Upload folder using huggingface_hub
Browse files- checkpoint-7200/config.json +61 -0
- checkpoint-7200/generation_config.json +5 -0
- checkpoint-7200/optimizer.pt +3 -0
- checkpoint-7200/pytorch_model-00001-of-00003.bin +3 -0
- checkpoint-7200/pytorch_model-00002-of-00003.bin +3 -0
- checkpoint-7200/pytorch_model-00003-of-00003.bin +3 -0
- checkpoint-7200/pytorch_model.bin.index.json +203 -0
- checkpoint-7200/rng_state_0.pth +3 -0
- checkpoint-7200/rng_state_1.pth +3 -0
- checkpoint-7200/rng_state_2.pth +3 -0
- checkpoint-7200/rng_state_3.pth +3 -0
- checkpoint-7200/scheduler.pt +3 -0
- checkpoint-7200/special_tokens_map.json +6 -0
- checkpoint-7200/tokenizer.json +0 -0
- checkpoint-7200/tokenizer_config.json +11 -0
- checkpoint-7200/trainer_state.json +0 -0
- checkpoint-7200/training_args.bin +3 -0
- config.json +61 -0
- generation_config.json +5 -0
- mm_projector.bin +3 -0
- mm_projector/checkpoint-2400.bin +3 -0
- mm_projector/checkpoint-4800.bin +3 -0
- mm_projector/checkpoint-7200.bin +3 -0
- pytorch_model-00001-of-00003.bin +3 -0
- pytorch_model-00002-of-00003.bin +3 -0
- pytorch_model-00003-of-00003.bin +3 -0
- pytorch_model.bin.index.json +203 -0
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +11 -0
- trainer_state.json +0 -0
- training_args.bin +3 -0
checkpoint-7200/config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mosaicml/mpt-7b-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaMPTForCausalLM"
|
5 |
+
],
|
6 |
+
"attn_config": {
|
7 |
+
"alibi": true,
|
8 |
+
"alibi_bias_max": 8,
|
9 |
+
"attn_impl": "torch",
|
10 |
+
"attn_pdrop": 0,
|
11 |
+
"attn_type": "multihead_attention",
|
12 |
+
"attn_uses_sequence_id": false,
|
13 |
+
"clip_qkv": null,
|
14 |
+
"prefix_lm": false,
|
15 |
+
"qk_ln": false,
|
16 |
+
"softmax_scale": null
|
17 |
+
},
|
18 |
+
"auto_map": {
|
19 |
+
"AutoConfig": "configuration_mpt.MPTConfig",
|
20 |
+
"AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
|
21 |
+
},
|
22 |
+
"d_model": 4096,
|
23 |
+
"emb_pdrop": 0,
|
24 |
+
"embedding_fraction": 1.0,
|
25 |
+
"expansion_ratio": 4,
|
26 |
+
"freeze_mm_mlp_adapter": false,
|
27 |
+
"init_config": {
|
28 |
+
"emb_init_std": null,
|
29 |
+
"emb_init_uniform_lim": null,
|
30 |
+
"fan_mode": "fan_in",
|
31 |
+
"init_div_is_residual": true,
|
32 |
+
"init_gain": 0,
|
33 |
+
"init_nonlinearity": "relu",
|
34 |
+
"init_std": 0.02,
|
35 |
+
"name": "kaiming_normal_",
|
36 |
+
"verbose": 0
|
37 |
+
},
|
38 |
+
"init_device": "cpu",
|
39 |
+
"learned_pos_emb": true,
|
40 |
+
"logit_scale": null,
|
41 |
+
"max_seq_len": 2048,
|
42 |
+
"mm_hidden_size": 1024,
|
43 |
+
"mm_use_im_start_end": true,
|
44 |
+
"mm_vision_select_layer": -2,
|
45 |
+
"mm_vision_tower": "openai/clip-vit-large-patch14",
|
46 |
+
"model_type": "llava_mpt",
|
47 |
+
"n_heads": 32,
|
48 |
+
"n_layers": 32,
|
49 |
+
"no_bias": true,
|
50 |
+
"norm_type": "low_precision_layernorm",
|
51 |
+
"resid_pdrop": 0,
|
52 |
+
"sep_image_conv_front": false,
|
53 |
+
"tokenizer_name": "EleutherAI/gpt-neox-20b",
|
54 |
+
"torch_dtype": "float32",
|
55 |
+
"transformers_version": "4.28.0.dev0",
|
56 |
+
"tune_mm_mlp_adapter": true,
|
57 |
+
"use_cache": false,
|
58 |
+
"use_mm_proj": true,
|
59 |
+
"verbose": 0,
|
60 |
+
"vocab_size": 50280
|
61 |
+
}
|
checkpoint-7200/generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.28.0.dev0",
|
4 |
+
"use_cache": false
|
5 |
+
}
|
checkpoint-7200/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9f3407258eea544abd007cb4c421ba24ce5a85281c707aa32f5ab637e804b988
|
3 |
+
size 33589607
|
checkpoint-7200/pytorch_model-00001-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4fe14e74fcfb2b961887e122ba24c2d1405c3384b4763ac88d7ddf16744cdd27
|
3 |
+
size 9951011493
|
checkpoint-7200/pytorch_model-00002-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51d38b05039d89b9e1d5ad6258d99b23f4aabaaad96e489324ccd20825479509
|
3 |
+
size 9932531069
|
checkpoint-7200/pytorch_model-00003-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d73e4d688b9f33c953396480581f4b159a950e14765f3da451b121151fbd3589
|
3 |
+
size 6727976839
|
checkpoint-7200/pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 26611449856
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"transformer.blocks.0.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
7 |
+
"transformer.blocks.0.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
8 |
+
"transformer.blocks.0.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
9 |
+
"transformer.blocks.0.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
10 |
+
"transformer.blocks.0.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
11 |
+
"transformer.blocks.0.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
12 |
+
"transformer.blocks.1.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
13 |
+
"transformer.blocks.1.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
14 |
+
"transformer.blocks.1.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
15 |
+
"transformer.blocks.1.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
16 |
+
"transformer.blocks.1.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
17 |
+
"transformer.blocks.1.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
18 |
+
"transformer.blocks.10.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
19 |
+
"transformer.blocks.10.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
