endif -%}

config.json

@@ -0,0 +1,60 @@
+{
+  "architectures": [
+    "Lfm2ForCausalLM"
+  ],
+  "block_auto_adjust_ff_dim": true,
+  "block_dim": 1024,
+  "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,
+  "full_attn_idxs": null,
+  "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_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_word_embeddings": true,
+  "transformers_version": "5.11.0",
+  "use_cache": true,
+  "use_pos_enc": true,
+  "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": [
+    7
+  ],
+  "pad_token_id": 0,
+  "transformers_version": "5.11.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bcf6431472e1c5e3276a5c23a418eb90b8ea5c6b35cceafb0a754c96f348454f
+size 708984464

tokenizer_config.json

@@ -0,0 +1,22 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|startoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "legacy": false,
+  "local_files_only": false,
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "model_specific_special_tokens": {},
+  "pad_token": "<|pad|>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "TokenizersBackend",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac0f05812d1e26298727ca4b9ca334a6e20277a2fcbbb1fa36983c48ef9019fc
+size 5649