digo-prayudha_-_unsloth-komodo-7B-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
digo-prayudha_-_unsloth-komodo-7B-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

unsloth-komodo-7B - GGUF

Model creator: https://huggingface.co/digo-prayudha/
Original model: https://huggingface.co/digo-prayudha/unsloth-komodo-7B/

Name	Quant method	Size
unsloth-komodo-7B.Q2_K.gguf	Q2_K	2.37GB
unsloth-komodo-7B.IQ3_XS.gguf	IQ3_XS	2.62GB
unsloth-komodo-7B.IQ3_S.gguf	IQ3_S	2.76GB
unsloth-komodo-7B.Q3_K_S.gguf	Q3_K_S	2.76GB
unsloth-komodo-7B.IQ3_M.gguf	IQ3_M	2.92GB
unsloth-komodo-7B.Q3_K.gguf	Q3_K	3.09GB
unsloth-komodo-7B.Q3_K_M.gguf	Q3_K_M	3.09GB
unsloth-komodo-7B.Q3_K_L.gguf	Q3_K_L	3.36GB
unsloth-komodo-7B.IQ4_XS.gguf	IQ4_XS	3.41GB
unsloth-komodo-7B.Q4_0.gguf	Q4_0	3.58GB
unsloth-komodo-7B.IQ4_NL.gguf	IQ4_NL	3.6GB
unsloth-komodo-7B.Q4_K_S.gguf	Q4_K_S	3.61GB
unsloth-komodo-7B.Q4_K.gguf	Q4_K	3.82GB
unsloth-komodo-7B.Q4_K_M.gguf	Q4_K_M	3.82GB
unsloth-komodo-7B.Q4_1.gguf	Q4_1	3.96GB
unsloth-komodo-7B.Q5_0.gguf	Q5_0	4.35GB
unsloth-komodo-7B.Q5_K_S.gguf	Q5_K_S	4.35GB
unsloth-komodo-7B.Q5_K.gguf	Q5_K	4.47GB
unsloth-komodo-7B.Q5_K_M.gguf	Q5_K_M	4.47GB
unsloth-komodo-7B.Q5_1.gguf	Q5_1	4.73GB
unsloth-komodo-7B.Q6_K.gguf	Q6_K	5.17GB
unsloth-komodo-7B.Q8_0.gguf	Q8_0	6.69GB

Original model description:

language:

en license: apache-2.0 tags:
text-generation-inference
transformers
unsloth
llama
trl
sft base_model: Yellow-AI-NLP/komodo-7b-base

Uploaded model

Developed by: digo-prayudha
License: apache-2.0
Finetuned from model : Yellow-AI-NLP/komodo-7b-base

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