20 |
+
"transformer.blocks.10.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
21 |
+
"transformer.blocks.10.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
22 |
+
"transformer.blocks.10.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
23 |
+
"transformer.blocks.10.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
24 |
+
"transformer.blocks.11.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
25 |
+
"transformer.blocks.11.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
26 |
+
"transformer.blocks.11.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
27 |
+
"transformer.blocks.11.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
28 |
+
"transformer.blocks.11.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
29 |
+
"transformer.blocks.11.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
30 |
+
"transformer.blocks.12.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
31 |
+
"transformer.blocks.12.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
32 |
+
"transformer.blocks.12.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
33 |
+
"transformer.blocks.12.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
34 |
+
"transformer.blocks.12.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
35 |
+
"transformer.blocks.12.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
36 |
+
"transformer.blocks.13.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
37 |
+
"transformer.blocks.13.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
38 |
+
"transformer.blocks.13.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
39 |
+
"transformer.blocks.13.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
40 |
+
"transformer.blocks.13.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
41 |
+
"transformer.blocks.13.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
42 |
+
"transformer.blocks.14.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
43 |
+
"transformer.blocks.14.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
44 |
+
"transformer.blocks.14.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
45 |
+
"transformer.blocks.14.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
46 |
+
"transformer.blocks.14.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
47 |
+
"transformer.blocks.14.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
48 |
+
"transformer.blocks.15.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
49 |
+
"transformer.blocks.15.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
50 |
+
"transformer.blocks.15.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
51 |
+
"transformer.blocks.15.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
52 |
+
"transformer.blocks.15.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
53 |
+
"transformer.blocks.15.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
54 |
+
"transformer.blocks.16.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
55 |
+
"transformer.blocks.16.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
56 |
+
"transformer.blocks.16.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
57 |
+
"transformer.blocks.16.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
58 |
+
"transformer.blocks.16.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
59 |
+
"transformer.blocks.16.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
60 |
+
"transformer.blocks.17.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
61 |
+
"transformer.blocks.17.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
62 |
+
"transformer.blocks.17.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
63 |
+
"transformer.blocks.17.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
64 |
+
"transformer.blocks.17.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
65 |
+
"transformer.blocks.17.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
66 |
+
"transformer.blocks.18.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
67 |
+
"transformer.blocks.18.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
68 |
+
"transformer.blocks.18.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
69 |
+
"transformer.blocks.18.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
70 |
+
"transformer.blocks.18.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
71 |
+
"transformer.blocks.18.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
72 |
+
"transformer.blocks.19.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
73 |
+
"transformer.blocks.19.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
74 |
+
"transformer.blocks.19.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
75 |
+
"transformer.blocks.19.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
76 |
+
"transformer.blocks.19.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
77 |
+
"transformer.blocks.19.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
78 |
+
"transformer.blocks.2.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
79 |
+
"transformer.blocks.2.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
80 |
+
"transformer.blocks.2.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
81 |
+
"transformer.blocks.2.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
82 |
+
"transformer.blocks.2.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
83 |
+
"transformer.blocks.2.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
