BramVanroy
commited on
Commit
•
aabeff7
1
Parent(s):
35f0d28
Training in progress, epoch 1, checkpoint
Browse files- checkpoint-1166/added_tokens.json +42 -0
- checkpoint-1166/config.json +34 -0
- checkpoint-1166/generation_config.json +7 -0
- checkpoint-1166/global_step1166/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt +3 -0
- checkpoint-1166/global_step1166/zero_pp_rank_0_mp_rank_00_model_states.pt +3 -0
- checkpoint-1166/latest +1 -0
- checkpoint-1166/merges.txt +0 -0
- checkpoint-1166/model-00001-of-00002.safetensors +3 -0
- checkpoint-1166/model-00002-of-00002.safetensors +3 -0
- checkpoint-1166/model.safetensors.index.json +460 -0
- checkpoint-1166/rng_state.pth +3 -0
- checkpoint-1166/scheduler.pt +3 -0
- checkpoint-1166/special_tokens_map.json +34 -0
- checkpoint-1166/tokenizer.json +0 -0
- checkpoint-1166/tokenizer_config.json +345 -0
- checkpoint-1166/trainer_state.json +0 -0
- checkpoint-1166/training_args.bin +3 -0
- checkpoint-1166/vocab.json +0 -0
- checkpoint-1166/zero_to_fp32.py +587 -0
checkpoint-1166/added_tokens.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"\t\t": 50294,
|
3 |
+
"\t\t\t": 50293,
|
4 |
+
"\t\t\t\t": 50292,
|
5 |
+
"\t\t\t\t\t": 50291,
|
6 |
+
"\t\t\t\t\t\t": 50290,
|
7 |
+
"\t\t\t\t\t\t\t": 50289,
|
8 |
+
"\t\t\t\t\t\t\t\t": 50288,
|
9 |
+
"\t\t\t\t\t\t\t\t\t": 50287,
|
10 |
+
" ": 50286,
|
11 |
+
" ": 50285,
|
12 |
+
" ": 50284,
|
13 |
+
" ": 50283,
|
14 |
+
" ": 50282,
|
15 |
+
" ": 50281,
|
16 |
+
" ": 50280,
|
17 |
+
" ": 50279,
|
18 |
+
" ": 50278,
|
19 |
+
" ": 50277,
|
20 |
+
" ": 50276,
|
21 |
+
" ": 50275,
|
22 |
+
" ": 50274,
|
23 |
+
" ": 50273,
|
24 |
+
" ": 50272,
|
25 |
+
" ": 50271,
|
26 |
+
" ": 50270,
|
27 |
+
" ": 50269,
|
28 |
+
" ": 50268,
|
29 |
+
" ": 50267,
|
30 |
+
" ": 50266,
|
31 |
+
" ": 50265,
|
32 |
+
" ": 50264,
|
33 |
+
" ": 50263,
|
34 |
+
" ": 50262,
|
35 |
+
" ": 50261,
|
36 |
+
" ": 50260,
|
37 |
+
" ": 50259,
|
38 |
+
" ": 50258,
|
39 |
+
" ": 50257,
|
40 |
+
"<|im_end|>": 50296,
|
41 |
+
"<|im_start|>": 50295
|
42 |
+
}
|
checkpoint-1166/config.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BramVanroy/fietje-2b-sft",
|
3 |
+
"architectures": [
|
4 |
+
"PhiForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"auto_map": {
|
8 |
+
"AutoConfig": "microsoft/phi-2--configuration_phi.PhiConfig",
|
9 |
+
"AutoModelForCausalLM": "microsoft/phi-2--modeling_phi.PhiForCausalLM"
|
10 |
+
},
|
11 |
+
"bos_token_id": 50256,
|
12 |
+
"embd_pdrop": 0.0,
|
13 |
+
"eos_token_id": 50256,
|
14 |
+
"hidden_act": "gelu_new",
|
15 |
+
"hidden_size": 2560,
|
16 |
+
"initializer_range": 0.02,
|
17 |
+
"intermediate_size": 10240,
|
18 |
+
"layer_norm_eps": 1e-05,
|
19 |
+
"max_position_embeddings": 2048,
|
20 |
+
"model_type": "phi",
|
21 |
+
"num_attention_heads": 32,
|
22 |
+
"num_hidden_layers": 32,
|
23 |
+
"num_key_value_heads": 32,
|
24 |
+
"partial_rotary_factor": 0.4,
|
25 |
+
"qk_layernorm": false,
|
26 |
+
"resid_pdrop": 0.1,
|
27 |
+
"rope_scaling": null,
|
28 |
+
"rope_theta": 10000.0,
|
29 |
+
"tie_word_embeddings": false,
|
30 |
+
"torch_dtype": "bfloat16",
|
31 |
+
"transformers_version": "4.39.1",
|
32 |
+
"use_cache": false,
|
33 |
+
"vocab_size": 50297
|
34 |
+
}
|
checkpoint-1166/generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50295,
|
4 |
+
"eos_token_id": 50296,
|
5 |
+
"pad_token_id": 50296,
|
6 |
+
"transformers_version": "4.39.1"
|
7 |
+
}
|
checkpoint-1166/global_step1166/bf16_zero_pp_rank_0_mp_rank_00_optim_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:838fea68213363dbc95550694f4e0c05fcbd41bdbd1488f007493e686d7beddd
|
3 |
+
size 22200481624
|
checkpoint-1166/global_step1166/zero_pp_rank_0_mp_rank_00_model_states.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fd41625af1bd0d32333bceec127177d84247f6179f856f8cdff9a3ba2d13e382
|
3 |
+
size 214911
|
checkpoint-1166/latest
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
global_step1166
|
checkpoint-1166/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1166/model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7e738b079913369d46164d298ea2383ae644e637d2874c03ab2e5712c151010
|
3 |
+
size 4990961488
|
checkpoint-1166/model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbbe7ec19b53a1fa62bc73fc61c14dd39fd30b1ee3c15d07aa9b47fdd8085443
|
3 |
+
size 559207842
|
checkpoint-1166/model.safetensors.index.json
ADDED
@@ -0,0 +1,460 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 5550119154
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.bias": "model-00002-of-00002.safetensors",
|
7 |
+
"lm_head.weight": "model-00002-of-00002.safetensors",
|
8 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
9 |
+
"model.final_layernorm.bias": "model-00002-of-00002.safetensors",
|
10 |
+
"model.final_layernorm.weight": "model-00002-of-00002.safetensors",
|
11 |
+
"model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
12 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
13 |
+
"model.layers.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
14 |
+
"model.layers.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
15 |
+
"model.layers.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
16 |
+
"model.layers.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
17 |
+
"model.layers.0.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
18 |
+
"model.layers.0.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
19 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
20 |
+
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
21 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
22 |
+
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
23 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
24 |
+
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
25 |
+
"model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
26 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
27 |
+
"model.layers.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
28 |
+
"model.layers.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
29 |
+
"model.layers.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
30 |
+
"model.layers.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
31 |
+
"model.layers.1.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
32 |
+
