Downloads · 30 days
14
19% of all-time downloads
Mixllama-2x7b-4bit-bitsnbytes
uisikdag/Mixllama-2x7b-4bit-bitsnbytes
Mixllama-2x7b-4bit-bitsnbytes is a text generation model from uisikdag. Use it when you need the model to write or continue text. It is set up for transformers.
All-time downloads
72
Public
Parameters
11.2B
7.1 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors7.1 GB · 100%
Parameter types
How the weights are stored.
U810.8B · 96%
Try a prompt
Model card
From the Hugging Face model README
Model Card for Model ID
prepared with mergekit
quantized 4 bits with bitsandbytes
base_model: meta-llama/Llama-2-7b-chat-hf
gate_mode: cheap_embed
experts:
- source_model: meta-llama/Llama-2-7b-chat-hf
positive_prompts: ["You are an helpful assistant."]
- source_model: TheTravellingEngineer/llama2-7b-hf-guanaco
positive_prompts: ["You are an helpful general-pupose assistant"]
- Task
- Text Generation
- Library
- transformers
- Type
- mixtral
- Created
- Mar 13, 2024
- Updated
- Mar 13, 2024