84 |
+
"transformer.blocks.20.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
85 |
+
"transformer.blocks.20.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
86 |
+
"transformer.blocks.20.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
87 |
+
"transformer.blocks.20.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
88 |
+
"transformer.blocks.20.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
89 |
+
"transformer.blocks.20.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
90 |
+
"transformer.blocks.21.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
91 |
+
"transformer.blocks.21.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
92 |
+
"transformer.blocks.21.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
93 |
+
"transformer.blocks.21.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
94 |
+
"transformer.blocks.21.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
95 |
+
"transformer.blocks.21.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
96 |
+
"transformer.blocks.22.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
97 |
+
"transformer.blocks.22.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
98 |
+
"transformer.blocks.22.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
99 |
+
"transformer.blocks.22.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
100 |
+
"transformer.blocks.22.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
101 |
+
"transformer.blocks.22.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
102 |
+
"transformer.blocks.23.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
103 |
+
"transformer.blocks.23.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
104 |
+
"transformer.blocks.23.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
105 |
+
"transformer.blocks.23.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
106 |
+
"transformer.blocks.23.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
107 |
+
"transformer.blocks.23.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
108 |
+
"transformer.blocks.24.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
109 |
+
"transformer.blocks.24.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
110 |
+
"transformer.blocks.24.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
111 |
+
"transformer.blocks.24.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
112 |
+
"transformer.blocks.24.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
113 |
+
"transformer.blocks.24.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
114 |
+
"transformer.blocks.25.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
115 |
+
"transformer.blocks.25.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
116 |
+
"transformer.blocks.25.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
117 |
+
"transformer.blocks.25.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
118 |
+
"transformer.blocks.25.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
119 |
+
"transformer.blocks.25.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
120 |
+
"transformer.blocks.26.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
121 |
+
"transformer.blocks.26.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
122 |
+
"transformer.blocks.26.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
123 |
+
"transformer.blocks.26.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
124 |
+
"transformer.blocks.26.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
125 |
+
"transformer.blocks.26.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
126 |
+
"transformer.blocks.27.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
127 |
+
"transformer.blocks.27.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
128 |
+
"transformer.blocks.27.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
129 |
+
"transformer.blocks.27.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
130 |
+
"transformer.blocks.27.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
131 |
+
"transformer.blocks.27.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
132 |
+
"transformer.blocks.28.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
133 |
+
"transformer.blocks.28.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
134 |
+
"transformer.blocks.28.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
135 |
+
"transformer.blocks.28.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
136 |
+
"transformer.blocks.28.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
137 |
+
"transformer.blocks.28.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
138 |
+
"transformer.blocks.29.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
139 |
+
"transformer.blocks.29.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
140 |
+
"transformer.blocks.29.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
141 |
+
"transformer.blocks.29.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
142 |
+
"transformer.blocks.29.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
143 |
+
"transformer.blocks.29.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
144 |
+
"transformer.blocks.3.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
145 |
+
"transformer.blocks.3.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
146 |
+
"transformer.blocks.3.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
147 |
+
