Hugging Face's logo

s0wa48
/
sn97-commit-mantis7

Safetensors
qwen3_5_text
Model card Files
xet
 Community
s0wa48 commited on
Commit
7b95292
·
verified ·
1 Parent(s): 9f03d2b

tied_continue (sparse128 3e-7 3ep from tied_baseline): kl=0.083 vs king 0.291 = -71.5% on block 8024298, full n=300

Browse files
Files changed (2) hide show
  1. config.json +76 -85
  2. model.safetensors +2 -2
config.json CHANGED
@@ -1,92 +1,83 @@
1
  {
2
  "architectures": [
3
- "Qwen3_5ForConditionalGeneration"
4
  ],
5
- "model_type": "qwen3_5",
6
- "text_config": {
7
- "attention_bias": false,
8
- "attention_dropout": 0.0,
9
- "attn_output_gate": true,
10
- "bos_token_id": null,
11
- "dtype": "bfloat16",
12
- "eos_token_id": 248044,
13
- "full_attention_interval": 4,
14
- "head_dim": 256,
15
- "hidden_act": "silu",
16
- "hidden_size": 2560,
17
- "initializer_range": 0.02,
18
- "intermediate_size": 9216,
19
- "layer_types": [
20
- "linear_attention",
21
- "linear_attention",
22
- "linear_attention",
23
- "full_attention",
24
- "linear_attention",
25
- "linear_attention",
26
- "linear_attention",
27
- "full_attention",
28
- "linear_attention",
29
- "linear_attention",
30
- "linear_attention",
31
- "full_attention",
32
- "linear_attention",
33
- "linear_attention",
34
- "linear_attention",
35
- "full_attention",
36
- "linear_attention",
37
- "linear_attention",
38
- "linear_attention",
39
- "full_attention",
40
- "linear_attention",
41
- "linear_attention",
42
- "linear_attention",
43
- "full_attention",
44
- "linear_attention",
45
- "linear_attention",
46
- "linear_attention",
47
- "full_attention",
48
- "linear_attention",
49
- "linear_attention",
50
- "linear_attention",
51
- "full_attention"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
52
  ],
53
- "linear_conv_kernel_dim": 4,
54
- "linear_key_head_dim": 128,
55
- "linear_num_key_heads": 16,
56
- "linear_num_value_heads": 32,
57
- "linear_value_head_dim": 128,
58
- "mamba_ssm_dtype": "float32",
59
- "max_position_embeddings": 262144,
60
- "mlp_only_layers": [],
61
- "mtp_num_hidden_layers": 1,
62
- "mtp_use_dedicated_embeddings": false,
63
- "num_attention_heads": 16,
64
- "num_hidden_layers": 32,
65
- "num_key_value_heads": 4,
66
- "pad_token_id": null,
67
  "partial_rotary_factor": 0.25,
68
- "rms_norm_eps": 1e-06,
69
- "rope_parameters": {
70
- "mrope_interleaved": true,
71
- "mrope_section": [
72
- 11,
73
- 11,
74
- 10
75
- ],
76
- "partial_rotary_factor": 0.25,
77
- "rope_theta": 10000000,
78
- "rope_type": "default"
79
- },
80
- "use_cache": true,
81
- "vocab_size": 248320,
82
- "architectures": [
83
- "Qwen3_5ForCausalLM"
84
- ],
85
- "model_type": "qwen3_5_text",
86
- "tie_word_embeddings": true,
87
- "transformers_version": "5.5.0.dev0"
88
  },
89
  "tie_word_embeddings": true,
90
- "torch_dtype": "bfloat16",
91
- "transformers_version": "5.5.0.dev0"
92
- }
 
 
1
  {
2
  "architectures": [
3
+ "Qwen3_5ForCausalLM"
4
  ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attn_output_gate": true,
8
+ "bos_token_id": null,
9
+ "dtype": "bfloat16",
10
+ "eos_token_id": 248044,
11
+ "full_attention_interval": 4,
12
+ "head_dim": 256,
13
+ "hidden_act": "silu",
14
+ "hidden_size": 2560,
15
+ "initializer_range": 0.02,
16
+ "intermediate_size": 9216,
17
+ "layer_types": [
18
+ "linear_attention",
19
+ "linear_attention",
20
+ "linear_attention",
21
+ "full_attention",
22
+ "linear_attention",
23
+ "linear_attention",
24
+ "linear_attention",
25
+ "full_attention",
26
+ "linear_attention",
27
+ "linear_attention",
28
+ "linear_attention",
29
+ "full_attention",
30
+ "linear_attention",
31
+ "linear_attention",
32
+ "linear_attention",
33
+ "full_attention",
34
+ "linear_attention",
35
+ "linear_attention",
36
+ "linear_attention",
37
+ "full_attention",
38
+ "linear_attention",
39
+ "linear_attention",
40
+ "linear_attention",
41
+ "full_attention",
42
+ "linear_attention",
43
+ "linear_attention",
44
+ "linear_attention",
45
+ "full_attention",
46
+ "linear_attention",
47
+ "linear_attention",
48
+ "linear_attention",
49
+ "full_attention"
50
+ ],
51
+ "linear_conv_kernel_dim": 4,
52
+ "linear_key_head_dim": 128,
53
+ "linear_num_key_heads": 16,
54
+ "linear_num_value_heads": 32,
55
+ "linear_value_head_dim": 128,
56
+ "mamba_ssm_dtype": "float32",
57
+ "max_position_embeddings": 262144,
58
+ "mlp_only_layers": [],
59
+ "model_type": "qwen3_5_text",
60
+ "mtp_num_hidden_layers": 1,
61
+ "mtp_use_dedicated_embeddings": false,
62
+ "num_attention_heads": 16,
63
+ "num_hidden_layers": 32,
64
+ "num_key_value_heads": 4,
65
+ "pad_token_id": null,
66
+ "partial_rotary_factor": 0.25,
67
+ "rms_norm_eps": 1e-06,
68
+ "rope_parameters": {
69
+ "mrope_interleaved": true,
70
+ "mrope_section": [
71
+ 11,
72
+ 11,
73
+ 10
74
  ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
75
  "partial_rotary_factor": 0.25,
76
+ "rope_theta": 10000000,
77
+ "rope_type": "default"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
78
  },
79
  "tie_word_embeddings": true,
80
+ "transformers_version": "5.5.0.dev0",
81
+ "use_cache": true,
82
+ "vocab_size": 248320
83
+ }
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:06db9453159a12e51bdd8f90aeb1c989f2c9d39440622ded593450af5e234d40
3
- size 8411558368
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe9531d62901732af21fc374d909f3c06d8299e7db1055b2de5f29e5c67b3085
3
+ size 8411558400