初始化项目，由ModelHub XC社区提供模型

Model: codestrate/Llama3.2-3B-Claude-Reasoning-Distill
Source: Original Platform

.gitattributes

@@ -0,0 +1,43 @@
+*.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
+Llama-3.2-3B-Instruct.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3b-ft-claude-merged.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3b-ft-claude-merged.BF16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3b-ft-claude-merged.F16.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3b-ft-claude-merged.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.2-3B-Claude-Reasoning-Distill.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama3.2-3B-Claude-Reasoning-Distill.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+loss_curve_with_rolling_average.png filter=lfs diff=lfs merge=lfs -text

Llama-3b-ft-claude-merged.F16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:23c0c74fba891ba6616e433900907c5142735360fe52803bb5d4154659ac6580
+size 6433700256

Llama3.2-3B-Claude-Reasoning-Distill.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dda4cd569d793655aa9fe13fe1b7b7f1a5ea440ee88630bc247a3763b9fb214d
+size 2019382624

Llama3.2-3B-Claude-Reasoning-Distill.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:673f24508da633866b3358c4b2d83b60bb250c5ad8a59ce757458c6eba37b163
+size 3421905696

Modelfile

@@ -0,0 +1,62 @@
+FROM Llama3.2-3B-Claude-Reasoning-Distill.Q4_K_M.gguf
+
+SYSTEM "You are a helpful assistant. Before giving your final answer, reason through the problem inside <think>...</think> tags. Close the thinking block and then give your final answer."
+
+TEMPLATE """{{ if .Messages }}
+{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|>
+{{- if .System }}
+
+{{ .System }}
+{{- end }}
+{{- if .Tools }}
+
+You are a helpful assistant with tool calling capabilities. When you receive a tool call response, use the output to format an answer to the original use question.
+{{- end }}
+{{- end }}<|eot_id|>
+{{- range $i, $_ := .Messages }}
+{{- $last := eq (len (slice $.Messages $i)) 1 }}
+{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|>
+{{- if and $.Tools $last }}
+
+Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt.
+
+Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables.
+
+{{ $.Tools }}
+{{- end }}
+
+{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}
+{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|>
+{{- if .ToolCalls }}
+
+{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }}
+{{- else }}
+
+{{ .Content }}{{ if not $last }}<|eot_id|>{{ end }}
+{{- end }}
+{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|>
+
+{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}
+{{- end }}
+{{- end }}
+{{- else }}
+{{- if .System }}<|start_header_id|>system<|end_header_id|>
+
+{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
+
+{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
+
+{{ end }}{{ .Response }}{{ if .Response }}<|eot_id|>{{ end }}"""
+
+PARAMETER stop "<|start_header_id|>"
+PARAMETER stop "<|end_header_id|>"
+PARAMETER stop "<|eot_id|>"
+PARAMETER stop "<|eom_id|>"
+PARAMETER temperature 0.7
+PARAMETER repeat_penalty 1.3
+PARAMETER min_p 0.1
+PARAMETER num_predict 1024