"transformer.blocks.3.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
148 |
+
"transformer.blocks.3.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
149 |
+
"transformer.blocks.3.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
150 |
+
"transformer.blocks.30.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
151 |
+
"transformer.blocks.30.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
152 |
+
"transformer.blocks.30.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
153 |
+
"transformer.blocks.30.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
154 |
+
"transformer.blocks.30.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
155 |
+
"transformer.blocks.30.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
156 |
+
"transformer.blocks.31.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
157 |
+
"transformer.blocks.31.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
158 |
+
"transformer.blocks.31.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
159 |
+
"transformer.blocks.31.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
160 |
+
"transformer.blocks.31.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
161 |
+
"transformer.blocks.31.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
162 |
+
"transformer.blocks.4.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
163 |
+
"transformer.blocks.4.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
164 |
+
"transformer.blocks.4.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
165 |
+
"transformer.blocks.4.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
166 |
+
"transformer.blocks.4.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
167 |
+
"transformer.blocks.4.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
168 |
+
"transformer.blocks.5.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
169 |
+
"transformer.blocks.5.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
170 |
+
"transformer.blocks.5.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
171 |
+
"transformer.blocks.5.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
172 |
+
"transformer.blocks.5.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
173 |
+
"transformer.blocks.5.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
174 |
+
"transformer.blocks.6.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
175 |
+
"transformer.blocks.6.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
176 |
+
"transformer.blocks.6.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
177 |
+
"transformer.blocks.6.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
178 |
+
"transformer.blocks.6.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
179 |
+
"transformer.blocks.6.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
180 |
+
"transformer.blocks.7.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
181 |
+
"transformer.blocks.7.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
182 |
+
"transformer.blocks.7.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
183 |
+
"transformer.blocks.7.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
184 |
+
"transformer.blocks.7.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
185 |
+
"transformer.blocks.7.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
186 |
+
"transformer.blocks.8.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
187 |
+
"transformer.blocks.8.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
188 |
+
"transformer.blocks.8.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
189 |
+
"transformer.blocks.8.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
190 |
+
"transformer.blocks.8.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
191 |
+
"transformer.blocks.8.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
192 |
+
"transformer.blocks.9.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
193 |
+
"transformer.blocks.9.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
194 |
+
"transformer.blocks.9.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
195 |
+
"transformer.blocks.9.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
196 |
+
"transformer.blocks.9.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
197 |
+
"transformer.blocks.9.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
198 |
+
"transformer.mm_projector.bias": "pytorch_model-00003-of-00003.bin",
|
199 |
+
"transformer.mm_projector.weight": "pytorch_model-00003-of-00003.bin",
|
200 |
+
"transformer.norm_f.weight": "pytorch_model-00003-of-00003.bin",
|
201 |
+
"transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
|
202 |
+
}
|
203 |
+
}
|
checkpoint-7200/rng_state_0.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e75c96f06b249e57a701db73ce821398e69672027a86d3a44063830602a29ab4
|
3 |
+
size 14583
|
checkpoint-7200/rng_state_1.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6dae7f45b6bac644ac207a61f43cba6d4b919a4cac22022bbb02907914422f5d
|
3 |
+
size 14583
|
checkpoint-7200/rng_state_2.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e53c770fe48635faad7fa341007d771781f1397cd47daab5b58f879ffb65f178
|
3 |
+
size 14583
|
checkpoint-7200/rng_state_3.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68692af1001e65d02e07ac9974ccf4c332cfb23bc8f89566e1a908b1f2c4a1ed
|
3 |
+
size 14583
|
checkpoint-7200/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a129ca5ec20f4a6c3e5435cc01ced782bef0ef09fd6e6a8f82452e6dcb4f4662
