初始化项目，由ModelHub XC社区提供模型

Model: ping98k/open-llama-3b-openthought-mid-4bit
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 +1,52 @@
+---
+library_name: transformers
+base_model: openlm-research/open_llama_3b_v2
+tags:
+  - 4bit
+  - bnb
+  - nf4
+  - reasoning
+  - think
+  - openthoughts
+  - sft
+---
+
+# open-llama-3b-openthought-mid-4bit
+
+Merged and 4-bit quantized OpenLLaMA 3B v2 fine-tuned on OpenThoughts-114k reasoning data.
+
+## How it was made
+
+1. Base: [openlm-research/open_llama_3b_v2](https://huggingface.co/openlm-research/open_llama_3b_v2)
+2. QLoRA fine-tuned on [open-thoughts/OpenThoughts-114k](https://huggingface.co/datasets/open-thoughts/OpenThoughts-114k)
+3. Merged LoRA into base (16bit)
+4. Quantized to 4-bit NF4
+
+## Training Data
+
+- open-thoughts/OpenThoughts-114k (DeepSeek-R1 reasoning traces)
+- 10,582 samples after filtering (<= 2024 tokens)
+- 3 epochs, bs=128, cosine LR 2e-4
+- Final loss: 0.71
+
+## Usage
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+model = AutoModelForCausalLM.from_pretrained("ping98k/open-llama-3b-openthought-mid-4bit", device_map="auto")
+tokenizer = AutoTokenizer.from_pretrained("ping98k/open-llama-3b-openthought-mid-4bit")
+
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": "What is a linked list?"},
+]
+prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=True)
+inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
+output = model.generate(**inputs, max_new_tokens=512, temperature=0.7, do_sample=True)
+print(tokenizer.decode(output[0], skip_special_tokens=False))
+```
+
+## LoRA adapter
+
+See [ping98k/open-llama-3b-openthought-mid-lora](https://huggingface.co/ping98k/open-llama-3b-openthought-mid-lora)

chat_template.jinja

@@ -0,0 +1 @@
+{%- if messages[0].role == 'system' %}{{ '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}{%- endif %}{%- for message in messages %}{%- if message.role == 'system' %}{%- elif message.role == 'user' %}{{ '<|im_start|>user\n' + message.content + '<|im_end|>\n' }}{%- elif message.role == 'assistant' %}{%- if message.content is defined and message.content %}{{ '<|im_start|>assistant\n' + message.content + '<|im_end|>\n' }}{%- endif %}{%- elif message.role == 'tool' %}{{ '<|im_start|>user\n<tool_response>\n' + message.content + '\n</tool_response><|im_end|>\n' }}{%- endif %}{%- endfor %}{%- if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{%- if enable_thinking is defined and enable_thinking is true %}{{ '<think>\n' }}{%- endif %}{%- endif %}

config.json

@@ -0,0 +1,47 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 100,
+  "hidden_act": "silu",
+  "hidden_size": 3200,
+  "initializer_range": 0.02,
+  "intermediate_size": 8640,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 26,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "_load_in_4bit": true,
+    "_load_in_8bit": false,
+    "bnb_4bit_compute_dtype": "bfloat16",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "nf4",
+    "bnb_4bit_use_double_quant": true,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": true,
+    "load_in_8bit": false,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "use_cache": true,
+  "vocab_size": 32011
+}

generation_config.json

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

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4d7e3d0d34229db2c37281144b9b87cb0dbf20351b59ddbaeda19765d0bb0a5e
+size 2072319759

tokenizer_config.json

@@ -0,0 +1,27 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "extra_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|endoftext|>",
+    "<think>",
+    "</think>",
+    "<tool_call>",
+    "</tool_call>",
+    "<tool_response>",
+    "</tool_response>",
+    "<tools>",
+    "</tools>"
+  ],
+  "is_local": true,
+  "model_max_length": 2048,
+  "pad_token": "<|endoftext|>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}