Hugging Face's logo

cgus
/
Galactic-Qwen-14B-Exp2-exl2

Text Generation
English
exllamav2
qwen2
text-generation-inference
math
qwen
14b
code
conversational
Eval Results
4-bit precision
exl2
Model card Files Community
cgus commited on
Commit
168c07e
·
verified ·
1 Parent(s): fad0279

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. output-00001-of-00002.safetensors +2 -2
  3. output-00002-of-00002.safetensors +2 -2
config.json CHANGED
@@ -27,7 +27,7 @@
27
  "quantization_config": {
28
  "quant_method": "exl2",
29
  "version": "0.2.8",
30
- "bits": 4.0,
31
  "head_bits": 6,
32
  "calibration": {
33
  "rows": 115,
 
27
  "quantization_config": {
28
  "quant_method": "exl2",
29
  "version": "0.2.8",
30
+ "bits": 4.5,
31
  "head_bits": 6,
32
  "calibration": {
33
  "rows": 115,
output-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19896a701b775c66d186e8fe3611889db0c9d6ff9f04890df333d5c022fb9ab9
3
- size 8163329908
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c8e2892f412fb2f0654d9ac98c135e2fec012735bc730694bc4590731cfc79
3
+ size 8545818984
output-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:e9ebafa21570661271a17f6f43d246533eac1ecf5d3c4226c85b02d782ef1072
3
- size 611573856
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0a7c58c60d642ffd9ca88683f2031d22c9b1f8468e9e42bb3e208f96b8da42c
3
+ size 1054838590