liminerity_-_llama3-3b-1.58bit-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
liminerity_-_llama3-3b-1.58bit-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

llama3-3b-1.58bit - GGUF

Model creator: https://huggingface.co/liminerity/
Original model: https://huggingface.co/liminerity/llama3-3b-1.58bit/

Name	Quant method	Size
llama3-3b-1.58bit.Q2_K.gguf	Q2_K	1.43GB
llama3-3b-1.58bit.Q3_K_S.gguf	Q3_K_S	1.66GB
llama3-3b-1.58bit.Q3_K.gguf	Q3_K	1.81GB
llama3-3b-1.58bit.Q3_K_M.gguf	Q3_K_M	1.81GB
llama3-3b-1.58bit.Q3_K_L.gguf	Q3_K_L	1.95GB
llama3-3b-1.58bit.IQ4_XS.gguf	IQ4_XS	2.02GB
llama3-3b-1.58bit.Q4_0.gguf	Q4_0	2.1GB
llama3-3b-1.58bit.IQ4_NL.gguf	IQ4_NL	2.12GB
llama3-3b-1.58bit.Q4_K_S.gguf	Q4_K_S	2.12GB
llama3-3b-1.58bit.Q4_K.gguf	Q4_K	2.23GB
llama3-3b-1.58bit.Q4_K_M.gguf	Q4_K_M	2.23GB
llama3-3b-1.58bit.Q4_1.gguf	Q4_1	2.31GB
llama3-3b-1.58bit.Q5_0.gguf	Q5_0	2.53GB
llama3-3b-1.58bit.Q5_K_S.gguf	Q5_K_S	2.53GB
llama3-3b-1.58bit.Q5_K.gguf	Q5_K	2.59GB
llama3-3b-1.58bit.Q5_K_M.gguf	Q5_K_M	2.59GB
llama3-3b-1.58bit.Q5_1.gguf	Q5_1	2.74GB
llama3-3b-1.58bit.Q6_K.gguf	Q6_K	2.97GB
llama3-3b-1.58bit.Q8_0.gguf	Q8_0	3.85GB

Original model description:

language:

en license: apache-2.0 tags:
text-generation-inference
transformers
unsloth
llama
trl base_model: liminerity/llama3-1bit2

NOT GOOD BUT... I finally converted llama 3 to bitnet

Uploaded model

Developed by: liminerity
License: apache-2.0
Finetuned from model : liminerity/llama3-1bit2

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.