README.md

@@ -0,0 +1,213 @@
+---
+tags:
+- gguf
+- llama.cpp
+- unsloth
+- llama
+- llama3.2
+- distillation
+- reasoning
+- fine-tuning
+license: llama3.2
+datasets:
+- angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k
+language:
+- en
+base_model:
+- unsloth/Llama-3.2-3B-Instruct-bnb-4bit
+pipeline_tag: text-generation
+library_name: transformers
+---
+
+# Llama 3.2 3B — Claude Reasoning Distill
+
+This model was a second attempt at reasoning distillation, with several fixes from the 1B run — but the core approach was still wrong.
+
+**1. Same root problem: SFT copies style, not capability** - GRPO is the right approach 
+
+**2. Dataset truncation caused the stopping problem**
+The training dataset (`angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k`) averages ~1,954 tokens per example, with p90 assistant responses alone hitting ~1,760 tokens. Trained at `seq_len=2048`, a significant portion of examples were silently truncated — cutting off the `<|eot_id|>` end-of-turn token before it could be written.
+The model learned from many examples that responses don't need to end. This is a dataset fit problem, not a model problem.
+
+**3. Wrong EOS token at inference**
+Llama 3 has two EOS-like tokens. `tokenizer.eos_token_id` returns `128001` (`<|end_of_text|>`), but the model generates `128009` (`<|eot_id|>`) to end a turn. The default `model.generate()` call never passes `128009`, so generation runs until `max_new_tokens`. This compounds the truncation issue above.
+
+**Same Fix as 1B if you're using this model:**
+
+```python
+model.generate(
+    input_ids=inputs,
+    eos_token_id=[128001, 128009],
+    max_new_tokens=512,
+    repetition_penalty=1.3,
+    no_repeat_ngram_size=6,
+)
+```
+
+For Ollama, add to your Modelfile:
+
+```
+PARAMETER stop "<|eot_id|>"
+PARAMETER stop "<|end_of_text|>"
+```
+---
+An updated attempt at distilling Claude Opus 4.6/4.7 reasoning traces into a small-form-factor model. The predecessor [Llama 3.2 1B Claude Opus Reasoning Distill](https://huggingface.co/codestrate/Llama3.2-1B-Claude-Opus-Reasoning-Distill) demonstrated that a 1B model could adopt `<think>` blocks but suffered from echolalia and a GSM8K regression. This run addresses the two root causes identified from that experiment:
+
+1. **Capacity** — 3B sits closer to the parameter floor where structured reasoning adoption is viable, as seen in models like [Gemma 4 E2B-IT](https://huggingface.co/google/gemma-4-E2B-it) and [Qwen3-1.7B](https://huggingface.co/Qwen/Qwen3-1.7B) (which has `<think>` baked into pretraining)
+2. **Token boundaries** — `<think>` and `</think>` are registered as special tokens (vocab 128256 → 128258) with trained embeddings, giving the model a hard mode boundary instead of treating them as plain text
+3. **Training on Reponses Only** - Unlike 1B run, I used the `train_on_responses_only` from `unsloth` to mask out user inputs to have a accuracy increase in multi-turn conversational fine tuning.
+
+> **Benchmarks will not be available.**
+---
+
+## Model Details
+
+| Field | Value |
+|---|---|
+| **Base model** | [`unsloth/Llama-3.2-3B-Instruct-bnb-4bit`](https://huggingface.co/unsloth/Llama-3.2-3B-Instruct-bnb-4bit) |
+| **Model type** | Causal LM — LoRA adapter (PEFT) on Llama-3.2-3B-Instruct |
+| **Language** | English |
+| **License** | [Meta Llama 3.2 Community License](https://www.llama.com/llama3_2/license/) |
+| **Training framework** | Unsloth + TRL SFTTrainer |
+| **Hardware** | Tesla T4 (Kaggle) |
+| **Max sequence length** | 2048 |
+
+---
+
+## Intended Use
+
+Generating step-by-step reasoning traces (`<think>` blocks) followed by final answers across a broad range of instruction-following tasks. Useful for studying how reasoning distillation scales to sub-4B models and how registered thinking tokens affect small-model behaviour.
+
+**Not intended for:** production use, mathematical proofs requiring reliability, or replacing a larger reasoning model. Benchmark regressions vs base are expected until verified otherwise.
+
+---
+
+## How to Get Started
+
+### From the adapter
+
+The LoRA adapter is available separately — load it on top of the base model without downloading the full merged weights.
+
+> **Important:** load the tokenizer from the adapter directory, not the base model. The adapter tokenizer carries the correct 128258-token vocabulary with `<think>`/`</think>` baked in. Using the base model tokenizer (128256) will cause an embedding dimension mismatch.
+
+```python
+from unsloth import FastLanguageModel
+from transformers import AutoTokenizer, TextStreamer
+from peft import PeftModel
+
+ADAPTER_PATH = "codestrate/Llama3.2-3B-Claude-Reasoning-Distill"
+
+model, _ = FastLanguageModel.from_pretrained(
+    model_name="unsloth/Llama-3.2-3B-Instruct-bnb-4bit",
+    load_in_4bit=True,
+    max_seq_length=2048,
+)
+tokenizer = AutoTokenizer.from_pretrained(ADAPTER_PATH)  # vocab=128258
