Hugging Face's logo

nm-testing
/
TinyLlama-1.1B-Chat-v1.0-W8A8_tensor_weight_static_per_tensor_act-e2e

Safetensors
llama
8-bit precision
compressed-tensors
Model card Files
xet
Community
nm-autobot commited on
Commit
2fa8fda
·
verified ·
1 Parent(s): 1a9651a

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +2 -1
  2. model.safetensors +1 -1
  3. recipe.yaml +1 -0
config.json CHANGED
@@ -21,6 +21,7 @@
21
  "quantization_config": {
22
  "config_groups": {
23
  "group_0": {
 
24
  "input_activations": {
25
  "actorder": null,
26
  "block_structure": null,
@@ -61,7 +62,7 @@
61
  "quantization_status": "compressed",
62
  "sparsity_config": {},
63
  "transform_config": {},
64
- "version": "0.10.3.a20250812"
65
  },
66
  "rms_norm_eps": 1e-05,
67
  "rope_scaling": null,
 
21
  "quantization_config": {
22
  "config_groups": {
23
  "group_0": {
24
+ "format": "int-quantized",
25
  "input_activations": {
26
  "actorder": null,
27
  "block_structure": null,
 
62
  "quantization_status": "compressed",
63
  "sparsity_config": {},
64
  "transform_config": {},
65
+ "version": "0.10.3.a20250815"
66
  },
67
  "rms_norm_eps": 1e-05,
68
  "rope_scaling": null,
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f40538be619454c2d887be5f2447e445e79c8b93291fb2e6a2ffb09bd1f4db86
3
  size 1231270112
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:83e2783c4828fbd132d1da1ec583cf0e080964be2c7c7dd0d77ee0caab23c0d9
3
  size 1231270112
recipe.yaml CHANGED
@@ -37,5 +37,6 @@ quant_stage:
37
  observer: minmax
38
  observer_kwargs: {}
39
  output_activations: null
 
40
  targets: [Linear]
41
  ignore: [lm_head]
 
37
  observer: minmax
38
  observer_kwargs: {}
39
  output_activations: null
40
+ format: null
41
  targets: [Linear]
42
  ignore: [lm_head]