初始化项目，由ModelHub XC社区提供模型

Model: Avtrkrb/SmolLM2-135M-Instruct-bnb-4bit-reasoning
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.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

README.md

@@ -0,0 +1,93 @@
+---
+license: apache-2.0
+language:
+  - en
+
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+
+library_name: transformers
+
+pipeline_tag: text-generation
+
+tags:
+  - smollm2
+  - reasoning
+  - chain-of-thought
+  - instruct
+  - lora
+  - merged
+
+datasets:
+  - Avtrkrb/combined-reasoning
+---
+
+# SmolLM2-135M-Instruct-Reasoning
+
+A reasoning-focused fine-tune of SmolLM2-135M-Instruct trained using Unsloth on the combined-reasoning dataset.
+
+## Model Overview
+
+This model was created by fine-tuning SmolLM2-135M-Instruct on a reasoning-oriented dataset containing step-by-step solutions and structured problem-solving examples.
+
+The model is intended to:
+
+- Produce detailed reasoning traces
+- Explain intermediate steps
+- Perform multi-step logical reasoning
+- Improve instruction following
+- Generate transparent solutions instead of only final answers
+
+## Base Model
+
+HuggingFaceTB/SmolLM2-135M-Instruct
+
+## Dataset
+
+Avtrkrb/combined-reasoning
+
+## Training Method
+
+- Framework: Unsloth
+- Fine-tuning type: LoRA
+- Task: Supervised Fine-Tuning (SFT)
+
+## Prompt Format
+
+This model uses the standard SmolLM2 chat template.
+
+<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face
+<|im_end|>
+
+<|im_start|>user
+What is 17 × 23?
+<|im_end|>
+
+<|im_start|>assistant
+
+## Example Usage
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+model_id = "Avtrkrb/SmolLM2-135M-Instruct-bnb-4bit-reasoning"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(model_id)
+
+## Intended Use
+
+- Reasoning tasks
+- Educational explanations
+- Problem solving
+- Step-by-step analysis
+
+## Limitations
+
+- Small 135M parameter model
+- Reasoning quality is limited compared to larger models
+- May hallucinate facts
+- Should not be used for high-stakes decisions
+
+## License
+
+Apache 2.0 (inherits base model licensing)

chat_template.jinja

@@ -0,0 +1,6 @@
+{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system
+You are a helpful AI assistant named SmolLM, trained by Hugging Face<|im_end|>
+' }}{% endif %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

config.json

@@ -0,0 +1,40 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 576,
+  "initializer_range": 0.041666666666666664,
+  "intermediate_size": 1536,
+  "is_llama_config": true,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 9,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 3,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_interleaved": false,
+  "rope_parameters": {
+    "rope_theta": 100000,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": true,
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "5.5.0",
+  "use_cache": true,
+  "vocab_size": 49152
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "5.5.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:558882433ce1dbc5af0b00267ed265de8e912b2ee6258de915aee52daf3ab0ae
+size 269060552

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}