Zihao-Li_-_mala-500-10b-v2-merged-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
Zihao-Li_-_mala-500-10b-v2-merged-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

mala-500-10b-v2-merged - GGUF

Model creator: https://huggingface.co/Zihao-Li/
Original model: https://huggingface.co/Zihao-Li/mala-500-10b-v2-merged/

Name	Quant method	Size
mala-500-10b-v2-merged.Q2_K.gguf	Q2_K	3.36GB
mala-500-10b-v2-merged.IQ3_XS.gguf	IQ3_XS	3.7GB
mala-500-10b-v2-merged.IQ3_S.gguf	IQ3_S	3.84GB
mala-500-10b-v2-merged.Q3_K_S.gguf	Q3_K_S	3.84GB
mala-500-10b-v2-merged.IQ3_M.gguf	IQ3_M	3.99GB
mala-500-10b-v2-merged.Q3_K.gguf	Q3_K	4.16GB
mala-500-10b-v2-merged.Q3_K_M.gguf	Q3_K_M	4.16GB
mala-500-10b-v2-merged.Q3_K_L.gguf	Q3_K_L	4.44GB
mala-500-10b-v2-merged.IQ4_XS.gguf	IQ4_XS	4.58GB
mala-500-10b-v2-merged.Q4_0.gguf	Q4_0	4.77GB
mala-500-10b-v2-merged.IQ4_NL.gguf	IQ4_NL	4.79GB
mala-500-10b-v2-merged.Q4_K_S.gguf	Q4_K_S	4.8GB
mala-500-10b-v2-merged.Q4_K.gguf	Q4_K	5.01GB
mala-500-10b-v2-merged.Q4_K_M.gguf	Q4_K_M	5.01GB
mala-500-10b-v2-merged.Q4_1.gguf	Q4_1	5.21GB
mala-500-10b-v2-merged.Q5_0.gguf	Q5_0	5.65GB
mala-500-10b-v2-merged.Q5_K_S.gguf	Q5_K_S	5.65GB
mala-500-10b-v2-merged.Q5_K.gguf	Q5_K	5.77GB
mala-500-10b-v2-merged.Q5_K_M.gguf	Q5_K_M	5.77GB
mala-500-10b-v2-merged.Q5_1.gguf	Q5_1	6.09GB
mala-500-10b-v2-merged.Q6_K.gguf	Q6_K	6.58GB
mala-500-10b-v2-merged.Q8_0.gguf	Q8_0	8.52GB

Original model description:

license: llama2 datasets:

cis-lmu/Glot500 language:
multilingual base_model: meta-llama/Llama-2-7b-hf pipeline_tag: text-generation

The model is the LoRA adaptation merged vision of MaLA-LM/mala-500-10b-v2.