"model.layers.1.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
33 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
34 |
+
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
35 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
36 |
+
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
37 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
38 |
+
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
39 |
+
"model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
40 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
41 |
+
"model.layers.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
42 |
+
"model.layers.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
43 |
+
"model.layers.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
44 |
+
"model.layers.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
45 |
+
"model.layers.10.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
46 |
+
"model.layers.10.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
47 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
48 |
+
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
49 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
50 |
+
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
51 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
52 |
+
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
53 |
+
"model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
54 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
55 |
+
"model.layers.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
56 |
+
"model.layers.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
57 |
+
"model.layers.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
58 |
+
"model.layers.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
59 |
+
"model.layers.11.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
60 |
+
"model.layers.11.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
61 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
62 |
+
"model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
63 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
64 |
+
"model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
65 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
66 |
+
"model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
67 |
+
"model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
68 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
69 |
+
"model.layers.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
70 |
+
"model.layers.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
71 |
+
"model.layers.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
72 |
+
"model.layers.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
73 |
+
"model.layers.12.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
74 |
+
"model.layers.12.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
75 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
76 |
+
"model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
77 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
78 |
+
"model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
79 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
80 |
+
"model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
81 |
+
"model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
82 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
83 |
+
"model.layers.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
84 |
+
"model.layers.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
85 |
+
"model.layers.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
86 |
+
"model.layers.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
87 |
+
"model.layers.13.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
88 |
+
"model.layers.13.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
89 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
90 |
+
"model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
91 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
92 |
+
"model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
93 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
94 |
+
"model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
95 |
+
"model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
96 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
97 |
+
"model.layers.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
98 |
+
"model.layers.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
99 |
+
"model.layers.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
100 |
+
"model.layers.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
101 |
+
"model.layers.14.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
102 |
+
"model.layers.14.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
103 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
104 |
+
"model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
105 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
106 |
+
"model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
107 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
108 |
+
"model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
109 |
+
"model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
110 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
111 |
+
"model.layers.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
112 |
+
"model.layers.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
113 |
+
"model.layers.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
114 |
+
"model.layers.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
115 |
+
"model.layers.15.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
116 |
+
"model.layers.15.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
117 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
118 |
+
"model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
119 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
120 |
+
"model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
121 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
122 |
+
"model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
123 |
+
"model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
124 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
125 |
