Upload 3 files
Browse files
merged_model_224/1/mp_rank_00_model_states.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e324cd51cf182dd6a6de1a57a71b2ba6808d1aa797b01fee6d7708c02a073fd8
|
| 3 |
+
size 35947831730
|
merged_model_224/latest
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
1
|
merged_model_224/model_config.json
ADDED
|
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"model_class": "FineTuneTestCogVLMModel",
|
| 3 |
+
"tokenizer_type": "vicuna-7b-v1.5",
|
| 4 |
+
"num_layers": 32,
|
| 5 |
+
"hidden_size": 4096,
|
| 6 |
+
"num_attention_heads": 32,
|
| 7 |
+
"vocab_size": 32000,
|
| 8 |
+
"layernorm_order": "pre",
|
| 9 |
+
"model_parallel_size": 1,
|
| 10 |
+
"max_sequence_length": 4096,
|
| 11 |
+
"is_decoder": [
|
| 12 |
+
true,
|
| 13 |
+
true,
|
| 14 |
+
true,
|
| 15 |
+
true,
|
| 16 |
+
true,
|
| 17 |
+
true,
|
| 18 |
+
true,
|
| 19 |
+
true,
|
| 20 |
+
true,
|
| 21 |
+
true,
|
| 22 |
+
true,
|
| 23 |
+
true,
|
| 24 |
+
true,
|
| 25 |
+
true,
|
| 26 |
+
true,
|
| 27 |
+
true,
|
| 28 |
+
true,
|
| 29 |
+
true,
|
| 30 |
+
true,
|
| 31 |
+
true,
|
| 32 |
+
true,
|
| 33 |
+
true,
|
| 34 |
+
true,
|
| 35 |
+
true,
|
| 36 |
+
true,
|
| 37 |
+
true,
|
| 38 |
+
true,
|
| 39 |
+
true,
|
| 40 |
+
true,
|
| 41 |
+
true,
|
| 42 |
+
true,
|
| 43 |
+
true
|
| 44 |
+
],
|
| 45 |
+
"cross_attn_hidden_size": 1024,
|
| 46 |
+
"use_bias": false,
|
| 47 |
+
"inner_hidden_size": 11008,
|
| 48 |
+
"cross_hidden_size_per_attention_head": 32,
|
| 49 |
+
"pre_seq_len": 8,
|
| 50 |
+
"lora_rank": 50,
|
| 51 |
+
"use_ptuning": false,
|
| 52 |
+
"use_lora": false,
|
| 53 |
+
"use_qlora": false,
|
| 54 |
+
"layer_range": null,
|
| 55 |
+
"image_length": 256,
|
| 56 |
+
"eva_args": {
|
| 57 |
+
"model_class": "EVA2CLIPModel",
|
| 58 |
+
"num_layers": 63,
|
| 59 |
+
"hidden_size": 1792,
|
| 60 |
+
"num_attention_heads": 16,
|
| 61 |
+
"vocab_size": 1,
|
| 62 |
+
"layernorm_order": "post",
|
| 63 |
+
"model_parallel_size": 1,
|
| 64 |
+
"max_sequence_length": 257,
|
| 65 |
+
"inner_hidden_size": 15360,
|
| 66 |
+
"use_final_layernorm": false,
|
| 67 |
+
"layernorm_epsilon": 1e-06,
|
| 68 |
+
"row_parallel_linear_final_bias": false,
|
| 69 |
+
"image_size": [
|
| 70 |
+
224,
|
| 71 |
+
224
|
| 72 |
+
],
|
| 73 |
+
"pre_len": 1,
|
| 74 |
+
"post_len": 0,
|
| 75 |
+
"in_channels": 3,
|
| 76 |
+
"patch_size": 14
|
| 77 |
+
},
|
| 78 |
+
"bos_token_id": 1,
|
| 79 |
+
"eos_token_id": 2,
|
| 80 |
+
"pad_token_id": 0
|
| 81 |
+
}
|