Downloads · 30 days
15
31% of all-time downloads
bishang520/Lit-VLLM-Agent-AWQ
Lit-VLLM-Agent-AWQ is a text generation model from bishang520. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
学术文档 Agent 专用模型:基于 Qwen2-7B 经过学术领域词表扩充、SFT 指令微调与 DPO 偏好对齐,再以 AWQ 4-bit 量化压缩,面向科研论文/技术文档的结构化问答与引用溯源场景。
Downloads · 30 days
15
31% of all-time downloads
All-time downloads
49
Public
Parameters
7.6B
5.6 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors5.6 GB · 100%
How the weights are stored.
I326.5B · 86%
From the Hugging Face model README
学术文档 Agent 专用模型:基于 Qwen2-7B 经过学术领域词表扩充、SFT 指令微调与 DPO 偏好对齐,再以 AWQ 4-bit 量化压缩,面向科研论文/技术文档的结构化问答与引用溯源场景。
| 项 | 值 |
|---|---|
| 基座模型 | Qwen/Qwen2-7B |
| 词表大小 | 151,806(原版 151,643 + 141 个学术领域 token) |
| 量化 | AWQ 4-bit,group_size=128,version=gemm |
| 微调 | SFT(QLoRA + DeepSpeed ZeRO-2)→ DPO 偏好对齐 |
| 输出格式 | 带结构化引用(JSON Schema / Guided Decoding 强约束) |
| 权重 | ~5.2 GB(2 个 safetensors 分片) |
vllm serve bishang520/Lit-VLLM-Agent-AWQ \
--task generate \
--quantization awq \
--dtype float16 \
--max-model-len 8192 \
--guided-decoding-backend xgrammar
from transformers import AutoModelForCausalLM, AutoTokenizer
model = AutoModelForCausalLM.from_pretrained(
"bishang520/Lit-VLLM-Agent-AWQ",
device_map="auto",
)
tokenizer = AutoTokenizer.from_pretrained("bishang520/Lit-VLLM-Agent-AWQ")