+
"model.layers.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
126 |
+
"model.layers.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
127 |
+
"model.layers.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
128 |
+
"model.layers.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
129 |
+
"model.layers.16.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
130 |
+
"model.layers.16.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
131 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
132 |
+
"model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
133 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
134 |
+
"model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
135 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
136 |
+
"model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
137 |
+
"model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
138 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
139 |
+
"model.layers.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
140 |
+
"model.layers.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
141 |
+
"model.layers.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
142 |
+
"model.layers.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
143 |
+
"model.layers.17.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
144 |
+
"model.layers.17.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
145 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
146 |
+
"model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
147 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
148 |
+
"model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
149 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
150 |
+
"model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
151 |
+
"model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
152 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
153 |
+
"model.layers.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
154 |
+
"model.layers.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
155 |
+
"model.layers.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
156 |
+
"model.layers.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
157 |
+
"model.layers.18.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
158 |
+
"model.layers.18.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
159 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
160 |
+
"model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
161 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
162 |
+
"model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
163 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
164 |
+
"model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
165 |
+
"model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
166 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
167 |
+
"model.layers.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
168 |
+
"model.layers.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
169 |
+
"model.layers.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
170 |
+
"model.layers.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
171 |
+
"model.layers.19.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
172 |
+
"model.layers.19.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
173 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
174 |
+
"model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
175 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
176 |
+
"model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
177 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
178 |
+
"model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
179 |
+
"model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
180 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
181 |
+
"model.layers.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
182 |
+
"model.layers.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
183 |
+
"model.layers.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
184 |
+
"model.layers.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
185 |
+
"model.layers.2.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
186 |
+
"model.layers.2.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
187 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
188 |
+
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
189 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
190 |
+
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
191 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
192 |
+
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
193 |
+
"model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
194 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
195 |
+
"model.layers.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
196 |
+
"model.layers.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
197 |
+
"model.layers.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
198 |
+
"model.layers.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
199 |
+
"model.layers.20.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
200 |
+
"model.layers.20.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
201 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
202 |
+
"model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
203 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
204 |
+
"model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
205 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
206 |
+
"model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
207 |
+
"model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
208 |
+
"model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
209 |
+
"model.layers.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
210 |
+
"model.layers.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
211 |
+
"model.layers.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
212 |
+
"model.layers.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
213 |
+
"model.layers.21.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
214 |
+
"model.layers.21.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
215 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
216 |
+
"model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
217 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
218 |
+
"model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
219 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
220 |
+
"model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
221 |
+
"model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
222 |
+
"model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
223 |
+
"model.layers.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
224 |
+
"model.layers.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
225 |
+
"model.layers.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
226 |
+
"model.layers.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
227 |
+
"model.layers.22.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
228 |
+
"model.layers.22.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
229 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
230 |
+
"model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
231 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
232 |
+
"model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
233 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
234 |
+
"model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
235 |
+
"model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
236 |
+
"model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
237 |
+
"model.layers.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
238 |
+
"model.layers.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
239 |
+
"model.layers.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
240 |
+
"model.layers.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
241 |
+
"model.layers.23.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
242 |
+
"model.layers.23.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
243 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
244 |
+
"model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
245 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
246 |
+
"model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
247 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
248 |
+
"model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
249 |
+
"model.layers.24.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
250 |
+
"model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
251 |
+
"model.layers.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
252 |
+
"model.layers.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
253 |
+
"model.layers.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
254 |
+
"model.layers.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
255 |
+
"model.layers.24.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
256 |
+
"model.layers.24.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
257 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
258 |
+
"model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
259 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
260 |
+
"model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
261 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
262 |
+
"model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
263 |
+
"model.layers.25.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
264 |
+
"model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
265 |
+
"model.layers.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
266 |
+
"model.layers.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
267 |
+
"model.layers.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
268 |
+
"model.layers.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
269 |
+
"model.layers.25.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
270 |
+
"model.layers.25.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
271 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
272 |
+
"model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
273 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
274 |
+
"model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
275 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
276 |
+
"model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
277 |
+
"model.layers.26.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
278 |
+
"model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
279 |
+
"model.layers.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
280 |
+
"model.layers.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
281 |
+
"model.layers.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
282 |
+
"model.layers.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
283 |
+
"model.layers.26.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
284 |
+
"model.layers.26.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
285 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
286 |
+
"model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
287 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
288 |
+
"model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
289 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
290 |
+
"model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
291 |
+
"model.layers.27.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
292 |
+
"model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
293 |
+
"model.layers.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
294 |
+
"model.layers.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
295 |
+
"model.layers.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
296 |
+
"model.layers.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
297 |
+
"model.layers.27.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
298 |
+
"model.layers.27.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
299 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
300 |
+
"model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
301 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
302 |
+
"model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
303 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
304 |
+
"model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
305 |
+
"model.layers.28.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
306 |
+
"model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
307 |
+
"model.layers.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
308 |
+
"model.layers.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
309 |
+
"model.layers.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
310 |
+
"model.layers.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
311 |
+
"model.layers.28.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
312 |
+
"model.layers.28.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
313 |
+
"model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
314 |
+
"model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
315 |
+
"model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
316 |
+
"model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
317 |
+
"model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
318 |
+
"model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
319 |
+
"model.layers.29.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
320 |
+
"model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
321 |
+
"model.layers.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
322 |
+
"model.layers.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
323 |
+
"model.layers.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
324 |
+
"model.layers.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
325 |
+
"model.layers.29.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
326 |
+
"model.layers.29.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
327 |
+
"model.layers.29.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
328 |
+
"model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
329 |
+
"model.layers.29.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
330 |
+
"model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
331 |
+
"model.layers.29.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
332 |
+
"model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
333 |
+
"model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
334 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
335 |
+
"model.layers.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
336 |
+
"model.layers.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
337 |
+
"model.layers.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
338 |
+
"model.layers.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
339 |
+
"model.layers.3.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
340 |
+
"model.layers.3.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
341 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
342 |
+
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
343 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
344 |
+
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
345 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
346 |
+
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
347 |
+
"model.layers.30.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
348 |
+
"model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
349 |
+
"model.layers.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
350 |
+
"model.layers.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
351 |
+
"model.layers.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
352 |
+
"model.layers.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
353 |
+
"model.layers.30.self_attn.dense.bias": "model-00002-of-00002.safetensors",
|
354 |
+
"model.layers.30.self_attn.dense.weight": "model-00002-of-00002.safetensors",
|
355 |
+
"model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
356 |
+
"model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
357 |
+
"model.layers.30.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
358 |
+
"model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
359 |
+
"model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
360 |
+
"model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
361 |
+
"model.layers.31.input_layernorm.bias": "model-00002-of-00002.safetensors",
|
362 |
+
"model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
363 |
+
"model.layers.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
364 |
+
"model.layers.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
365 |
+
"model.layers.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
366 |
+
"model.layers.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
367 |
+
"model.layers.31.self_attn.dense.bias": "model-00002-of-00002.safetensors",
|
368 |
+
"model.layers.31.self_attn.dense.weight": "model-00002-of-00002.safetensors",
|
369 |
+
"model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
370 |
+
"model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
|
371 |
+
"model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
372 |
+
"model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
|
373 |
+
"model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
374 |
+
"model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
|
375 |
+
"model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
376 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
377 |
+
"model.layers.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
378 |
+
"model.layers.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
379 |
+
"model.layers.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
380 |
+
"model.layers.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
381 |
+
"model.layers.4.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
382 |
+
"model.layers.4.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
383 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
384 |
+
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
385 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
386 |
+
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
387 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
388 |
+
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
389 |
+
"model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
390 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
391 |
+
"model.layers.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
392 |
+
