You can deploy this model and start earning money today!

RichardErkhov/
JCX-kcuf_-_Llama-2-7b-hf-llama2-chat-80k-gguf

Name: JCX-kcuf_-_Llama-2-7b-hf-llama2-chat-80k-gguf
Availability: InStock

endpoints_compatible

gguf

template

Views

No views yet

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-2-7b-hf-llama2-chat-80k - GGUF

Model creator: https://huggingface.co/JCX-kcuf/
Original model: https://huggingface.co/JCX-kcuf/Llama-2-7b-hf-llama2-chat-80k/

Name	Quant method	Size
Llama-2-7b-hf-llama2-chat-80k.Q2_K.gguf	Q2_K	2.36GB
Llama-2-7b-hf-llama2-chat-80k.IQ3_XS.gguf	IQ3_XS	2.6GB
Llama-2-7b-hf-llama2-chat-80k.IQ3_S.gguf	IQ3_S	2.75GB
Llama-2-7b-hf-llama2-chat-80k.Q3_K_S.gguf	Q3_K_S	2.75GB
Llama-2-7b-hf-llama2-chat-80k.IQ3_M.gguf	IQ3_M	2.9GB
Llama-2-7b-hf-llama2-chat-80k.Q3_K.gguf	Q3_K	3.07GB
Llama-2-7b-hf-llama2-chat-80k.Q3_K_M.gguf	Q3_K_M	3.07GB
Llama-2-7b-hf-llama2-chat-80k.Q3_K_L.gguf	Q3_K_L	3.35GB
Llama-2-7b-hf-llama2-chat-80k.IQ4_XS.gguf	IQ4_XS	3.4GB
Llama-2-7b-hf-llama2-chat-80k.Q4_0.gguf	Q4_0	3.56GB
Llama-2-7b-hf-llama2-chat-80k.IQ4_NL.gguf	IQ4_NL	3.58GB
Llama-2-7b-hf-llama2-chat-80k.Q4_K_S.gguf	Q4_K_S	3.59GB
Llama-2-7b-hf-llama2-chat-80k.Q4_K.gguf	Q4_K	3.8GB
Llama-2-7b-hf-llama2-chat-80k.Q4_K_M.gguf	Q4_K_M	3.8GB
Llama-2-7b-hf-llama2-chat-80k.Q4_1.gguf	Q4_1	3.95GB
Llama-2-7b-hf-llama2-chat-80k.Q5_0.gguf	Q5_0	4.33GB
Llama-2-7b-hf-llama2-chat-80k.Q5_K_S.gguf	Q5_K_S	4.33GB
Llama-2-7b-hf-llama2-chat-80k.Q5_K.gguf	Q5_K	4.45GB
Llama-2-7b-hf-llama2-chat-80k.Q5_K_M.gguf	Q5_K_M	4.45GB
Llama-2-7b-hf-llama2-chat-80k.Q5_1.gguf	Q5_1	4.72GB
Llama-2-7b-hf-llama2-chat-80k.Q6_K.gguf	Q6_K	5.15GB
Llama-2-7b-hf-llama2-chat-80k.Q8_0.gguf	Q8_0	6.67GB

Original model description:

license: apache-2.0

Description

This model is finetuned on the distillation data from Llama-2-7b-chat-hf. The base model is meta-llama/Llama-2-7b-hf

Usage

The model has a query format as in llama-2.

<s> [INST] <<SYS>>
You are a helpful, respectful and honest assistant. Always answer as helpfully as possible, while being safe.  Your answers should not include any harmful, unethical, racist, sexist, toxic, dangerous, or illegal content. Please ensure that your responses are socially unbiased and positive in nature.

If a question does not make any sense, or is not factually coherent, explain why instead of answering something not correct. If you don't know the answer to a question, please don't share false information.
<</SYS>>

{query} [/INST]

RichardErkhov/JCX-kcuf_-_Llama-2-7b-hf-llama2-chat-80k-gguf

Original model description:

license: apache-2.0

Description

Usage

RichardErkhov/
JCX-kcuf_-_Llama-2-7b-hf-llama2-chat-80k-gguf