gstaff
/

Mistral-7B-Instruct-v0.1-AWQ

Model card Files Files and versions

Mistral-7B-Instruct-v0.1-AWQ

14.7 GB

1 contributor

History: 2 commits

gstaff's picture

Upload pre-quantized weight files.

4128c4a verified over 1 year ago

mistral7b_hf_tokenizer
Upload pre-quantized weight files. over 1 year ago
mistral_kv_int8_scales
Upload pre-quantized weight files. over 1 year ago
.gitattributes

1.52 kB

initial commit over 1 year ago
mistral_tp1.json

94.9 kB

Upload pre-quantized weight files. over 1 year ago
mistral_tp1_rank0.npz
Pickle imports
- No problematic imports detected
What is a pickle import?
14.7 GB
xet

Upload pre-quantized weight files. over 1 year ago