Modelpublic

RichardErkhov/shawon-majid_-_float16-gguf

sourceHugging Faceupdated 1y agoView on Hugging Face

0likes309downloads

Model Card

Quantization made by Richard Erkhov.

Request more models

float16 - GGUF

—Model creator: https://huggingface.co/shawon-majid/
—Original model: https://huggingface.co/shawon-majid/float16/

Name	Quant method	Size
float16.Q2_K.gguf	Q2_K	2.96GB
float16.IQ3_XS.gguf	IQ3_XS	3.28GB
float16.IQ3_S.gguf	IQ3_S	3.43GB
float16.Q3_K_S.gguf	Q3KS	3.41GB
float16.IQ3_M.gguf	IQ3_M	3.52GB
float16.Q3_K.gguf	Q3_K	3.74GB
float16.Q3_K_M.gguf	Q3KM	3.74GB
float16.Q3_K_L.gguf	Q3KL	4.03GB
float16.IQ4_XS.gguf	IQ4_XS	4.18GB
float16.Q4_0.gguf	Q4_0	4.34GB
float16.IQ4_NL.gguf	IQ4_NL	4.38GB
float16.Q4_K_S.gguf	Q4KS	4.37GB
float16.Q4_K.gguf	Q4_K	4.58GB
float16.Q4_K_M.gguf	Q4KM	4.58GB
float16.Q4_1.gguf	Q4_1	4.78GB
float16.Q5_0.gguf	Q5_0	5.21GB
float16.Q5_K_S.gguf	Q5KS	5.21GB
float16.Q5_K.gguf	Q5_K	5.34GB
float16.Q5_K_M.gguf	Q5KM	5.34GB
float16.Q5_1.gguf	Q5_1	5.65GB
float16.Q6_K.gguf	Q6_K	6.14GB
float16.Q8_0.gguf	Q8_0	7.95GB

Original model description: --- base_model: unsloth/meta-llama-3.1-8b-bnb-4bit language:

—en license: apache-2.0 tags:
—text-generation-inference
—transformers
—unsloth
—llama
—trl
—sft ---

Uploaded model

—Developed by: shawon-majid
—License: apache-2.0
—Finetuned from model : unsloth/meta-llama-3.1-8b-bnb-4bit

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

<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>