+model.resize_token_embeddings(len(tokenizer))
+model = PeftModel.from_pretrained(model, ADAPTER_PATH)
+FastLanguageModel.for_inference(model)
+
+SYSTEM_PROMPT = "You are a helpful assistant. Think step by step inside <think>...</think> before giving your final answer."
+messages = [
+    {"role": "system", "content": SYSTEM_PROMPT},
+    {"role": "user", "content": "Write a Python function to check if a number is prime."},
+]
+inputs = tokenizer.apply_chat_template(messages, return_tensors="pt").to("cuda")
+
+streamer = TextStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+_ = model.generate(
+    input_ids=inputs,
+    streamer=streamer,
+    max_new_tokens=1024,
+    temperature=0.7,
+    min_p=0.1,
+    repetition_penalty=1.3,
+    no_repeat_ngram_size=6,
+    use_cache=True,
+)
+```
+
+### From GGUF (Ollama / LM Studio)
+
+A Modelfile is included for Ollama. For direct use:
+
+```
+ollama run hf.co/codestrate/Llama3.2-3B-Claude-Reasoning-Distill:Q4_K_M
+```
+
+---
+
+## Training Details
+
+### Dataset
+
+[`angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k`](https://huggingface.co/datasets/angrygiraffe/claude-opus-4.6-4.7-reasoning-8.7k) — `instruct_train.jsonl` split (full instruct + reasoning, ~7,700 examples). Data already in OpenAI messages format; mapped directly through `apply_chat_template` with no additional preprocessing.
+
+The previous 1B run used only the `coding` + `math` categories (~2,000 examples). This run uses the full instruct split for broader coverage.
+
+### Hyperparameters
+
+| Parameter | Value |
+|---|---|
+| LoRA Rank / Alpha | 32 / 64 |
+| Target Modules | All |
+| Sequence Length | 2048 |
+| Effective Batch | 16 (2 × grad_accum 8) |
+| Steps | 904 (~2 epochs) |
+| Learning Rate | 1e-4 / cosine |
+| Warmup Steps | 50 |
+| Optimizer | adamw_8bit |
+| Weight Decay | 0.01 |
+| Precision | bfloat16 |
+
+### Loss Curve
+
+![Loss Curve](loss_curve_with_rolling_average.png)
+
+| Step | Loss | Step | Loss | Step | Loss |
+|---|---|---|---|---|---|
+| 50 | 2.1372 | 350 | 1.8798 | 650 | 1.7567 |
+| 100 | 1.9597 | 400 | 1.8512 | 700 | 1.7530 |
+| 150 | 1.9251 | 450 | 1.8493 | 750 | **1.7391** |
+| 200 | 1.8972 | 500 | 1.7670 | 800 | 1.7709 |
+| 250 | 1.8891 | 550 | 1.7707 | 850 | 1.7401 |
+| 300 | 1.8738 | 600 | 1.7668 | 900 | 1.7598 |
+
+Drop: 2.14 → 1.74 (~0.40 absolute). Visible cross-epoch improvement at step ~452 (−0.082). Plateau reached in epoch 2 from step 750 — a third epoch would not have been beneficial on this dataset.
+
+---
+
+## Known Limitations
+
+- **Benchmarks not yet available** — results will be added when the evaluation runs complete
+- **Echolalia / repetition** — reduced vs the 1B run due to special token boundaries, but not eliminated; `repetition_penalty=1.3` and `no_repeat_ngram_size=6` are recommended at inference (needs more testing)
+- **System prompt required** — without the `<think>...</think>` contract in the system prompt, the model may not cleanly transition from reasoning block to final answer
+- **Not a production model** — a research artefact studying reasoning distillation at sub-4B scale
+
+---
+
+## Available Files
+
+| File | Format | Use |
+|---|---|---|
+| `Llama-3.2-3B-Claude-Reasoning-Distill.Q4_K_M.gguf` | GGUF Q4_K_M | LM Studio / Ollama (recommended) |
+| `Llama-3.2-3B-Claude-Reasoning-Distill.Q8_0.gguf` | GGUF Q8 | Higher fidelity inference (near lossless; still lightweight)|
+| `Llama-3.2-3B-Claude-Reasoning-Distill.F16.gguf` | GGUF F16 | Full precision GGUF |
+| Adapter (`adapter_model.safetensors`) | LoRA adapter | PEFT inference / further fine-tuning |
+
+---
+
+## Framework Versions
+
+- Python 3.12.13
+- Unsloth 2026.5.8
+- PEFT 0.19.1
+- TRL 0.24.0
+- PyTorch 2.10.0+cu128
+- Transformers 4.47.1
+
+---
+
+*Predecessor: [Llama3.2-1B-Claude-Opus-Reasoning-Distill](https://huggingface.co/codestrate/Llama3.2-1B-Claude-Opus-Reasoning-Distill)*  
+*Trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth)*  
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

config.json

@@ -0,0 +1,38 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "dtype": "float16",
+  "eos_token_id": 128009,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 3072,
+  "initializer_range": 0.02,
+  "intermediate_size": 8192,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "pad_token_id": 128004,
+  "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": "5.5.0",
+  "unsloth_fixed": true,
+  "unsloth_version": "2026.5.8",
+  "use_cache": true,
+  "vocab_size": 128258
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "do_sample": true,
+  "max_new_tokens": 1024,
+  "min_p": 0.1,
+  "no_repeat_ngram_size": 6,
+  "repetition_penalty": 1.3,
+  "temperature": 0.7,
+  "transformers_version": "5.5.0"
+}

loss_curve_with_rolling_average.png

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41d8d767c5d5621feb0573e489e60ceb61c0cfa22adc1837ae46a713ecac57ef
+size 135182