commit 85117846aac145b58bdff031ab598900a069c4ae Author: ModelHub XC Date: Mon Jul 20 14:52:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled Source: Original Platform 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..619153c --- /dev/null +++ b/README.md @@ -0,0 +1,84 @@ +--- +license: apache-2.0 +tags: +- text-generation +- code +- reasoning +- codegemma +- gemma +- safe-tensors +- distillation +- synthetic-dataset +base_model: google/codegemma-1.1-2b +datasets: +- WithinUsAI/GeminiPro3.2_max_distill_god_seed_25k +- WithinUsAI/gemini_3.5_flash_distilled_25k +- WithinUsAI/Gemini_3.2_Pro_Distilled +- WithinUsAI/codegemma_gemini_pro_32_distilled_25k +- WithinUsAI/DEEPMIND_Alpha_Distilled +pipeline_tag: text-generation +library_name: transformers +language: +- en +--- + +# Gemini3.5-Code.Reasoner-2b-Distilled + +Gemini3.5-Code.Reasoner-2b-Distilled is a highly efficient, reasoning-dense model tailored for advanced coding tasks, algorithmic problem-solving, and logical chain-of-thought workflows. + +By applying a specialized Low-Rank Adaptation (LoRA) layer over **CodeGemma 1.1 2B**, this model infuses frontier-level reasoning mechanics into a compact, 2-billion parameter architecture. It bridges the gap between massive cloud-hosted models and local, edge-compute hardware. + +## Model Details + +- **Developed by:** WithinUsAI +- **Model Type:** Causal Language Model (Fine-tuned / Knowledge Distilled) +- **Base Model:** [google/codegemma-1.1-2b](https://huggingface.co/google/codegemma-1.1-2b) +- **Architecture:** GemmaForCausalLM (CodeGemma variant) + LoRA Adapters +- **License:** Apache 2.0 + +## Training & Dataset Recipe + +The "Reasoner" capabilities of this model are distilled from a multi-source synthetic pipeline focusing on complex coding logic, algorithmic optimization, and step-by-step thinking patterns. The training mixture leverages approximately 100K+ high-quality reasoning examples across five core datasets: + +| Dataset Name | Source / Focus | Approx. Size | +| :--- | :--- | :--- | +| `WithinUsAI/GeminiPro3.2_max_distill_god_seed_25k` | High-quality frontier seed prompts for code generation. | ~25k samples | +| `WithinUsAI/gemini_3.5_flash_distilled_25k` | Fast, iterative logical steps and multi-turn debugging data. | ~25k samples | +| `WithinUsAI/Gemini_3.2_Pro_Distilled` | Heavy math logic, structural coding, and system design patterns. | Premium corpus | +| `WithinUsAI/codegemma_gemini_pro_32_distilled_25k` | Target-aligned distillation data optimized for the CodeGemma vocabulary. | ~25k samples | +| `WithinUsAI/DEEPMIND_Alpha_Distilled` | Deep algorithmic competitive programming and math reasoning. | Premium corpus | + +## Intended Use + +- **Local Code Assistants:** Ideal for IDE plugins requiring fast, low-latency code completion and instruction following. +- **Logical Chain-of-Thought:** Designed to output its reasoning process before writing the final code block, minimizing syntax and logical errors. +- **Resource-Constrained Environments:** Can easily be deployed on mobile devices, single-GPU setups, or local laptops using frameworks like `vLLM`, `Ollama`, or `SGLang`. + +## Quickstart Guide + +### Inference with Hugging Face Transformers + +Because CodeGemma utilizes specialized tokens for coding workflows, it's recommended to structure your prompts cleanly to prompt the model's inner chain-of-thought. + +```python +from transformers import AutoTokenizer, AutoModelForCausalLM +import torch + +model_id = "WithinUsAI/Gemini3.5-Code.Reasoner-2b-Distilled" + +tokenizer = AutoTokenizer.from_pretrained(model_id) +model = AutoModelForCausalLM.from_pretrained( + model_id, + torch_dtype=torch.bfloat16, + device_map="auto" +) + +# Prompt the model to think step-by-step before delivering code +prompt = """Analyze the problem and think step-by-step before writing any code. +Problem: Write a Python generator function that yields the Fibonacci sequence up to n elements. +Answer:""" + +inputs = tokenizer(prompt, return_tensors="pt").to("cuda") +outputs = model.generate(**inputs, max_new_tokens=512, temperature=0.2) + +print(tokenizer.decode(outputs[0], skip_special_tokens=True)) diff --git a/config.json b/config.json new file mode 100644 index 0000000..351c906 --- /dev/null +++ b/config.json @@ -0,0 +1,32 @@ +{ + "architectures": [ + "GemmaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 2, + "dtype": "float16", + "eos_token_id": 1, + "head_dim": 256, + "hidden_act": "gelu_pytorch_tanh", + "hidden_activation": null, + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 16384, + "max_position_embeddings": 8192, + "model_type": "gemma", + "num_attention_heads": 8, + "num_hidden_layers": 18, + "num_key_value_heads": 1, + "pad_token_id": 0, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 10000.0, + "rope_type": "default" + }, + "tie_word_embeddings": true, + "transformers_version": "5.0.0", + "use_bidirectional_attention": null, + "use_cache": true, + "vocab_size": 256000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..4b22d42 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "eos_token_id": 1, + "pad_token_id": 0, + "transformers_version": "5.0.0" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..c9176d3 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:782d4cc509fce11347b1943f8270e4d6d6fb19ad715159eef10fd4aded600238 +size 5012363688 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..4d1ffdc --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88649feb2ca8710ba0b8d7402ac0dc737b2b4cc58f4a10878127449a01cee96c +size 34362790 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..bf49910 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,15 @@ +{ + "backend": "tokenizers", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "is_local": false, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}