Hugging Face's logo

nm-testing
/
TinyLlama-1.1B-Chat-v1.0-W4A16_2of4_channel-e2e

Text Generation
Transformers
Safetensors
llama
conversational
text-generation-inference
Inference Endpoints
compressed-tensors
Model card Files Community
nm-autobot commited on
Commit
ad658e5
·
verified ·
1 Parent(s): 5952666

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 +2 -1
config.json CHANGED
@@ -51,7 +51,7 @@
51
  "quantization_status": "compressed",
52
  "sparsity_config": {
53
  "format": "dense",
54
- "global_sparsity": 0.45357729044945944,
55
  "ignore": [
56
  "lm_head"
57
  ],
 
51
  "quantization_status": "compressed",
52
  "sparsity_config": {
53
  "format": "dense",
54
+ "global_sparsity": 0.45357314542111843,
55
  "ignore": [
56
  "lm_head"
57
  ],
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:40b19c4c15e2e741f486e37e62580e04de10a03a7bf13c55661461ca99f4d31f
3
  size 626506392
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cf5127ce6ddab4186b303b90b89201d53ccce52a214ba34ae704a72509dbe6a3
3
  size 626506392
recipe.yaml CHANGED
@@ -1,7 +1,8 @@
1
  sparsity_stage:
2
  sparsity_modifiers:
3
  SparseGPTModifier: {sparsity: 0.5, mask_structure: '2:4', sequential_update: false}
4
- run_type: &id001 !!python/object/apply:llmcompressor.recipe.stage.StageRunType [oneshot]
 
5
  quantization_stage:
6
  quantization_modifiers:
7
  GPTQModifier:
 
1
  sparsity_stage:
2
  sparsity_modifiers:
3
  SparseGPTModifier: {sparsity: 0.5, mask_structure: '2:4', sequential_update: false}
4
+ run_type: &id001 !!python/object/apply:builtins.getattr [!!python/name:llmcompressor.recipe.stage.StageRunType '',
5
+ ONESHOT]
6
  quantization_stage:
7
  quantization_modifiers:
8
  GPTQModifier: