Hugging Face's logo

neuralmagic
/
DeepSeek-R1-Distill-Qwen-14B-quantized.w4a16

Text Generation
Transformers
Safetensors
qwen2
deepseek
int4
vllm
llmcompressor
conversational
text-generation-inference
Inference Endpoints
compressed-tensors
Model card Files Community
nm-research commited on
Commit
c8e7601
·
verified ·
1 Parent(s): a5976e7

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. config.json +1 -1
  2. model-00001-of-00002.safetensors +1 -1
  3. model-00002-of-00002.safetensors +1 -1
config.json CHANGED
@@ -48,7 +48,7 @@
48
  "quantization_status": "compressed",
49
  "sparsity_config": {
50
  "format": "dense",
51
- "global_sparsity": 0.15071896708076415,
52
  "ignore": [
53
  "model.layers.0.self_attn.q_proj",
54
  "model.layers.0.self_attn.k_proj",
 
48
  "quantization_status": "compressed",
49
  "sparsity_config": {
50
  "format": "dense",
51
+ "global_sparsity": 0.15074144834327785,
52
  "ignore": [
53
  "model.layers.0.self_attn.q_proj",
54
  "model.layers.0.self_attn.k_proj",
model-00001-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:83262ed41c0f4271b4f457e4b4bdf68b5ff06ef3a53395a5254166d1811e7060
3
  size 4996734832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d2f409586cbbd8bb4bfc6a2966a9e61adf11fe3d6b02a0e6ada164de83c6d51f
3
  size 4996734832
model-00002-of-00002.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7f3ef5695134ae526aa28779eaecbcd04e4f3e92951fa701b6d22b6110569dfa
3
  size 4931832296
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:de7efeeef830452ea570d5447561e4ddef49c095200e7bebd5b67437912a1dce
3
  size 4931832296