MaziyarPanahi_-_Llama-3-70B-Instruct-32k-v0.1-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
MaziyarPanahi_-_Llama-3-70B-Instruct-32k-v0.1-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

Llama-3-70B-Instruct-32k-v0.1 - GGUF

Model creator: https://huggingface.co/MaziyarPanahi/
Original model: https://huggingface.co/MaziyarPanahi/Llama-3-70B-Instruct-32k-v0.1/

Name	Quant method	Size
Llama-3-70B-Instruct-32k-v0.1.Q2_K.gguf	Q2_K	24.56GB
Llama-3-70B-Instruct-32k-v0.1.Q3_K_S.gguf	Q3_K_S	28.79GB
Llama-3-70B-Instruct-32k-v0.1.Q3_K.gguf	Q3_K	31.91GB
Llama-3-70B-Instruct-32k-v0.1.Q3_K_M.gguf	Q3_K_M	31.91GB
Llama-3-70B-Instruct-32k-v0.1.Q3_K_L.gguf	Q3_K_L	34.59GB
Llama-3-70B-Instruct-32k-v0.1.IQ4_XS.gguf	IQ4_XS	35.64GB
Llama-3-70B-Instruct-32k-v0.1.Q4_0.gguf	Q4_0	37.22GB
Llama-3-70B-Instruct-32k-v0.1.IQ4_NL.gguf	IQ4_NL	37.58GB
Llama-3-70B-Instruct-32k-v0.1.Q4_K_S.gguf	Q4_K_S	37.58GB
Llama-3-70B-Instruct-32k-v0.1.Q4_K.gguf	Q4_K	39.6GB
Llama-3-70B-Instruct-32k-v0.1.Q4_K_M.gguf	Q4_K_M	39.6GB
Llama-3-70B-Instruct-32k-v0.1.Q4_1.gguf	Q4_1	41.27GB
Llama-3-70B-Instruct-32k-v0.1.Q5_0.gguf	Q5_0	45.32GB
Llama-3-70B-Instruct-32k-v0.1.Q5_K_S.gguf	Q5_K_S	45.32GB
Llama-3-70B-Instruct-32k-v0.1.Q5_K.gguf	Q5_K	46.52GB
Llama-3-70B-Instruct-32k-v0.1.Q5_K_M.gguf	Q5_K_M	46.52GB
Llama-3-70B-Instruct-32k-v0.1.Q5_1.gguf	Q5_1	49.36GB
Llama-3-70B-Instruct-32k-v0.1.Q6_K.gguf	Q6_K	53.91GB
Llama-3-70B-Instruct-32k-v0.1.Q8_0.gguf	Q8_0	69.83GB

Original model description:

base_model: meta-llama/Meta-Llama-3-70B-Instruct library_name: transformers tags:

facebook
meta
pytorch
llama
llama-3 language:
en pipeline_tag: text-generation license: other license_name: llama3 license_link: LICENSE inference: false model_creator: MaziyarPanahi model_name: Llama-3-8B-Instruct-32k-v0.1 quantized_by: MaziyarPanahi

Llama-3 DPO Logo

Llama-3-70B-Instruct-32k-v0.1

This is an experiment by setting rope_theta to 8m.

Quantized models

You can find all GGUF quantized models here: MaziyarPanahi/Llama-3-70B-Instruct-32k-v0.1-GGUF