|
3 |
+
size 627
|
checkpoint-7200/special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
checkpoint-7200/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-7200/tokenizer_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 2048,
|
7 |
+
"padding_side": "right",
|
8 |
+
"special_tokens_map_file": "/home/ubuntu/.cache/huggingface/hub/models--mosaicml--mpt-7b-instruct/snapshots/1fc4634127ec64a45716003578b9cfae23265849/special_tokens_map.json",
|
9 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
10 |
+
"unk_token": "<|endoftext|>"
|
11 |
+
}
|
checkpoint-7200/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-7200/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:499e95a18ec8111d7e7627b4f751606ef8f56f60a773b5003e79240171b023ff
|
3 |
+
size 3963
|
config.json
ADDED
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "mosaicml/mpt-7b-instruct",
|
3 |
+
"architectures": [
|
4 |
+
"LlavaMPTForCausalLM"
|
5 |
+
],
|
6 |
+
"attn_config": {
|
7 |
+
"alibi": true,
|
8 |
+
"alibi_bias_max": 8,
|
9 |
+
"attn_impl": "torch",
|
10 |
+
"attn_pdrop": 0,
|
11 |
+
"attn_type": "multihead_attention",
|
12 |
+
"attn_uses_sequence_id": false,
|
13 |
+
"clip_qkv": null,
|
14 |
+
"prefix_lm": false,
|
15 |
+
"qk_ln": false,
|
16 |
+
"softmax_scale": null
|
17 |
+
},
|
18 |
+
"auto_map": {
|
19 |
+
"AutoConfig": "configuration_mpt.MPTConfig",
|
20 |
+
"AutoModelForCausalLM": "modeling_mpt.MPTForCausalLM"
|
21 |
+
},
|
22 |
+
"d_model": 4096,
|
23 |
+
"emb_pdrop": 0,
|
24 |
+
"embedding_fraction": 1.0,
|
25 |
+
"expansion_ratio": 4,
|
26 |
+
"freeze_mm_mlp_adapter": false,
|
27 |
+
"init_config": {
|
28 |
+
"emb_init_std": null,
|
29 |
+
"emb_init_uniform_lim": null,
|
30 |
+
"fan_mode": "fan_in",
|
31 |
+
"init_div_is_residual": true,
|
32 |
+
"init_gain": 0,
|
33 |
+
"init_nonlinearity": "relu",
|
34 |
+
"init_std": 0.02,
|
35 |
+
"name": "kaiming_normal_",
|
36 |
+
"verbose": 0
|
37 |
+
},
|
38 |
+
"init_device": "cpu",
|
39 |
+
"learned_pos_emb": true,
|
40 |
+
"logit_scale": null,
|
41 |
+
"max_seq_len": 2048,
|
42 |
+
"mm_hidden_size": 1024,
|
43 |
+
"mm_use_im_start_end": true,
|
44 |
+
"mm_vision_select_layer": -2,
|
45 |
+
"mm_vision_tower": "openai/clip-vit-large-patch14",
|
46 |
+
"model_type": "llava_mpt",
|
47 |
+
"n_heads": 32,
|
48 |
+
"n_layers": 32,
|
49 |
+
"no_bias": true,
|
50 |
+
"norm_type": "low_precision_layernorm",
|
51 |
+
"resid_pdrop": 0,
|
52 |
+
"sep_image_conv_front": false,
|
53 |
+
"tokenizer_name": "EleutherAI/gpt-neox-20b",
|
54 |
+
"torch_dtype": "float32",
|
55 |
+
"transformers_version": "4.28.0.dev0",
|
56 |
+
"tune_mm_mlp_adapter": true,
|
57 |
+
"use_cache": false,
|
58 |
+
"use_mm_proj": true,
|
59 |
+
"verbose": 0,
|
60 |
+
"vocab_size": 50280
|
61 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"transformers_version": "4.28.0.dev0",
|
4 |
+
"use_cache": false
|
5 |
+
}
|
mm_projector.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab8060530a37295ebc3f85fe92d8be3ab43cda30013f2b0701da12b527373c8f
|
3 |
+
size 16794683
|
mm_projector/checkpoint-2400.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0c78339d408c43e44fe3dd6e4a64faa4a61674a2c3a2036ed019c91b77073ccb
|
3 |
+
size 16794695
|
mm_projector/checkpoint-4800.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:15337be5f5cf33e7b55fa5d2f399237540d9bfa6870bae6b156a38206d92a756
|
3 |
+
size 16794695
|
mm_projector/checkpoint-7200.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cf33b04ba818e3ff23909914525748a47b2adfbc4c89a0f03f8945b3817342f4
|
3 |
+
size 16794695
|
pytorch_model-00001-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ee8a86b6c06ab73b5f2a40aa146dba1fe1c72f9c4bbd9cd074dda1e11d35fe8e
|
3 |
+
size 9951010469
|
pytorch_model-00002-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ddd640111d8792ff43f5667303350665a9f04a51143411fd0e881815d1a07497
|
3 |
+
size 9932530109
|
pytorch_model-00003-of-00003.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:66ea039e9772bd94cae8b99c8cb58ee5fc6ddc2a916398713fa7132a74e54cc6
|
3 |
+
size 6727976135
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,203 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 26611449856
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"transformer.blocks.0.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
7 |
+
"transformer.blocks.0.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
8 |
+
"transformer.blocks.0.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
9 |
+
"transformer.blocks.0.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
10 |
+
"transformer.blocks.0.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
11 |
+
"transformer.blocks.0.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
12 |
+
"transformer.blocks.1.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
13 |
+
"transformer.blocks.1.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
14 |
+
"transformer.blocks.1.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
15 |
+
"transformer.blocks.1.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
16 |
+
"transformer.blocks.1.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
17 |
+
"transformer.blocks.1.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
18 |
+
"transformer.blocks.10.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
19 |
+
