初始化项目，由ModelHub XC社区提供模型

Model: Ma7ee7/SmolLM2-135M-Reasoning-5K
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 +1,114 @@
+---
+base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+datasets:
+- SupraLabs/reasoning-corpus-4K-5M-v1
+library_name: transformers
+pipeline_tag: text-generation
+license: apache-2.0
+language:
+- en
+tags:
+- smollm2
+- reasoning
+- supervised-fine-tuning
+- chat
+- transformers
+- safetensors
+---
+
+# SmolLM2-135M Reasoning-5K
+
+A full-parameter reasoning fine-tune of
+[`HuggingFaceTB/SmolLM2-135M-Instruct`](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct) using 5,000 examples
+sampled from [`SupraLabs/reasoning-corpus-4K-5M-v1`](https://huggingface.co/datasets/SupraLabs/reasoning-corpus-4K-5M-v1).
+
+The model was trained to place its reasoning trace inside `<think>` and
+`</think>` tags, followed by a separate final answer.
+
+## Training summary
+
+| Setting | Value |
+|---|---:|
+| Training examples | 5,000 |
+| Evaluation examples | 128 |
+| Epochs | 2 |
+| Maximum sequence length | 4,096 tokens |
+| Learning rate | 3e-05 |
+| Training objective | Assistant-only causal cross-entropy |
+| Parameter training | Full model |
+| Precision | bfloat16/float16 depending on training GPU |
+
+The system and user portions were masked from the loss. Samples exceeding the
+maximum context length were rejected instead of being cut through the middle of
+a reasoning trace.
+
+## Usage
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model_id = "YOUR_USERNAME/SmolLM2-135M-Reasoning-5K"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype="auto",
+    device_map="auto",
+)
+
+messages = [
+    {
+        "role": "system",
+        "content": 'You are a helpful AI assistant. For difficult problems, reason carefully inside <think> and </think> tags, then provide a clear final answer.',
+    },
+    {
+        "role": "user",
+        "content": "A farmer has 17 sheep. All but 9 run away. How many remain?",
+    },
+]
+
+inputs = tokenizer.apply_chat_template(
+    messages,
+    tokenize=True,
+    add_generation_prompt=True,
+    return_tensors="pt",
+    return_dict=True,
+).to(model.device)
+
+with torch.inference_mode():
+    output = model.generate(
+        **inputs,
+        max_new_tokens=256,
+        do_sample=False,
+        repetition_penalty=1.05,
+    )
+
+new_tokens = output[0, inputs["input_ids"].shape[1]:]
+print(tokenizer.decode(new_tokens, skip_special_tokens=False))
+```
+
+## Reasoning format
+
+The expected assistant format is:
+
+```text
+<think>
+Internal reasoning trace
+</think>
+
+Final answer
+```
+
+This small model is experimental. It should not be assumed to produce correct
+reasoning merely because it emits a structured reasoning trace.
+
+## Files
+
+`training_info.json` records the training configuration, any metrics found in
+the local output directory, and SHA-256 hashes of the uploaded weight files.
+
+## License
+
+The model follows the Apache 2.0 license used by the base SmolLM2 model. Review
+the base model repository and source dataset for their complete terms.

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 +1,38 @@
+{
+  "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_scaling": null,
+  "rope_theta": 100000,
+  "tie_word_embeddings": true,
+  "transformers.js_config": {
+    "kv_cache_dtype": {
+      "fp16": "float16",
+      "q4f16": "float16"
+    }
+  },
+  "transformers_version": "4.57.6",
+  "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": "4.57.6"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d4e7b05c25b575e1519ea785a69792f0cff31843fbaf3e1f05e213cfb3315ce
+size 269060552

special_tokens_map.json

@@ -0,0 +1,34 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,154 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<repo_name>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<file_sep>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<jupyter_script>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": "<|im_start|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": {},
+  "model_max_length": 8192,
+  "pad_token": "<|im_end|>",
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

training_info.json

@@ -0,0 +1,60 @@
+{
+  "model_name": "SmolLM2-135M-Reasoning-5K",
+  "base_model": "HuggingFaceTB/SmolLM2-135M-Instruct",
+  "dataset": "SupraLabs/reasoning-corpus-4K-5M-v1",
+  "training_method": "full-parameter supervised fine-tuning",
+  "training_rows": 5000,
+  "evaluation_rows": 128,
+  "epochs": 2,
+  "learning_rate": 3e-05,
+  "maximum_sequence_length": 4096,
+  "loss_masking": "assistant tokens only",
+  "reasoning_format": "<think>reasoning</think> followed by the final answer",
+  "system_prompt": "You are a helpful AI assistant. For difficult problems, reason carefully inside <think> and </think> tags, then provide a clear final answer.",
+  "architecture": [
+    "LlamaForCausalLM"
+  ],
+  "model_type": "llama",
+  "hidden_size": 576,
+  "num_hidden_layers": 30,
+  "vocab_size": 49152,
+  "weight_size_bytes": 269060552,
+  "weight_sha256": {
+    "model.safetensors": "5d4e7b05c25b575e1519ea785a69792f0cff31843fbaf3e1f05e213cfb3315ce"
+  },
+  "recorded_training_metrics": {
+    "train_results.json": {
+      "epoch": 1.0,
+      "total_flos": 1.2703418486728704e+16,
+      "train_loss": 1.257179560470581,
+      "train_runtime": 2169.844,
+      "train_samples_per_second": 4.609,
+      "train_steps_per_second": 0.288
+    },
+    "eval_results.json": {
+      "epoch": 1.0,
+      "eval_loss": 1.272692322731018,
+      "eval_runtime": 7.2216,
+      "eval_samples_per_second": 17.725,
+      "eval_steps_per_second": 8.862
+    },
+    "all_results.json": {
+      "epoch": 1.0,
+      "eval_loss": 1.272692322731018,
+      "eval_runtime": 7.2216,
+      "eval_samples_per_second": 17.725,
+      "eval_steps_per_second": 8.862,
+      "total_flos": 1.2703418486728704e+16,
+      "train_loss": 1.257179560470581,
+      "train_runtime": 2169.844,
+      "train_samples_per_second": 4.609,
+      "train_steps_per_second": 0.288
+    },
+    "trainer_state_summary": {
+      "best_metric": 1.2715508937835693,
+      "best_model_checkpoint": "/content/SmolLM2-135M-Reasoning-5K/checkpoint-624",
+      "epoch": 1.0,
+      "global_step": 625
+    }
+  }
+}