sanchit-gandhi_-_distil-mistral-1.5B-v0.1-gguf – AI Model by RichardErkhov | AlphaNeural AI

You can deploy this model and start earning money today!

RichardErkhov/
sanchit-gandhi_-_distil-mistral-1.5B-v0.1-gguf

like

0

endpoints_compatible

Views

No views yet

Quantization made by Richard Erkhov.

Request more models

distil-mistral-1.5B-v0.1 - GGUF

Model creator: https://huggingface.co/sanchit-gandhi/
Original model: https://huggingface.co/sanchit-gandhi/distil-mistral-1.5B-v0.1/

Name	Quant method	Size
distil-mistral-1.5B-v0.1.Q2_K.gguf	Q2_K	0.59GB
distil-mistral-1.5B-v0.1.Q3_K_S.gguf	Q3_K_S	0.68GB
distil-mistral-1.5B-v0.1.Q3_K.gguf	Q3_K	0.74GB
distil-mistral-1.5B-v0.1.Q3_K_M.gguf	Q3_K_M	0.74GB
distil-mistral-1.5B-v0.1.Q3_K_L.gguf	Q3_K_L	0.79GB
distil-mistral-1.5B-v0.1.IQ4_XS.gguf	IQ4_XS	0.82GB
distil-mistral-1.5B-v0.1.Q4_0.gguf	Q4_0	0.86GB
distil-mistral-1.5B-v0.1.IQ4_NL.gguf	IQ4_NL	0.86GB
distil-mistral-1.5B-v0.1.Q4_K_S.gguf	Q4_K_S	0.86GB
distil-mistral-1.5B-v0.1.Q4_K.gguf	Q4_K	0.89GB
distil-mistral-1.5B-v0.1.Q4_K_M.gguf	Q4_K_M	0.89GB
distil-mistral-1.5B-v0.1.Q4_1.gguf	Q4_1	0.94GB
distil-mistral-1.5B-v0.1.Q5_0.gguf	Q5_0	1.02GB
distil-mistral-1.5B-v0.1.Q5_K_S.gguf	Q5_K_S	1.02GB
distil-mistral-1.5B-v0.1.Q5_K.gguf	Q5_K	1.04GB
distil-mistral-1.5B-v0.1.Q5_K_M.gguf	Q5_K_M	1.04GB
distil-mistral-1.5B-v0.1.Q5_1.gguf	Q5_1	1.11GB
distil-mistral-1.5B-v0.1.Q6_K.gguf	Q6_K	1.2GB
distil-mistral-1.5B-v0.1.Q8_0.gguf	Q8_0	1.56GB

Original model description:

datasets:

HuggingFaceTB/cosmopedia library_name: transformers

To reproduce this run:

accelerate launch --multi_gpu --mixed_precision=fp16 --num_processes=8 run_distillation.py config_mistral.yaml