commit fcd61a0edc3f4dc3c06d4094691906fba329e4d8 Author: ModelHub XC Date: Fri Jul 24 02:41:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: RefinedNeuro/RefinedToolCallV5-3b Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..3c2a05f --- /dev/null +++ b/.gitattributes @@ -0,0 +1,39 @@ +*.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 +RefinedToolCallV5-3b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +RefinedToolCallV5-3b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +RefinedToolCallV5-3b-f16.gguf 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..4a266bc --- /dev/null +++ b/README.md @@ -0,0 +1,101 @@ +--- +license: apache-2.0 +base_model: WeiboAI/VibeThinker-3B +datasets: + - lambda/hermes-agent-reasoning-traces +language: + - en +pipeline_tag: text-generation +tags: + - tool-calling + - function-calling + - multi-turn + - agentic + - hermes + - reasoning + - qwen2 +--- + +# 🛠️🧠 RefinedToolCall-V5-3B + +### A 3B model that *reasons* and *calls tools* — and actually holds a multi-turn conversation. + +**Math-grade reasoning · real function calling · multi-turn agentic · 2.5 GB · runs on your laptop.** + +> `ollama run refinedneuro/refinedtoolcallv5-3b` + +--- + +## Why it's different + +Most 3B tool-callers nail a single function call and then fall apart the moment the task spans +several turns. **RefinedToolCall-V5** was built specifically to fix that — and the numbers moved on +*every* axis at once, not just the one we were targeting. + +- 🔁 **Multi-turn agentic that actually works** — **~3.7× better** at stateful, multi-step + tool-use (Berkeley Function-Calling Leaderboard `multi_turn`) than where we started. +- 🛠️ **Sharper single-turn calling** — **70.7%** on BFCL single-turn (held-out), our best ever. +- 💪 **Recovers from tool errors** — **0.896** recovery rate; it diagnoses failures instead of + looping on them. +- 🧮 **Reasoning fully intact** — **AIME-2024 pass@8 0.933**, unchanged by all the tool training. +- ⚡ **Tiny & local** — 3B params, **2.5 GB** Q6_K, one command on Ollama, no GPU required. +- 🆓 **Apache-2.0** — use it, ship it, fine-tune it. + +--- + +## The receipts (all held-out, canary-gated) + +| capability | this model | +|---|---| +| 🔁 Multi-turn agentic (BFCL `multi_turn`, k=3) | **0.220 avg / 0.298 pass@3** | +| 🛠️ Single-turn function calling (BFCL, held-out) | **0.707** | +| 🩹 Recovery from tool errors (n=250) | **0.896** | +| 🧮 Reasoning (AIME-2024 pass@8) | **0.933** | + +Every number is the **best across five fine-tuning rounds** — multi-turn, single-turn, recovery, +*and* reasoning all peaked together. + +--- + +## How we got here (and why it generalizes) + +We didn't just throw data at it. Five disciplined rounds, each one gated so it could **never** +regress reasoning or recovery: + +1. **Grounding** — stop inventing shell commands; call the actual functions. +2. **Plan + finish** — think before calling, and know when the turn is done. +3. **Scale + long context** — harder tasks, up to 24k tokens. +4. **On-policy self-improvement (the breakthrough)** — the model learns from its *own* successful + multi-turn solutions (expert iteration), which broke past the imitation ceiling **and** sharpened + single-turn calling and error-recovery as a bonus. + +--- + +## Quick start + +**Ollama** +```bash +ollama run refinedneuro/refinedtoolcallv5-3b # latest = Q6_K, 2.5 GB +``` +> 💡 Use **Q6_K or higher** for tool-calling — lower quants corrupt the call tokens. + +**Format:** ChatML + Hermes tools. Each turn the model emits a `` plan → one or more +`` blocks → a final reply. Recommended: temp 0.6, top_p 0.95, repeat_penalty 1.1. + +--- + +## Great for +✅ Local/offline agentic tool-use prototypes ✅ Multi-step function-calling assistants +✅ Math & STEM reasoning ✅ Learning how small agentic models are actually built. + +## Be honest with me (research preview) +⚠️ It's a **3B research preview**. Multi-turn is **dramatically improved (~3.7×) but not solved** — +very long, open-ended autonomous loops can still write buggy code or mis-plan. A brilliant, +tiny building block; not yet a drop-in autonomous engineer. + +--- + +*Built on [WeiboAI/VibeThinker-3B](https://huggingface.co/WeiboAI/VibeThinker-3B) + +[lambda/hermes-agent-reasoning-traces](https://huggingface.co/datasets/lambda/hermes-agent-reasoning-traces). +Trained with distribution-matched RFT + on-policy expert iteration, every checkpoint gated against +reasoning/recovery canaries. Apache-2.0.* diff --git a/RefinedToolCallV5-3b-Q6_K.gguf b/RefinedToolCallV5-3b-Q6_K.gguf new file mode 100644 index 0000000..9f0555d --- /dev/null +++ b/RefinedToolCallV5-3b-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eaae72d41879b68de730368248d61485b98ef0dac0170004aa88d7e6ddfc5236 +size 2538158304 diff --git a/RefinedToolCallV5-3b-Q8_0.gguf b/RefinedToolCallV5-3b-Q8_0.gguf new file mode 100644 index 0000000..2183ff4 --- /dev/null +++ b/RefinedToolCallV5-3b-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b41c055f1faf32903a9df71e90ae26c1623f62dc2c80c84b0a55e336e607b685 +size 3285476320 diff --git a/RefinedToolCallV5-3b-f16.gguf b/RefinedToolCallV5-3b-f16.gguf new file mode 100644 index 0000000..459002d --- /dev/null +++ b/RefinedToolCallV5-3b-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32b00f5b4404a76ba06d182eb1a22e2dcdf88de76af447bddca96d85a7ed74c8 +size 6178317280 diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..28028c0 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,54 @@ +{%- if tools %} + {{- '<|im_start|>system\n' }} + {%- if messages[0]['role'] == 'system' %} + {{- messages[0]['content'] }} + {%- else %} + {{- 'You are a helpful assistant.' }} + {%- endif %} + {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within XML tags:\n" }} + {%- for tool in tools %} + {{- "\n" }} + {{- tool | tojson }} + {%- endfor %} + {{- "\n\n\nFor each function call, return a json object with function name and arguments within XML tags:\n\n{\"name\": , \"arguments\": }\n<|im_end|>\n" }} +{%- else %} + {%- if messages[0]['role'] == 'system' %} + {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }} + {%- else %} + {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }} + {%- endif %} +{%- endif %} +{%- for message in messages %} + {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %} + {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }} + {%- elif message.role == "assistant" %} + {{- '<|im_start|>' + message.role }} + {%- if message.content %} + {{- '\n' + message.content }} + {%- endif %} + {%- for tool_call in message.tool_calls %} + {%- if tool_call.function is defined %} + {%- set tool_call = tool_call.function %} + {%- endif %} + {{- '\n\n{"name": "' }} + {{- tool_call.name }} + {{- '", "arguments": ' }} + {{- tool_call.arguments | tojson }} + {{- '}\n' }} + {%- endfor %} + {{- '<|im_end|>\n' }} + {%- elif message.role == "tool" %} + {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|im_start|>user' }} + {%- endif %} + {{- '\n\n' }} + {{- message.content }} + {{- '\n' }} + {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} + {{- '<|im_end|>\n' }} + {%- endif %} + {%- endif %} +{%- endfor %} +{%- if add_generation_prompt %} + {{- '<|im_start|>assistant\n' }} +{%- endif %} diff --git a/config.json b/config.json new file mode 100644 index 0000000..6621777 --- /dev/null +++ b/config.json @@ -0,0 +1,69 @@ +{ + "architectures": [ + "Qwen2ForCausalLM" + ], + "attention_dropout": 0.0, + "bos_token_id": 151643, + "dtype": "bfloat16", + "eos_token_id": 151643, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 11008, + "layer_types": [ + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention", + "full_attention" + ], + "max_position_embeddings": 131072, + "max_window_layers": 36, + "model_type": "qwen2", + "num_attention_heads": 16, + "num_hidden_layers": 36, + "num_key_value_heads": 2, + "pad_token_id": null, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 1000000.0, + "rope_type": "default" + }, + "sliding_window": null, + "tie_word_embeddings": true, + "transformers_version": "5.7.0", + "use_cache": false, + "use_sliding_window": false, + "vocab_size": 151936 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..27f6985 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,12 @@ +{ + "bos_token_id": 151643, + "do_sample": true, + "eos_token_id": [ + 151645, + 151643 + ], + "max_new_tokens": 65536, + "temperature": 0.6, + "top_p": 0.95, + "transformers_version": "5.7.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..12065fa --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e64a0fc8121c4aa9d2110318280ecad3916513c6a64f8035b8a64ba65911a52 +size 6171927112 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..55e03a0 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b17e16899b7fab7e695509f84bac5f10ed12804f0a590e935941e5af7f092f7f +size 11422263 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..ea724e4 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,16 @@ +{ + "add_prefix_space": false, + "backend": "tokenizers", + "bos_token": null, + "clean_up_tokenization_spaces": false, + "eos_token": "<|endoftext|>", + "errors": "replace", + "is_local": true, + "local_files_only": false, + "model_max_length": 131072, + "pad_token": "<|endoftext|>", + "padding_side": "right", + "split_special_tokens": false, + "tokenizer_class": "Qwen2Tokenizer", + "unk_token": null +}