"model.layers.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
393 |
+
"model.layers.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
394 |
+
"model.layers.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
395 |
+
"model.layers.5.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
396 |
+
"model.layers.5.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
397 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
398 |
+
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
399 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
400 |
+
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
401 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
402 |
+
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
403 |
+
"model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
404 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
405 |
+
"model.layers.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
406 |
+
"model.layers.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
407 |
+
"model.layers.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
408 |
+
"model.layers.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
409 |
+
"model.layers.6.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
410 |
+
"model.layers.6.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
411 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
412 |
+
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
413 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
414 |
+
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
415 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
416 |
+
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
417 |
+
"model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
418 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
419 |
+
"model.layers.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
420 |
+
"model.layers.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
421 |
+
"model.layers.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
422 |
+
"model.layers.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
423 |
+
"model.layers.7.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
424 |
+
"model.layers.7.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
425 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
426 |
+
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
427 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
428 |
+
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
429 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
430 |
+
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
431 |
+
"model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
432 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
433 |
+
"model.layers.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
434 |
+
"model.layers.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
435 |
+
"model.layers.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
436 |
+
"model.layers.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
437 |
+
"model.layers.8.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
438 |
+
"model.layers.8.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
439 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
440 |
+
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
441 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
442 |
+
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
443 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
444 |
+
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
|
445 |
+
"model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
|
446 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
447 |
+
"model.layers.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
448 |
+
"model.layers.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
449 |
+
"model.layers.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
450 |
+
"model.layers.9.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
451 |
+
"model.layers.9.self_attn.dense.bias": "model-00001-of-00002.safetensors",
|
452 |
+
"model.layers.9.self_attn.dense.weight": "model-00001-of-00002.safetensors",
|
453 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
454 |
+
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
|
455 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
456 |
+
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
|
457 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
458 |
+
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors"
|
459 |
+
}
|
460 |
+
}
|
checkpoint-1166/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7c733f603eddfbf8aea2db46dfb96d2d44052ea3c8d772ba82a9011002700581
|
3 |
+
size 14244
|
checkpoint-1166/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f9265eb5f0305f42b366f1f01d33d5d0c69b9271a58777097c906d787d6129cb
|
3 |
+
size 1064
|
checkpoint-1166/special_tokens_map.json
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<|im_start|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|im_end|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"pad_token": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
},
|
27 |
+
"unk_token": {
|
28 |
+
"content": "<|endoftext|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false
|
33 |
+
}
|
34 |
+
}
|
checkpoint-1166/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1166/tokenizer_config.json
ADDED
@@ -0,0 +1,345 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"50257": {
|
13 |
+
"content": " ",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": false
|
19 |
+
},
|
20 |
+
"50258": {
|
21 |
+
"content": " ",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": true,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": false
|
27 |
+
},
|
28 |
+
"50259": {
|
29 |
+
"content": " ",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false,
|
34 |
+
"special": false
|
35 |
+
},
|
36 |
+
"50260": {
|
37 |
+
"content": " ",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": true,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false,
|
42 |
+
"special": false
|
43 |
+
},
|
44 |
+
"50261": {
|
45 |
+
"content": " ",
|
46 |
+
"lstrip": false,
|
47 |
+
"normalized": true,
|
48 |
+
"rstrip": false,
|
49 |
+
"single_word": false,
