yunyin007 commited on
Commit
7153c58
·
verified ·
1 Parent(s): 313931e

Upload folder using huggingface_hub

Browse files
Files changed (2) hide show
  1. mtp/config.json +82 -0
  2. mtp/model.safetensors +3 -0
mtp/config.json ADDED
@@ -0,0 +1,82 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "IQuestQ1MTP"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "fp32_residual_connection": true,
7
+ "hidden_size": 3072,
8
+ "model_type": "iquest_q1_mtp",
9
+ "num_draft_slots": 7,
10
+ "num_target_layers": 88,
11
+ "sliding_window": 512,
12
+ "swa_rope_theta": 10000.0,
13
+ "target_config": {
14
+ "architectures": [
15
+ "IQuestQ1ForCausalLM"
16
+ ],
17
+ "attention_bias": false,
18
+ "attention_dropout": 0.0,
19
+ "attn_out_scale": 1.0,
20
+ "dense_intermediate_size": 12288,
21
+ "dtype": "bfloat16",
22
+ "embed_scale": 1.0,
23
+ "enable_sink_attention": true,
24
+ "eos_token_id": 0,
25
+ "ffn_out_scale": 0.53881590608,
26
+ "first_layer_attn_out_scale": 1.0,
27
+ "first_layer_ffn_out_scale": 1.0,
28
+ "first_layers_types": [
29
+ "full_attention"
30
+ ],
31
+ "fuse_sink_attention": true,
32
+ "head_dim": 128,
33
+ "hidden_act": "silu",
34
+ "hidden_size": 3072,
35
+ "hybrid_layers_types_block": [
36
+ "full_attention",
37
+ "sliding_attention",
38
+ "sliding_attention",
39
+ "sliding_attention"
40
+ ],
41
+ "intermediate_size": 1536,
42
+ "last_layers_types": [
43
+ "full_attention",
44
+ "full_attention",
45
+ "full_attention"
46
+ ],
47
+ "logit_scale": 1.0,
48
+ "max_position_embeddings": 524288,
49
+ "mlp_only_layers": [
50
+ 0
51
+ ],
52
+ "model_type": "iquest_q1",
53
+ "moe_router_dtype": "fp32",
54
+ "enable_lm_head_fp32": true,
55
+ "no_rope_layers": [],
56
+ "num_attention_heads": 48,
57
+ "num_experts": 256,
58
+ "num_experts_per_tok": 8,
59
+ "num_hidden_layers": 88,
60
+ "num_hybrid_layers_block": 21,
61
+ "num_key_value_heads": 8,
62
+ "num_mtp_layers": 0,
63
+ "rms_norm_eps": 1e-06,
64
+ "rope_theta": 1000000,
65
+ "rotary_dim": 32,
66
+ "shared_kv_num_layers": 0,
67
+ "shared_kv_source_begin": 0,
68
+ "shared_kv_target_begin": 0,
69
+ "sliding_window": 4096,
70
+ "softmax_scale": null,
71
+ "swa_rope_theta": 10000.0,
72
+ "tie_word_embeddings": false,
73
+ "transformers_version": "4.57.1",
74
+ "use_cache": true,
75
+ "use_hybrid_layers": true,
76
+ "use_over_encoding": false,
77
+ "use_sliding_window": true,
78
+ "vocab_size": 160000
79
+ },
80
+ "vocab_size": 160000,
81
+ "max_position_embeddings": 524288
82
+ }
mtp/model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32d4e15f30fa5a6e9d2a70fc3e7ff5187f2bc9eab9a7e6942ef18f3c894fe2ed
3
+ size 9341293352