CoolFace
Modelpublic

RichardErkhov/JCX-kcuf_-_Llama-2-7b-chat-hf-gpt-4-80k-base_lora-gguf

sourceHugging Faceupdated 2y agoView on Hugging Face
0likes3.2kdownloads
Model Card

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-2-7b-chat-hf-gpt-4-80k-base_lora - GGUF

  • —Model creator: https://huggingface.co/JCX-kcuf/
  • —Original model: https://huggingface.co/JCX-kcuf/Llama-2-7b-chat-hf-gpt-4-80k-base_lora/
NameQuant methodSize
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q2_K.ggufQ2_K2.36GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.IQ3_XS.ggufIQ3_XS2.6GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.IQ3_S.ggufIQ3_S2.75GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q3_K_S.ggufQ3KS2.75GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.IQ3_M.ggufIQ3_M2.9GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q3_K.ggufQ3_K3.07GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q3_K_M.ggufQ3KM3.07GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q3_K_L.ggufQ3KL3.35GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.IQ4_XS.ggufIQ4_XS3.4GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q4_0.ggufQ4_03.56GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.IQ4_NL.ggufIQ4_NL3.58GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q4_K_S.ggufQ4KS3.59GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q4_K.ggufQ4_K3.8GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q4_K_M.ggufQ4KM3.8GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q4_1.ggufQ4_13.95GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q5_0.ggufQ5_04.33GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q5_K_S.ggufQ5KS4.33GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q5_K.ggufQ5_K4.45GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q5_K_M.ggufQ5KM4.45GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q5_1.ggufQ5_14.72GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q6_K.ggufQ6_K5.15GB
Llama-2-7b-chat-hf-gpt-4-80k-base_lora.Q8_0.ggufQ8_06.67GB

Original model description: --- license: apache-2.0 ---

Description

This model is finetuned on the distillation data from GPT-4. The base model is meta-llama/Llama-2-7b-chat-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]