初始化项目，由ModelHub XC社区提供模型

Model: Kerassy/qwen-2.5-3b-smoltalk-sft
Source: Original Platform

.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

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+tags:
+- text-generation
+- casual-lm
+- sft
+- trl
+base_model: Qwen/Qwen2.5-3B
+datasets:
+- HuggingFaceTB/smoltalk
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# Qwen-2.5-3B Smoltalk SFT
+
+This is a fine-tuned version of the 3-billion parameter **Qwen/Qwen2.5-3B** base model. It has been instruction fine-tuned via Low-Rank Adaptation (LoRA) and fully merged.
+
+## Model Details
+
+- **Base Model:** Qwen/Qwen2.5-3B
+- **Fine-tuning Dataset:** HuggingFaceTB/smoltalk (everyday-conversations subset)
+- **Methodology:** Supervised Fine-Tuning (SFT) using TRL
+- **Hardware Used:** 1 x NVIDIA L4 GPU (24GB VRAM)
+
+## How to Get Started
+
+You can load and use this model directly with the Hugging Face `pipeline` API.
+
+```python
+import torch
+from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
+
+MODEL_ID = "Kerassy/qwen-2.5-3b-smoltalk-sft"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID, 
+    torch_dtype=torch.bfloat16 if torch.cuda.is_bf16_supported() else torch.float16,
+    device_map="auto"
+)
+
+pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)
+
+messages = [
+    {"role": "user", "content": "Why is the sky blue?"}
+]
+
+formatted_prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+
+outputs = pipe(
+    formatted_prompt, 
+    max_new_tokens=128, 
+    do_sample=True, 
+    temperature=0.7,
+    top_k=40,
+    clean_up_tokenization_spaces=False,
+    pad_token_id=tokenizer.pad_token_id,
+    eos_token_id=tokenizer.encode("<|end|>")[0] if "<|end|>" in tokenizer.get_vocab() else tokenizer.eos_token_id
+)
+
+print(outputs[0]['generated_text'])

chat_template.jinja

@@ -0,0 +1,7 @@
+{%- for message in messages -%}{%- if message['role'] == 'user' -%}{{ '<|user|>
+' + message['content'] + '
+' }}{%- elif message['role'] == 'assistant' -%}{{ '<|assistant|>
+' }}{%- generation -%}{{ message['content'] + '<|end|>
+' }}{%- endgeneration -%}{%- else -%}{{ '<|system|>
+' + message['content'] + '
+' }}{%- endif -%}{%- endfor -%}

config.json

@@ -0,0 +1,70 @@
+{
+  "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": 32768,
+  "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": "5.12.1",
+  "use_cache": true,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": false,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "5.12.1"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c025e3825192f4cc0b5e60a3cc31e0019fb7be5a3bae6bd110ef9d99fdf5d52
+size 6171927112

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd169731d2cbde95e10bf356d66d5997fd885dd8dbb6fb4684da3f23b2585d8
+size 11421892

tokenizer_config.json

@@ -0,0 +1,30 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "is_local": true,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}