RichardErkhov/TheTravellingEngineer_-_llama2-7b-chat-hf-guanaco-gguf

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama2-7b-chat-hf-guanaco - GGUF

• Model creator: https://huggingface.co/TheTravellingEngineer/
• Original model: https://huggingface.co/TheTravellingEngineer/llama2-7b-chat-hf-guanaco/

Name	Quant method	Size
llama2-7b-chat-hf-guanaco.Q2_K.gguf	Q2_K	2.36GB
llama2-7b-chat-hf-guanaco.IQ3_XS.gguf	IQ3_XS	2.6GB
llama2-7b-chat-hf-guanaco.IQ3_S.gguf	IQ3_S	2.75GB
llama2-7b-chat-hf-guanaco.Q3_K_S.gguf	Q3_K_S	2.75GB
llama2-7b-chat-hf-guanaco.IQ3_M.gguf	IQ3_M	2.9GB
llama2-7b-chat-hf-guanaco.Q3_K.gguf	Q3_K	3.07GB
llama2-7b-chat-hf-guanaco.Q3_K_M.gguf	Q3_K_M	3.07GB
llama2-7b-chat-hf-guanaco.Q3_K_L.gguf	Q3_K_L	3.35GB
llama2-7b-chat-hf-guanaco.IQ4_XS.gguf	IQ4_XS	3.4GB
llama2-7b-chat-hf-guanaco.Q4_0.gguf	Q4_0	3.56GB
llama2-7b-chat-hf-guanaco.IQ4_NL.gguf	IQ4_NL	3.58GB
llama2-7b-chat-hf-guanaco.Q4_K_S.gguf	Q4_K_S	3.59GB
llama2-7b-chat-hf-guanaco.Q4_K.gguf	Q4_K	3.8GB
llama2-7b-chat-hf-guanaco.Q4_K_M.gguf	Q4_K_M	3.8GB
llama2-7b-chat-hf-guanaco.Q4_1.gguf	Q4_1	3.95GB
llama2-7b-chat-hf-guanaco.Q5_0.gguf	Q5_0	4.33GB
llama2-7b-chat-hf-guanaco.Q5_K_S.gguf	Q5_K_S	4.33GB
llama2-7b-chat-hf-guanaco.Q5_K.gguf	Q5_K	4.45GB
llama2-7b-chat-hf-guanaco.Q5_K_M.gguf	Q5_K_M	4.45GB
llama2-7b-chat-hf-guanaco.Q5_1.gguf	Q5_1	4.72GB
llama2-7b-chat-hf-guanaco.Q6_K.gguf	Q6_K	5.15GB
llama2-7b-chat-hf-guanaco.Q8_0.gguf	Q8_0	6.67GB

Original model description: The base model is meta's Llama-2-7b-chat-hf. It was finetuned using SFT and the Guanaco dataset and the model prompt is similar to the original Guanaco model. This repo contains the merged fp16 model.

Legal Disclaimer: This model is bound by the usage restrictions of the original Llama-2 model. And comes with no warranty or gurantees of any kind.

• license:
  • llama2
    
• datasets:
  • timdettmers/openassistant-guanaco
    
• language:
  • en
    
• reference: https://gist.github.com/younesbelkada/9f7f75c94bdc1981c8ca5cc937d4a4da

---