Upload folder using huggingface_hub
Browse files
attnfusionv2-fullmha/config.json
ADDED
|
@@ -0,0 +1,78 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"LlamaForCausalLMEagle3"
|
| 4 |
+
],
|
| 5 |
+
"attention_bias": false,
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 128000,
|
| 8 |
+
"draft_vocab_size": 128256,
|
| 9 |
+
"eagle_config": {
|
| 10 |
+
"eagle_aux_hidden_state_layer_ids": [
|
| 11 |
+
0,
|
| 12 |
+
1,
|
| 13 |
+
2,
|
| 14 |
+
3,
|
| 15 |
+
4,
|
| 16 |
+
5,
|
| 17 |
+
6,
|
| 18 |
+
7,
|
| 19 |
+
8,
|
| 20 |
+
9,
|
| 21 |
+
10,
|
| 22 |
+
11,
|
| 23 |
+
12,
|
| 24 |
+
13,
|
| 25 |
+
14,
|
| 26 |
+
15,
|
| 27 |
+
16,
|
| 28 |
+
17,
|
| 29 |
+
18,
|
| 30 |
+
19,
|
| 31 |
+
20,
|
| 32 |
+
21,
|
| 33 |
+
22,
|
| 34 |
+
23,
|
| 35 |
+
24,
|
| 36 |
+
25,
|
| 37 |
+
26,
|
| 38 |
+
27,
|
| 39 |
+
28,
|
| 40 |
+
29,
|
| 41 |
+
30
|
| 42 |
+
]
|
| 43 |
+
},
|
| 44 |
+
"enable_fc_norm": true,
|
| 45 |
+
"eos_token_id": 128001,
|
| 46 |
+
"fc_config": {
|
| 47 |
+
"num_heads": 32,
|
| 48 |
+
"query_type": "first_token",
|
| 49 |
+
"type": "attn_fusion"
|
| 50 |
+
},
|
| 51 |
+
"head_dim": 128,
|
| 52 |
+
"hidden_act": "silu",
|
| 53 |
+
"hidden_size": 4096,
|
| 54 |
+
"initializer_range": 0.02,
|
| 55 |
+
"intermediate_size": 14336,
|
| 56 |
+
"max_position_embeddings": 131072,
|
| 57 |
+
"mlp_bias": false,
|
| 58 |
+
"model_type": "llama",
|
| 59 |
+
"num_attention_heads": 32,
|
| 60 |
+
"num_hidden_layers": 1,
|
| 61 |
+
"num_key_value_heads": 32,
|
| 62 |
+
"pad_token_id": 0,
|
| 63 |
+
"pretraining_tp": 1,
|
| 64 |
+
"rms_norm_eps": 1e-05,
|
| 65 |
+
"rope_scaling": {
|
| 66 |
+
"factor": 8.0,
|
| 67 |
+
"high_freq_factor": 4.0,
|
| 68 |
+
"low_freq_factor": 1.0,
|
| 69 |
+
"original_max_position_embeddings": 8192,
|
| 70 |
+
"rope_type": "llama3"
|
| 71 |
+
},
|
| 72 |
+
"rope_theta": 500000.0,
|
| 73 |
+
"tie_word_embeddings": false,
|
| 74 |
+
"torch_dtype": "bfloat16",
|
| 75 |
+
"transformers_version": "4.55.2",
|
| 76 |
+
"use_cache": true,
|
| 77 |
+
"vocab_size": 128256
|
| 78 |
+
}
|
attnfusionv2-fullmha/model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d780a3e4d435c2d1634de79e0f507d6bbdc9b89bede9dbbd65c8cc324279bb7
|
| 3 |
+
size 2824217952
|
attnfusionv2-fullmha/training_state.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9edb59ab4e3fd8960e06694016c7fbd46bd119b6b58b931bbec1f8d32d17fe7a
|
| 3 |
+
size 10263
|