YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co./docs/hub/model-cards#model-card-metadata)
该模型支持ollama，量化4bit（Q4_K_M）可以在8GB显存下流畅推理。
1.首先shell要cd到你想下载到本地的目录，完成后运行:git lfs install&&git clone https://huggingface.co./DudeGuuud/DaiDai_Bot_4bit
2.继续cd到modelfile所存在的目录，运行:ollama create daibot(或设定你喜欢的名字) -f modelfile
3.启动模型:ollama run daibot(或你设定的名字)
PS：在一些情况下模型会重复自言自语，颇有自闭症的感觉，建议出现此问题时再调整温度和topp相关，或者关掉上下文/set nohistory或者及时/clear清楚以往对话信息
感谢开源框架unsloth，感谢谷歌colab，得益于unsloth框架惊人的训练速度，简单的任务可以在colab用很短的时间完成！
base_model: unsloth/meta-llama-3.1-8b-bnb-4bit tags: - text-generation-inference - transformers - unsloth - llama - gguf license: apache-2.0 language: - en
Uploaded model
- Developed by: DudeGuuud
- License: apache-2.0
- Finetuned from model : unsloth/meta-llama-3.1-8b-bnb-4bit
This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.
- Downloads last month
- 40