From f11e68932700895878904798cd7b7a8684517589 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Mon, 20 Jul 2026 21:43:10 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: Keitsuna123/llama-3.2-1b-fc-dpo Source: Original Platform --- .gitattributes | 36 +++++++++++++ README.md | 113 +++++++++++++++++++++++++++++++++++++++++ chat_template.jinja | 93 +++++++++++++++++++++++++++++++++ config.json | 40 +++++++++++++++ generation_config.json | 12 +++++ model.safetensors | 3 ++ tokenizer.json | 3 ++ tokenizer_config.json | 15 ++++++ 8 files changed, 315 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 chat_template.jinja create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 model.safetensors create mode 100644 tokenizer.json create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..2172707 --- /dev/null +++ b/README.md @@ -0,0 +1,113 @@ +--- +base_model: meta-llama/Llama-3.2-1B-Instruct +library_name: transformers +tags: +- function-calling +- tool-use +- llama +- dpo +- preference-optimization +- bfcl +license: llama3.2 +language: +- en +--- + +# Llama-3.2-1B-Instruct — Function Calling (DPO) + +The [v1 SFT model](https://huggingface.co/Keitsuna123/llama-3.2-1b-fc-sft-full) further trained with **DPO (Direct Preference Optimization)** to recover an irrelevance-detection regression. DPO is a *preference optimization* method — not reinforcement learning — that optimizes a model to prefer "chosen" over "rejected" responses directly, without a reward model or sampling. This is one of six models in a study comparing supervised, preference, and RL post-training for small-model function calling. + +**Code & writeup:** https://github.com/keitake123/llama-function-calling-study + +## Results (BFCL v4) + +| Category | Base | v1 SFT | GRPO (RL) | DPO (pref.) | Path B (SFT) | +|---|---|---|---|---|---| +| irrelevance | 35.8 | 5.8 | 5.4 | **8.3** | 21.7 | +| live_irrelevance | 67.3 | 16.9 | 17.2 | **28.6** | 36.8 | +| simple_python | 75.0 | 77.5 | 77.2 | 77.5 | 78.2 | +| multiple | 50.5 | 74.0 | 74.0 | 73.5 | 72.0 | +| live_simple | 31.8 | 57.0 | 56.2 | 58.5 | 54.3 | +| live_multiple | 7.3 | 38.8 | 39.4 | 37.0 | 35.7 | +| live_relevance | 43.8 | 93.8 | 93.8 | 81.2 | 81.2 | + +**Finding:** DPO produced **partial** irrelevance recovery (5.8→8.3 non-live; 16.9→28.6 live) — clearly better than GRPO (which showed no recovery) but below refusal-SFT. This fits a clean pattern across the three methods: + +> Recovery scaled with how *directly* each method exposed the model to the target behavior. +> **GRPO** never samples a refusal (the SFT always-call prior is too strong) → no signal → no recovery. +> **DPO** is *shown* refusals as the "chosen" response → partial recovery, at low cost to call categories. +> **Refusal-SFT** trains *directly* on refusals → strongest recovery. +> +> Ordering: imitation (SFT) > preference (DPO) > RL (GRPO). RL recovers least because it cannot reinforce a behavior absent from the policy's sampling distribution. + +Notably, DPO preserved call-required categories well (simple_python, live_simple held up), giving arguably the best precision/recall balance despite a lower raw irrelevance score than Path B. + +## Training details + +- **Base:** v1 SFT model, cleanly merged (see note below) +- **Method:** DPO (TRL `DPOTrainer`), LoRA (r=16, α=32) +- **Data:** ~1,600 preference pairs, 50/50 mix: + - *Irrelevance pairs:* chosen = natural refusal, rejected = v1's hallucinated call (generated by running v1 on the irrelevance prompts) + - *Call-required pairs:* chosen = correct call, rejected = wrong-function call +- **Config:** 1 epoch, effective batch 8, lr 5e-6, **beta (KL) 0.3**, bf16 +- **Hardware:** 1× RTX A6000 + +**Note on stability:** an initial run with beta=0.1 and a stacked (unmerged) reference adapter caused output-format drift (the model emitted a malformed call schema and occasionally code). Fixed by (1) cleanly merging the v1 adapter into the base before DPO so the reference model is well-formed, and (2) raising beta to 0.3 for a stronger anchor. See the repo's LESSONS.md. + +## Usage + +```python +from transformers import AutoModelForCausalLM, AutoTokenizer +import torch + +tokenizer = AutoTokenizer.from_pretrained("Keitsuna123/llama-3.2-1b-fc-dpo") +model = AutoModelForCausalLM.from_pretrained( + "Keitsuna123/llama-3.2-1b-fc-dpo", torch_dtype=torch.bfloat16, device_map="auto" +) + +messages = [{"role": "user", "content": "What's the weather in Tokyo?"