"transformer.blocks.10.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
20 |
+
"transformer.blocks.10.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
21 |
+
"transformer.blocks.10.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
22 |
+
"transformer.blocks.10.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
23 |
+
"transformer.blocks.10.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
24 |
+
"transformer.blocks.11.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
25 |
+
"transformer.blocks.11.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
26 |
+
"transformer.blocks.11.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
27 |
+
"transformer.blocks.11.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
28 |
+
"transformer.blocks.11.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
29 |
+
"transformer.blocks.11.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
30 |
+
"transformer.blocks.12.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
31 |
+
"transformer.blocks.12.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
32 |
+
"transformer.blocks.12.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
33 |
+
"transformer.blocks.12.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
34 |
+
"transformer.blocks.12.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
35 |
+
"transformer.blocks.12.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
36 |
+
"transformer.blocks.13.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
37 |
+
"transformer.blocks.13.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
38 |
+
"transformer.blocks.13.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
39 |
+
"transformer.blocks.13.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
40 |
+
"transformer.blocks.13.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
41 |
+
"transformer.blocks.13.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
42 |
+
"transformer.blocks.14.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
43 |
+
"transformer.blocks.14.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
44 |
+
"transformer.blocks.14.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
45 |
+
"transformer.blocks.14.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
46 |
+
"transformer.blocks.14.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
47 |
+
"transformer.blocks.14.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
48 |
+
"transformer.blocks.15.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
49 |
+
"transformer.blocks.15.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
50 |
+
"transformer.blocks.15.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
51 |
+
"transformer.blocks.15.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
52 |
+
"transformer.blocks.15.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
53 |
+
"transformer.blocks.15.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
54 |
+
"transformer.blocks.16.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
55 |
+
"transformer.blocks.16.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
56 |
+
"transformer.blocks.16.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
57 |
+
"transformer.blocks.16.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
58 |
+
"transformer.blocks.16.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
59 |
+
"transformer.blocks.16.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
60 |
+
"transformer.blocks.17.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
61 |
+
"transformer.blocks.17.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
62 |
+
"transformer.blocks.17.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
63 |
+
"transformer.blocks.17.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
64 |
+
"transformer.blocks.17.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
65 |
+
"transformer.blocks.17.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
66 |
+
"transformer.blocks.18.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
67 |
+
"transformer.blocks.18.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
68 |
+
"transformer.blocks.18.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
69 |
+
"transformer.blocks.18.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
70 |
+
"transformer.blocks.18.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
71 |
+
"transformer.blocks.18.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
72 |
+
"transformer.blocks.19.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
73 |
+
"transformer.blocks.19.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
74 |
+
"transformer.blocks.19.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
75 |
+
"transformer.blocks.19.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
76 |
+
"transformer.blocks.19.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
77 |
+
"transformer.blocks.19.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
78 |
+
"transformer.blocks.2.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
79 |
+
"transformer.blocks.2.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
80 |
+
"transformer.blocks.2.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
81 |
+
"transformer.blocks.2.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
82 |
+
"transformer.blocks.2.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
83 |
+
