该模型当前使用的是默认介绍模版,处于“预发布”阶段,页面仅限所有者可见。
请根据模型贡献文档说明,及时完善模型卡片内容。ModelScope平台将在模型卡片完善后展示。谢谢您的理解。
Clone with HTTP
git clone https://www.modelscope.cn/levenchen/Llama-2-7b-hm.git
Training procedure
The following bitsandbytes
quantization config was used during training:
- quant_method: bitsandbytes
- loadin8bit: False
- loadin4bit: True
- llmint8threshold: 6.0
- llmint8skip_modules: None
- llmint8enablefp32cpu_offload: False
- llmint8hasfp16weight: False
- bnb4bitquant_type: nf4
- bnb4bitusedoublequant: True
- bnb4bitcompute_dtype: bfloat16
Framework versions
- SWIFT 1.2.0
Base model information
- BaseModel Class LlamaForCausalLM
评论