}] +tools = [{"type": "function", "function": { + "name": "get_weather", "description": "Get the weather for a location", + "parameters": {"type": "object", "properties": {"location": {"type": "string"}}, "required": ["location"]} +}}] + +text = tokenizer.apply_chat_template(messages, tools=tools, tokenize=False, add_generation_prompt=True) +inputs = tokenizer(text, return_tensors="pt").to(model.device) +out = model.generate(**inputs, max_new_tokens=128, do_sample=False) +print(tokenizer.decode(out[0][inputs['input_ids'].shape[1]:], skip_special_tokens=True)) +``` + +## Limitations + +- Residual irrelevance failures concentrate in short, factual-seeming queries ("what's 2+2", "capital of France") — the same sub-case that beat every method in this study. +- Parallel calls near-zero (single-call training only). + +## Part of a series + +| Model | Method | Description | +|---|---|---| +| [fc-sft-full](https://huggingface.co/Keitsuna123/llama-3.2-1b-fc-sft-full) | SFT | v1 SFT on xLAM | +| [fc-sft-v2-merged](https://huggingface.co/Keitsuna123/llama-3.2-1b-fc-sft-v2-merged) | SFT | + distilabel (data-scaling ablation) | +| [fc-grpo](https://huggingface.co/Keitsuna123/llama-3.2-1b-fc-grpo) | RL | GRPO (no recovery) | +| [fc-pathb](https://huggingface.co/Keitsuna123/llama-3.2-1b-fc-pathb) | SFT | refusal-SFT (best recovery) | +| [fc-dpo](https://huggingface.co/Keitsuna123/llama-3.2-1b-fc-dpo) | DPO | preference optimization (this model) | + +## References & Acknowledgements + +- **Base model:** Llama 3.2 (Meta AI) — [meta-llama/Llama-3.2-1B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-1B-Instruct) +- **Training data:** Salesforce xLAM — [xlam-function-calling-60k](https://huggingface.co/datasets/Salesforce/xlam-function-calling-60k); preference pairs constructed for this study +- **Method:** DPO (Rafailov et al., "Direct Preference Optimization") +- **Benchmark:** Berkeley Function Calling Leaderboard (BFCL) — [Gorilla project](https://github.com/ShishirPatil/gorilla) +- **Frameworks:** HuggingFace TRL (DPOTrainer), PEFT, Transformers + +## Citation + +```bibtex +@misc{taketsuna2026_fc_smallmodel, + title = {Small-Model Function Calling: Comparing SFT, Data Scaling, GRPO, and DPO Post-Training}, + author = {Taketsuna, Keiichi}, + year = {2026}, + howpublished = {\url{https://github.com/keitake123/llama-function-calling-study}}, + note = {Llama-3.2-1B function-calling post-training study on BFCL v4} +} +``` \ No newline at end of file diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..1bad6a0 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,93 @@ +{{- bos_token }} +{%- if custom_tools is defined %} + {%- set tools = custom_tools %} +{%- endif %} +{%- if not tools_in_user_message is defined %} + {%- set tools_in_user_message = true %} +{%- endif %} +{%- if not date_string is defined %} + {%- if strftime_now is defined %} + {%- set date_string = strftime_now("%d %b %Y") %} + {%- else %} + {%- set date_string = "26 Jul 2024" %} + {%- endif %} +{%- endif %} +{%- if not tools is defined %} + {%- set tools = none %} +{%- endif %} + +{#- This block extracts the system message, so we can slot it into the right place. #} +{%- if messages[0]['role'] == 'system' %} + {%- set system_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} +{%- else %} + {%- set system_message = "" %} +{%- endif %} + +{#- System message #} +{{- "<|start_header_id|>system<|end_header_id|>\n\n" }} +{%- if tools is not none %} + {{- "Environment: ipython\n" }} +{%- endif %} +{{- "Cutting Knowledge Date: December 2023\n" }} +{{- "Today