Hugging Face's logo

AngelSlim
/
Deepseek_r1_distill_qwen-32b_fp8_static

Safetensors
qwen2
compressed-tensors
Model card Files
xet
Community
woodchen7 commited on
Commit
2f64894
·
verified ·
1 Parent(s): 3398502

Upload config.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. config.json +56 -33
config.json CHANGED
@@ -1,35 +1,58 @@
1
  {
2
- "architectures": [
3
- "Qwen2ForCausalLM"
4
- ],
5
- "attention_dropout": 0.0,
6
- "bos_token_id": 151643,
7
- "eos_token_id": 151643,
8
- "hidden_act": "silu",
9
- "hidden_size": 5120,
10
- "initializer_range": 0.02,
11
- "intermediate_size": 27648,
12
- "max_position_embeddings": 131072,
13
- "max_window_layers": 64,
14
- "model_type": "qwen2",
15
- "num_attention_heads": 40,
16
- "num_hidden_layers": 64,
17
- "num_key_value_heads": 8,
18
- "quantization_config": {
19
- "activation_scheme": "static",
20
- "ignored_layers": [
21
- "lm_head"
22
  ],
23
- "quant_method": "fp8"
24
- },
25
- "rms_norm_eps": 1e-05,
26
- "rope_scaling": null,
27
- "rope_theta": 1000000.0,
28
- "sliding_window": 131072,
29
- "tie_word_embeddings": false,
30
- "torch_dtype": "bfloat16",
31
- "transformers_version": "4.51.3",
32
- "use_cache": false,
33
- "use_sliding_window": false,
34
- "vocab_size": 152064
35
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
  {
2
+ "architectures": [
3
+ "Qwen2ForCausalLM"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4
  ],
5
+ "attention_dropout": 0.0,
6
+ "bos_token_id": 151643,
7
+ "eos_token_id": 151643,
8
+ "hidden_act": "silu",
9
+ "hidden_size": 5120,
10
+ "initializer_range": 0.02,
11
+ "intermediate_size": 27648,
12
+ "max_position_embeddings": 131072,
13
+ "max_window_layers": 64,
14
+ "model_type": "qwen2",
15
+ "num_attention_heads": 40,
16
+ "num_hidden_layers": 64,
17
+ "num_key_value_heads": 8,
18
+ "quantization_config": {
19
+ "config_groups": {
20
+ "group_0": {
21
+ "input_activations": {
22
+ "dynamic": false,
23
+ "num_bits": 8,
24
+ "strategy": "tensor",
25
+ "type": "float"
26
+ },
27
+ "output_activations": null,
28
+ "targets": [
29
+ "Linear"
30
+ ],
31
+ "weights": {
32
+ "dynamic": false,
33
+ "num_bits": 8,
34
+ "strategy": "tensor",
35
+ "type": "float"
36
+ }
37
+ }
38
+ },
39
+ "format": "naive-quantized",
40
+ "kv_cache_scheme": null,
41
+ "quant_method": "compressed-tensors",
42
+ "quantization_status": "compressed",
43
+ "ignored_layers": [
44
+ "lm_head",
45
+ "model.embed_tokens"
46
+ ]
47
+ },
48
+ "rms_norm_eps": 1e-05,
49
+ "rope_scaling": null,
50
+ "rope_theta": 1000000.0,
51
+ "sliding_window": 131072,
52
+ "tie_word_embeddings": false,
53
+ "torch_dtype": "bfloat16",
54
+ "transformers_version": "4.51.3",
55
+ "use_cache": false,
56
+ "use_sliding_window": false,
57
+ "vocab_size": 152064
58
+ }