metadata
license: apache-2.0
base_model: unsloth/DeepSeek-R1-Distill-Llama-8B
tags:
- text-generation
- frontend
- analysis
- requirements
- chinese
- lora
- peft
- sft
- trl
- unsloth
- conversational
pipeline_tag: text-generation
analysis-llm-v1
这是一个基于 DeepSeek-R1-Distill-Llama-8B 微调的前端需求分析模型。
使用方法
from transformers import AutoTokenizer, AutoModelForCausalLM
import torch
model_name = "MANSTAGE/analysis-llm-v1"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float16)
# 推理代码...
训练详情
- 基础模型: unsloth/DeepSeek-R1-Distill-Llama-8B
- 训练数据: 219条前端需求分析数据
- 训练步数: 100步
- LoRA配置: r=16, alpha=16