Date: " + date_string + "\n\n" }} +{%- if tools is not none and not tools_in_user_message %} + {{- "You have access to the following functions. To call a function, please respond with JSON for a function call." }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} +{%- endif %} +{{- system_message }} +{{- "<|eot_id|>" }} + +{#- Custom tools are passed in a user message with some extra guidance #} +{%- if tools_in_user_message and not tools is none %} + {#- Extract the first user message so we can plug it in here #} + {%- if messages | length != 0 %} + {%- set first_user_message = messages[0]['content']|trim %} + {%- set messages = messages[1:] %} + {%- else %} + {{- raise_exception("Cannot put tools in the first user message when there's no first user message!") }} +{%- endif %} + {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}} + {{- "Given the following functions, please respond with a JSON for a function call " }} + {{- "with its proper arguments that best answers the given prompt.\n\n" }} + {{- 'Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}.' }} + {{- "Do not use variables.\n\n" }} + {%- for t in tools %} + {{- t | tojson(indent=4) }} + {{- "\n\n" }} + {%- endfor %} + {{- first_user_message + "<|eot_id|>"}} +{%- endif %} + +{%- for message in messages %} + {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %} + {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' }} + {%- elif 'tool_calls' in message %} + {%- if not message.tool_calls|length == 1 %} + {{- raise_exception("This model only supports single tool-calls at once!") }} + {%- endif %} + {%- set tool_call = message.tool_calls[0].function %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}} + {{- '{"name": "' + tool_call.name + '", ' }} + {{- '"parameters": ' }} + {{- tool_call.arguments | tojson }} + {{- "}" }} + {{- "<|eot_id|>" }} + {%- elif message.role == "tool" or message.role == "ipython" %} + {{- "<|start_header_id|>ipython<|end_header_id|>\n\n" }} + {%- if message.content is mapping or message.content is iterable %} + {{- message.content | tojson }} + {%- else %} + {{- message.content }} + {%- endif %} + {{- "<|eot_id|>" }} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..ebb8dd6 --- /dev/null +++ b/config.json @@ -0,0 +1,40 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 128000, + "dtype": "bfloat16", + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "head_dim": 64, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 131072, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 16, + "num_key_value_heads": 8, + "pad_token_id": null, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_parameters": { + "factor": 32.0, + "high_freq_factor": 4.0, + "low_freq_factor": 1.0, + "original_max_position_embeddings": 8192, + "rope_theta": 500000.0, + "rope_type": "llama3" + }, + "tie_word_embeddings": true, + "transformers_version": "5.13.0", + "use_cache": true, + "vocab_size": 128256 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..a7c5047 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 128000, + "do_sample": true, + "eos_token_id": [ + 128001, + 128008, + 128009 + ], + "temperature": 0.6, + "top_p": 0.9, + "transformers_version": "5.13.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..1992e17 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47055c3256bc01b347c1bd1fd00753745a5fe1741f2a3ef52d2e42f5a6c98892 +size 2471645608 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..1c1d8d5 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b +size 17209920 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..a3ccf3a --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,15 @@ +{ + "backend": "tokenizers", + "bos_token": "<|begin_of_text|>", + "clean_up_tokenization_spaces": true, + "eos_token": "<|eot_id|>", + "is_local": false, + "local_files_only": false, + "model_input_names": [ + "input_ids", + "attention_mask" + ], + "model_max_length": 131072, + "pad_token": "<|eot_id|>", + "tokenizer_class": "TokenizersBackend" +}