"transformer.blocks.2.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
84 |
+
"transformer.blocks.20.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
85 |
+
"transformer.blocks.20.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
86 |
+
"transformer.blocks.20.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
87 |
+
"transformer.blocks.20.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
88 |
+
"transformer.blocks.20.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
89 |
+
"transformer.blocks.20.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
90 |
+
"transformer.blocks.21.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
91 |
+
"transformer.blocks.21.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
92 |
+
"transformer.blocks.21.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
93 |
+
"transformer.blocks.21.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
94 |
+
"transformer.blocks.21.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
95 |
+
"transformer.blocks.21.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
96 |
+
"transformer.blocks.22.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
97 |
+
"transformer.blocks.22.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
98 |
+
"transformer.blocks.22.ffn.down_proj.weight": "pytorch_model-00002-of-00003.bin",
|
99 |
+
"transformer.blocks.22.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
100 |
+
"transformer.blocks.22.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
101 |
+
"transformer.blocks.22.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
102 |
+
"transformer.blocks.23.attn.Wqkv.weight": "pytorch_model-00002-of-00003.bin",
|
103 |
+
"transformer.blocks.23.attn.out_proj.weight": "pytorch_model-00002-of-00003.bin",
|
104 |
+
"transformer.blocks.23.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
105 |
+
"transformer.blocks.23.ffn.up_proj.weight": "pytorch_model-00002-of-00003.bin",
|
106 |
+
"transformer.blocks.23.norm_1.weight": "pytorch_model-00002-of-00003.bin",
|
107 |
+
"transformer.blocks.23.norm_2.weight": "pytorch_model-00002-of-00003.bin",
|
108 |
+
"transformer.blocks.24.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
109 |
+
"transformer.blocks.24.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
110 |
+
"transformer.blocks.24.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
111 |
+
"transformer.blocks.24.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
112 |
+
"transformer.blocks.24.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
113 |
+
"transformer.blocks.24.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
114 |
+
"transformer.blocks.25.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
115 |
+
"transformer.blocks.25.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
116 |
+
"transformer.blocks.25.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
117 |
+
"transformer.blocks.25.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
118 |
+
"transformer.blocks.25.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
119 |
+
"transformer.blocks.25.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
120 |
+
"transformer.blocks.26.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
121 |
+
"transformer.blocks.26.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
122 |
+
"transformer.blocks.26.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
123 |
+
"transformer.blocks.26.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
124 |
+
"transformer.blocks.26.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
125 |
+
"transformer.blocks.26.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
126 |
+
"transformer.blocks.27.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
127 |
+
"transformer.blocks.27.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
128 |
+
"transformer.blocks.27.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
129 |
+
"transformer.blocks.27.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
130 |
+
"transformer.blocks.27.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
131 |
+
"transformer.blocks.27.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
132 |
+
"transformer.blocks.28.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
133 |
+
"transformer.blocks.28.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
134 |
+
"transformer.blocks.28.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
135 |
+
"transformer.blocks.28.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
136 |
+
"transformer.blocks.28.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
137 |
+
"transformer.blocks.28.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
138 |
+
"transformer.blocks.29.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
139 |
+
"transformer.blocks.29.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
140 |
+
"transformer.blocks.29.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
141 |
+
"transformer.blocks.29.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
142 |
+
"transformer.blocks.29.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
143 |
+
"transformer.blocks.29.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
144 |
+
"transformer.blocks.3.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
145 |
+
"transformer.blocks.3.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
146 |
+
