Hugging Face's logo

neuralmagic
/
DeepSeek-R1-Distill-Qwen-32B-FP8-dynamic

Text Generation
Transformers
Safetensors
qwen2
deepseek
fp8
vllm
conversational
text-generation-inference
compressed-tensors
Model card Files Community
nm-research commited on
Commit
140b8be
·
verified ·
1 Parent(s): 4b6f87b

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +5 -5
  2. model-00001-of-00007.safetensors +3 -0
  3. model-00002-of-00007.safetensors +3 -0
  4. model-00003-of-00007.safetensors +3 -0
  5. model-00004-of-00007.safetensors +3 -0
  6. model-00005-of-00007.safetensors +3 -0
  7. model-00006-of-00007.safetensors +3 -0
  8. model-00007-of-00007.safetensors +3 -0
  9. model.safetensors.index.json +0 -0
config.json CHANGED
@@ -1,5 +1,5 @@
1
  {
2
- "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-14B",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
@@ -9,12 +9,12 @@
9
  "hidden_act": "silu",
10
  "hidden_size": 5120,
11
  "initializer_range": 0.02,
12
- "intermediate_size": 13824,
13
  "max_position_embeddings": 131072,
14
- "max_window_layers": 48,
15
  "model_type": "qwen2",
16
  "num_attention_heads": 40,
17
- "num_hidden_layers": 48,
18
  "num_key_value_heads": 8,
19
  "quantization_config": {
20
  "config_groups": {
@@ -50,7 +50,7 @@
50
  }
51
  },
52
  "format": "float-quantized",
53
- "global_compression_ratio": 1.531585969025769,
54
  "ignore": [
55
  "lm_head"
56
  ],
 
1
  {
2
+ "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Qwen-32B",
3
  "architectures": [
4
  "Qwen2ForCausalLM"
5
  ],
 
9
  "hidden_act": "silu",
10
  "hidden_size": 5120,
11
  "initializer_range": 0.02,
12
+ "intermediate_size": 27648,
13
  "max_position_embeddings": 131072,
14
+ "max_window_layers": 64,
15
  "model_type": "qwen2",
16
  "num_attention_heads": 40,
17
+ "num_hidden_layers": 64,
18
  "num_key_value_heads": 8,
19
  "quantization_config": {
20
  "config_groups": {
 
50
  }
51
  },
52
  "format": "float-quantized",
53
+ "global_compression_ratio": 1.533275278369312,
54
  "ignore": [
55
  "lm_head"
56
  ],
model-00001-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd8ff997ac8f8599761f6297e9f172a292805788909b8dcc6cc376f8cfc33b4c
3
+ size 4997762744
model-00002-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6ac42fc7f546f2d45c983dffc5a34d542a6be7ee7673b54bfdd4c12202402c6
3
+ size 4914421680
model-00003-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:294b3d86ffc0fe422297c770beeb7669aeb74d7050b70d1d3d71929fe38179a2
3
+ size 4877702248
model-00004-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:408d2458e103566b1c848c3226505db8acffb5096e2435c65ff8dc95f5aef6a2
3
+ size 4877702248
model-00005-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c8fe5fc6dd376bc078bba9d190fdf31f53a920e58e0b93accba9acbffb7ec75
3
+ size 4877702248
model-00006-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cfe313a001266604ca15c4782c30c71f82e3312dae1034bcec7cc4623d9ef2ab
3
+ size 4877702248
model-00007-of-00007.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8e4bef730ddab35c068267cf78fd7f385bbe480528d2d485e87a9efba7a4e92a
3
+ size 4908583200
model.safetensors.index.json CHANGED
The diff for this file is too large to render. See raw diff