Hugging Face's logo

devpramod-intel
/
Qwen3-8B-quantized.w8a8

Safetensors
qwen3
8-bit precision
compressed-tensors
Model card Files
xet
 Community
devpramod-intel commited on
Commit
83ccb7f
·
verified ·
1 Parent(s): 7fb0270

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. model-00001-of-00002.safetensors +1 -1
  2. model-00002-of-00002.safetensors +1 -1
  3. recipe.yaml +1 -1
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b798394b701a70faa10a83f551a09e68d893b109e396469e080c0e53239f105e
3
  size 4954286136
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:709c366460d60d093aaecb1206372a717d35617414ee26ad3f75a8e5b49f5f21
3
  size 4954286136
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d7fdf6b57259fd68a4372f9b5fb6a5c5cd7db5ef5adaf85ef0a290cbb9afe3e
3
  size 4484294568
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e542dcc29858ac4198ec42c85c3d855b3c1ef3b025ae7a81a90d6a291353fb4
3
  size 4484294568
recipe.yaml CHANGED
@@ -17,5 +17,5 @@ default_stage:
17
  bypass_divisibility_checks: false
18
  block_size: 64
19
  dampening_frac: 0.05
20
- actorder: weight
21
  offload_hessians: false
 
17
  bypass_divisibility_checks: false
18
  block_size: 64
19
  dampening_frac: 0.05
20
+ actorder: static
21
  offload_hessians: false