DBlake-BoxedLogic commited on
Commit
fd2a351
·
verified ·
1 Parent(s): 4a4f638

Training in progress, step 250

Browse files
Files changed (4) hide show
  1. config.json +99 -0
  2. generation_config.json +7 -0
  3. model.safetensors +3 -0
  4. training_args.bin +3 -0
config.json ADDED
@@ -0,0 +1,99 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "GraniteMoeHybridForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "attention_multiplier": 0.0078125,
8
+ "bos_token_id": 100257,
9
+ "dtype": "bfloat16",
10
+ "embedding_multiplier": 12,
11
+ "eos_token_id": 100257,
12
+ "hidden_act": "silu",
13
+ "hidden_size": 1536,
14
+ "initializer_range": 0.1,
15
+ "intermediate_size": 512,
16
+ "layer_types": [
17
+ "mamba",
18
+ "mamba",
19
+ "mamba",
20
+ "mamba",
21
+ "mamba",
22
+ "attention",
23
+ "mamba",
24
+ "mamba",
25
+ "mamba",
26
+ "mamba",
27
+ "mamba",
28
+ "mamba",
29
+ "mamba",
30
+ "mamba",
31
+ "mamba",
32
+ "attention",
33
+ "mamba",
34
+ "mamba",
35
+ "mamba",
36
+ "mamba",
37
+ "mamba",
38
+ "mamba",
39
+ "mamba",
40
+ "mamba",
41
+ "mamba",
42
+ "attention",
43
+ "mamba",
44
+ "mamba",
45
+ "mamba",
46
+ "mamba",
47
+ "mamba",
48
+ "mamba",
49
+ "mamba",
50
+ "mamba",
51
+ "mamba",
52
+ "attention",
53
+ "mamba",
54
+ "mamba",
55
+ "mamba",
56
+ "mamba"
57
+ ],
58
+ "logits_scaling": 6,
59
+ "mamba_chunk_size": 256,
60
+ "mamba_conv_bias": true,
61
+ "mamba_d_conv": 4,
62
+ "mamba_d_head": 64,
63
+ "mamba_d_state": 128,
64
+ "mamba_expand": 2,
65
+ "mamba_n_groups": 1,
66
+ "mamba_n_heads": 48,
67
+ "mamba_proj_bias": false,
68
+ "max_position_embeddings": 131072,
69
+ "model_type": "granitemoehybrid",
70
+ "normalization_function": "rmsnorm",
71
+ "num_attention_heads": 12,
72
+ "num_experts_per_tok": 6,
73
+ "num_hidden_layers": 40,
74
+ "num_key_value_heads": 4,
75
+ "num_local_experts": 64,
76
+ "output_router_logits": false,
77
+ "pad_token_id": 100256,
78
+ "position_embedding_type": "nope",
79
+ "residual_multiplier": 0.22,
80
+ "rms_norm_eps": 1e-05,
81
+ "rope_parameters": {
82
+ "rope_theta": 10000,
83
+ "rope_type": "default"
84
+ },
85
+ "router_aux_loss_coef": 0.0,
86
+ "shared_intermediate_size": 1024,
87
+ "tie_word_embeddings": true,
88
+ "time_step_limit": [
89
+ 0.0,
90
+ {
91
+ "__float__": "Infinity"
92
+ }
93
+ ],
94
+ "time_step_max": 0.1,
95
+ "time_step_min": 0.001,
96
+ "transformers_version": "5.3.0",
97
+ "use_cache": false,
98
+ "vocab_size": 100352
99
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 100257,
4
+ "eos_token_id": 100257,
5
+ "pad_token_id": 100256,
6
+ "transformers_version": "5.3.0"
7
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:474821c1d9281a0edc521f3f394be4ca46cd7412c3350e09c7a20762164dad4d
3
+ size 14186424184
training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:12f2be75b84f0eecdd98cb53bf394d0e8a665f8dc0abfa141e56d1e68a9c2592
3
+ size 6609