Hugging Face's logo

nm-testing
/
TinyLlama-1.1B-Chat-v1.0-W4A16-e2e

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
compressed-tensors
Model card Files Community
nm-autobot commited on
Commit
e4f30d7
•
1 Parent(s): 77c2f44

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. model.safetensors +1 -1
  3. recipe.yaml +1 -1
config.json CHANGED
@@ -51,7 +51,7 @@
51
  "quantization_status": "compressed",
52
  "sparsity_config": {
53
  "format": "dense",
54
- "global_sparsity": 0.14375328644374685,
55
  "ignore": [],
56
  "registry_requires_subclass": false,
57
  "sparsity_structure": "unstructured",
 
51
  "quantization_status": "compressed",
52
  "sparsity_config": {
53
  "format": "dense",
54
+ "global_sparsity": 0.14329888201729718,
55
  "ignore": [],
56
  "registry_requires_subclass": false,
57
  "sparsity_structure": "unstructured",
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:892873b79abcf66508b526a74179177e303de9b4b1464a6177096348faa7fd76
3
  size 761968800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f3c99c37708043eee70aa1961dcda6621a800fe68feaa47f280f1083e5b2a53f
3
  size 761968800
recipe.yaml CHANGED
@@ -1,6 +1,6 @@
1
  DEFAULT_stage:
2
  DEFAULT_modifiers:
3
  GPTQModifier:
 
4
  targets: Linear
5
  ignore: [lm_head]
6
- scheme: W4A16
 
1
  DEFAULT_stage:
2
  DEFAULT_modifiers:
3
  GPTQModifier:
4
+ scheme: W4A16
5
  targets: Linear
6
  ignore: [lm_head]