"transformer.blocks.3.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
147 |
+
"transformer.blocks.3.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
148 |
+
"transformer.blocks.3.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
149 |
+
"transformer.blocks.3.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
150 |
+
"transformer.blocks.30.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
151 |
+
"transformer.blocks.30.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
152 |
+
"transformer.blocks.30.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
153 |
+
"transformer.blocks.30.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
154 |
+
"transformer.blocks.30.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
155 |
+
"transformer.blocks.30.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
156 |
+
"transformer.blocks.31.attn.Wqkv.weight": "pytorch_model-00003-of-00003.bin",
|
157 |
+
"transformer.blocks.31.attn.out_proj.weight": "pytorch_model-00003-of-00003.bin",
|
158 |
+
"transformer.blocks.31.ffn.down_proj.weight": "pytorch_model-00003-of-00003.bin",
|
159 |
+
"transformer.blocks.31.ffn.up_proj.weight": "pytorch_model-00003-of-00003.bin",
|
160 |
+
"transformer.blocks.31.norm_1.weight": "pytorch_model-00003-of-00003.bin",
|
161 |
+
"transformer.blocks.31.norm_2.weight": "pytorch_model-00003-of-00003.bin",
|
162 |
+
"transformer.blocks.4.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
163 |
+
"transformer.blocks.4.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
164 |
+
"transformer.blocks.4.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
165 |
+
"transformer.blocks.4.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
166 |
+
"transformer.blocks.4.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
167 |
+
"transformer.blocks.4.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
168 |
+
"transformer.blocks.5.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
169 |
+
"transformer.blocks.5.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
170 |
+
"transformer.blocks.5.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
171 |
+
"transformer.blocks.5.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
172 |
+
"transformer.blocks.5.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
173 |
+
"transformer.blocks.5.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
174 |
+
"transformer.blocks.6.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
175 |
+
"transformer.blocks.6.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
176 |
+
"transformer.blocks.6.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
177 |
+
"transformer.blocks.6.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
178 |
+
"transformer.blocks.6.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
179 |
+
"transformer.blocks.6.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
180 |
+
"transformer.blocks.7.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
181 |
+
"transformer.blocks.7.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
182 |
+
"transformer.blocks.7.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
183 |
+
"transformer.blocks.7.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
184 |
+
"transformer.blocks.7.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
185 |
+
"transformer.blocks.7.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
186 |
+
"transformer.blocks.8.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
187 |
+
"transformer.blocks.8.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
188 |
+
"transformer.blocks.8.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
189 |
+
"transformer.blocks.8.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
190 |
+
"transformer.blocks.8.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
191 |
+
"transformer.blocks.8.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
192 |
+
"transformer.blocks.9.attn.Wqkv.weight": "pytorch_model-00001-of-00003.bin",
|
193 |
+
"transformer.blocks.9.attn.out_proj.weight": "pytorch_model-00001-of-00003.bin",
|
194 |
+
"transformer.blocks.9.ffn.down_proj.weight": "pytorch_model-00001-of-00003.bin",
|
195 |
+
"transformer.blocks.9.ffn.up_proj.weight": "pytorch_model-00001-of-00003.bin",
|
196 |
+
"transformer.blocks.9.norm_1.weight": "pytorch_model-00001-of-00003.bin",
|
197 |
+
"transformer.blocks.9.norm_2.weight": "pytorch_model-00001-of-00003.bin",
|
198 |
+
"transformer.mm_projector.bias": "pytorch_model-00003-of-00003.bin",
|
199 |
+
"transformer.mm_projector.weight": "pytorch_model-00003-of-00003.bin",
|
200 |
+
"transformer.norm_f.weight": "pytorch_model-00003-of-00003.bin",
|
201 |
+
"transformer.wte.weight": "pytorch_model-00001-of-00003.bin"
|
202 |
+
}
|
203 |
+
}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"bos_token": "<|endoftext|>",
|
4 |
+
"clean_up_tokenization_spaces": true,
|
5 |
+
"eos_token": "<|endoftext|>",
|
6 |
+
"model_max_length": 2048,
|
7 |
+
"padding_side": "right",
|
8 |
+
"special_tokens_map_file": "/home/ubuntu/.cache/huggingface/hub/models--mosaicml--mpt-7b-instruct/snapshots/1fc4634127ec64a45716003578b9cfae23265849/special_tokens_map.json",
|
9 |
+
"tokenizer_class": "GPTNeoXTokenizer",
|
10 |
+
"unk_token": "<|endoftext|>"
|
11 |
+
}
|
trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:499e95a18ec8111d7e7627b4f751606ef8f56f60a773b5003e79240171b023ff
|
3 |
+
size 3963
|