Hugging Face's logo

sahilchachra
/
Qwythos-9B-Claude-Mythos-5-1M-mxfp8-mlx

MLX
Safetensors
qwen3_5
quantized
apple-silicon
8-bit precision
Model card Files
xet
 Community
1
sahilchachra commited on
Commit
d09ab66
·
verified ·
1 Parent(s): b5272ab

Re-tag as text-only causal LM (config.json)

Browse files
Files changed (1) hide show
  1. config.json +99 -103
config.json CHANGED
@@ -1,109 +1,105 @@
1
  {
2
- "architectures": [
3
- "Qwen3_5ForConditionalGeneration"
4
- ],
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
5
  "dtype": "bfloat16",
6
- "eos_token_id": [
7
- 248046,
8
- 248044
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
9
  ],
10
- "image_token_id": 248056,
11
- "model_type": "qwen3_5",
12
- "pad_token_id": 248044,
13
- "quantization": {
14
- "group_size": 32,
15
- "bits": 8,
16
- "mode": "mxfp8"
17
- },
18
- "quantization_config": {
19
- "group_size": 32,
20
- "bits": 8,
21
- "mode": "mxfp8"
22
- },
23
- "text_config": {
24
- "attention_bias": false,
25
- "attention_dropout": 0.0,
26
- "attn_output_gate": true,
27
- "bos_token_id": null,
28
- "dtype": "bfloat16",
29
- "eos_token_id": 248044,
30
- "full_attention_interval": 4,
31
- "head_dim": 256,
32
- "hidden_act": "silu",
33
- "hidden_size": 4096,
34
- "initializer_range": 0.02,
35
- "intermediate_size": 12288,
36
- "layer_types": [
37
- "linear_attention",
38
- "linear_attention",
39
- "linear_attention",
40
- "full_attention",
41
- "linear_attention",
42
- "linear_attention",
43
- "linear_attention",
44
- "full_attention",
45
- "linear_attention",
46
- "linear_attention",
47
- "linear_attention",
48
- "full_attention",
49
- "linear_attention",
50
- "linear_attention",
51
- "linear_attention",
52
- "full_attention",
53
- "linear_attention",
54
- "linear_attention",
55
- "linear_attention",
56
- "full_attention",
57
- "linear_attention",
58
- "linear_attention",
59
- "linear_attention",
60
- "full_attention",
61
- "linear_attention",
62
- "linear_attention",
63
- "linear_attention",
64
- "full_attention",
65
- "linear_attention",
66
- "linear_attention",
67
- "linear_attention",
68
- "full_attention"
69
- ],
70
- "linear_conv_kernel_dim": 4,
71
- "linear_key_head_dim": 128,
72
- "linear_num_key_heads": 16,
73
- "linear_num_value_heads": 32,
74
- "linear_value_head_dim": 128,
75
- "mamba_ssm_dtype": "float32",
76
- "max_position_embeddings": 1048576,
77
- "mlp_only_layers": [],
78
- "model_type": "qwen3_5_text",
79
- "mtp_num_hidden_layers": 1,
80
- "mtp_use_dedicated_embeddings": false,
81
- "num_attention_heads": 16,
82
- "num_hidden_layers": 32,
83
- "num_key_value_heads": 4,
84
- "pad_token_id": null,
85
- "partial_rotary_factor": 0.25,
86
- "rms_norm_eps": 1e-06,
87
- "rope_parameters": {
88
- "factor": 4.0,
89
- "original_max_position_embeddings": 262144,
90
- "mrope_interleaved": true,
91
- "mrope_section": [
92
- 11,
93
- 11,
94
- 10
95
- ],
96
- "rope_theta": 10000000,
97
- "type": "yarn"
98
- },
99
- "tie_word_embeddings": false,
100
- "use_cache": true,
101
- "vocab_size": 248320
102
  },
103
  "tie_word_embeddings": false,
104
- "transformers_version": "5.12.1",
105
- "use_cache": false,
106
- "video_token_id": 248057,
107
- "vision_end_token_id": 248054,
108
- "vision_start_token_id": 248053
 
109
  }
 
1
  {
2
+ "architectures": [
3
+ "Qwen3_5ForCausalLM"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": [
7
+ 248046,
8
+ 248044
9
+ ],
10
+ "model_type": "qwen3_5",
11
+ "pad_token_id": 248044,
12
+ "quantization": {
13
+ "group_size": 32,
14
+ "bits": 8,
15
+ "mode": "mxfp8"
16
+ },
17
+ "quantization_config": {
18
+ "group_size": 32,
19
+ "bits": 8,
20
+ "mode": "mxfp8"
21
+ },
22
+ "text_config": {
23
+ "attention_bias": false,
24
+ "attention_dropout": 0.0,
25
+ "attn_output_gate": true,
26
+ "bos_token_id": null,
27
  "dtype": "bfloat16",
28
+ "eos_token_id": 248044,
29
+ "full_attention_interval": 4,
30
+ "head_dim": 256,
31
+ "hidden_act": "silu",
32
+ "hidden_size": 4096,
33
+ "initializer_range": 0.02,
34
+ "intermediate_size": 12288,
35
+ "layer_types": [
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
+ "linear_attention",
53
+ "linear_attention",
54
+ "linear_attention",
55
+ "full_attention",
56
+ "linear_attention",
57
+ "linear_attention",
58
+ "linear_attention",
59
+ "full_attention",
60
+ "linear_attention",
61
+ "linear_attention",
62
+ "linear_attention",
63
+ "full_attention",
64
+ "linear_attention",
65
+ "linear_attention",
66
+ "linear_attention",
67
+ "full_attention"
68
  ],
69
+ "linear_conv_kernel_dim": 4,
70
+ "linear_key_head_dim": 128,
71
+ "linear_num_key_heads": 16,
72
+ "linear_num_value_heads": 32,
73
+ "linear_value_head_dim": 128,
74
+ "mamba_ssm_dtype": "float32",
75
+ "max_position_embeddings": 1048576,
76
+ "mlp_only_layers": [],
77
+ "model_type": "qwen3_5_text",
78
+ "mtp_num_hidden_layers": 1,
79
+ "mtp_use_dedicated_embeddings": false,
80
+ "num_attention_heads": 16,
81
+ "num_hidden_layers": 32,
82
+ "num_key_value_heads": 4,
83
+ "pad_token_id": null,
84
+ "partial_rotary_factor": 0.25,
85
+ "rms_norm_eps": 1e-06,
86
+ "rope_parameters": {
87
+ "factor": 4.0,
88
+ "original_max_position_embeddings": 262144,
89
+ "mrope_interleaved": true,
90
+ "mrope_section": [
91
+ 11,
92
+ 11,
93
+ 10
94
+ ],
95
+ "rope_theta": 10000000,
96
+ "type": "yarn"
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
97
  },
98
  "tie_word_embeddings": false,
99
+ "use_cache": true,
100
+ "vocab_size": 248320
101
+ },
102
+ "tie_word_embeddings": false,
103
+ "transformers_version": "5.12.1",
104
+ "use_cache": false
105
  }