|
50 |
+
"special": false
|
51 |
+
},
|
52 |
+
"50262": {
|
53 |
+
"content": " ",
|
54 |
+
"lstrip": false,
|
55 |
+
"normalized": true,
|
56 |
+
"rstrip": false,
|
57 |
+
"single_word": false,
|
58 |
+
"special": false
|
59 |
+
},
|
60 |
+
"50263": {
|
61 |
+
"content": " ",
|
62 |
+
"lstrip": false,
|
63 |
+
"normalized": true,
|
64 |
+
"rstrip": false,
|
65 |
+
"single_word": false,
|
66 |
+
"special": false
|
67 |
+
},
|
68 |
+
"50264": {
|
69 |
+
"content": " ",
|
70 |
+
"lstrip": false,
|
71 |
+
"normalized": true,
|
72 |
+
"rstrip": false,
|
73 |
+
"single_word": false,
|
74 |
+
"special": false
|
75 |
+
},
|
76 |
+
"50265": {
|
77 |
+
"content": " ",
|
78 |
+
"lstrip": false,
|
79 |
+
"normalized": true,
|
80 |
+
"rstrip": false,
|
81 |
+
"single_word": false,
|
82 |
+
"special": false
|
83 |
+
},
|
84 |
+
"50266": {
|
85 |
+
"content": " ",
|
86 |
+
"lstrip": false,
|
87 |
+
"normalized": true,
|
88 |
+
"rstrip": false,
|
89 |
+
"single_word": false,
|
90 |
+
"special": false
|
91 |
+
},
|
92 |
+
"50267": {
|
93 |
+
"content": " ",
|
94 |
+
"lstrip": false,
|
95 |
+
"normalized": true,
|
96 |
+
"rstrip": false,
|
97 |
+
"single_word": false,
|
98 |
+
"special": false
|
99 |
+
},
|
100 |
+
"50268": {
|
101 |
+
"content": " ",
|
102 |
+
"lstrip": false,
|
103 |
+
"normalized": true,
|
104 |
+
"rstrip": false,
|
105 |
+
"single_word": false,
|
106 |
+
"special": false
|
107 |
+
},
|
108 |
+
"50269": {
|
109 |
+
"content": " ",
|
110 |
+
"lstrip": false,
|
111 |
+
"normalized": true,
|
112 |
+
"rstrip": false,
|
113 |
+
"single_word": false,
|
114 |
+
"special": false
|
115 |
+
},
|
116 |
+
"50270": {
|
117 |
+
"content": " ",
|
118 |
+
"lstrip": false,
|
119 |
+
"normalized": true,
|
120 |
+
"rstrip": false,
|
121 |
+
"single_word": false,
|
122 |
+
"special": false
|
123 |
+
},
|
124 |
+
"50271": {
|
125 |
+
"content": " ",
|
126 |
+
"lstrip": false,
|
127 |
+
"normalized": true,
|
128 |
+
"rstrip": false,
|
129 |
+
"single_word": false,
|
130 |
+
"special": false
|
131 |
+
},
|
132 |
+
"50272": {
|
133 |
+
"content": " ",
|
134 |
+
"lstrip": false,
|
135 |
+
"normalized": true,
|
136 |
+
"rstrip": false,
|
137 |
+
"single_word": false,
|
138 |
+
"special": false
|
139 |
+
},
|
140 |
+
"50273": {
|
141 |
+
"content": " ",
|
142 |
+
"lstrip": false,
|
143 |
+
"normalized": true,
|
144 |
+
"rstrip": false,
|
145 |
+
"single_word": false,
|
146 |
+
"special": false
|
147 |
+
},
|
148 |
+
"50274": {
|
149 |
+
"content": " ",
|
150 |
+
"lstrip": false,
|
151 |
+
"normalized": true,
|
152 |
+
"rstrip": false,
|
153 |
+
"single_word": false,
|
154 |
+
"special": false
|
155 |
+
},
|
156 |
+
"50275": {
|
157 |
+
"content": " ",
|
158 |
+
"lstrip": false,
|
159 |
+
"normalized": true,
|
160 |
+
"rstrip": false,
|
161 |
+
"single_word": false,
|
162 |
+
"special": false
|
163 |
+
},
|
164 |
+
"50276": {
|
165 |
+
"content": " ",
|
166 |
+
"lstrip": false,
|
167 |
+
"normalized": true,
|
168 |
+
"rstrip": false,
|
169 |
+
"single_word": false,
|
170 |
+
"special": false
|
171 |
+
},
|
172 |
+
"50277": {
|
173 |
+
"content": " ",
|
174 |
+
"lstrip": false,
|
175 |
+
"normalized": true,
|
176 |
+
"rstrip": false,
|
177 |
+
"single_word": false,
|
178 |
+
"special": false
|
179 |
+
},
|
180 |
+
"50278": {
|
181 |
+
"content": " ",
|
182 |
+
"lstrip": false,
|
183 |
+
"normalized": true,
|
184 |
+
"rstrip": false,
|
185 |
+
"single_word": false,
|
186 |
+
"special": false
|
187 |
+
},
|
188 |
+
"50279": {
|
189 |
+
"content": " ",
|
190 |
+
"lstrip": false,
|
191 |
+
"normalized": true,
|
192 |
+
"rstrip": false,
|
193 |
+
"single_word": false,
|
194 |
+
"special": false
|
195 |
+
},
|
196 |
+
"50280": {
|
197 |
+
"content": " ",
|
198 |
+
"lstrip": false,
|
199 |
+
"normalized": true,
|
200 |
+
"rstrip": false,
|
201 |
+
"single_word": false,
|
202 |
+
"special": false
|
203 |
+
},
|
204 |
+
"50281": {
|
205 |
+
"content": " ",
|
206 |
+
"lstrip": false,
|
207 |
+
"normalized": true,
|
208 |
+
"rstrip": false,
|
209 |
+
"single_word": false,
|
210 |
+
"special": false
|
211 |
+
},
|
212 |
+
"50282": {
|
213 |
+
"content": " ",
|
214 |
+
"lstrip": false,
|
215 |
+
"normalized": true,
|
216 |
+
"rstrip": false,
|
217 |
+
"single_word": false,
|
218 |
+
"special": false
|
219 |
+
},
|
220 |
+
"50283": {
|
221 |
+
"content": " ",
|
222 |
+
"lstrip": false,
|
223 |
+
"normalized": true,
|
224 |
+
"rstrip": false,
|
225 |
+
"single_word": false,
|
226 |
+
"special": false
|
227 |
+
},
|
228 |
+
"50284": {
|
229 |
+
"content": " ",
|
230 |
+
"lstrip": false,
|
231 |
+
"normalized": true,
|
232 |
+
"rstrip": false,
|
233 |
+
"single_word": false,
|
234 |
+
"special": false
|
235 |
+
},
|
236 |
+
"50285": {
|
237 |
+
"content": " ",
|
238 |
+
"lstrip": false,
|
239 |
+
"normalized": true,
|
240 |
+
"rstrip": false,
|
241 |
+
"single_word": false,
|
242 |
+
"special": false
|
243 |
+
},
|
244 |
+
"50286": {
|
245 |
+
"content": " ",
|
246 |
+
"lstrip": false,
|
247 |
+
"normalized": true,
|
248 |
+
"rstrip": false,
|
249 |
+
"single_word": false,
|
250 |
+
"special": false
|
251 |
+
},
|
252 |
+
"50287": {
|
253 |
+
"content": "\t\t\t\t\t\t\t\t\t",
|
254 |
+
"lstrip": false,
|
255 |
+
"normalized": true,
|
256 |
+
"rstrip": false,
|
257 |
+
"single_word": false,
|
258 |
+
"special": false
|
259 |
+
},
|
260 |
+
"50288": {
|
261 |
+
"content": "\t\t\t\t\t\t\t\t",
|
262 |
+
"lstrip": false,
|
263 |
+
"normalized": true,
|
264 |
+
"rstrip": false,
|
265 |
+
"single_word": false,
|
266 |
+
"special": false
|
267 |
+
},
|
268 |
+
"50289": {
|
269 |
+
"content": "\t\t\t\t\t\t\t",
|
270 |
+
"lstrip": false,
|
271 |
+
"normalized": true,
|
272 |
+
"rstrip": false,
|
273 |
+
"single_word": false,
|
274 |
+
"special": false
|
275 |
+
},
|
276 |
+
"50290": {
|
277 |
+
"content": "\t\t\t\t\t\t",
|
278 |
+
"lstrip": false,
|
279 |
+
"normalized": true,
|
280 |
+
"rstrip": false,
|
281 |
+
"single_word": false,
|
282 |
+
"special": false
|
283 |
+
},
|
284 |
+
"50291": {
|
285 |
+
"content": "\t\t\t\t\t",
|
286 |
+
"lstrip": false,
|
287 |
+
"normalized": true,
|
288 |
+
"rstrip": false,
|
289 |
+
"single_word": false,
|
290 |
+
"special": false
|
291 |
+
},
|
292 |
+
"50292": {
|
293 |
+
"content": "\t\t\t\t",
|
294 |
+
"lstrip": false,
|
295 |
+
"normalized": true,
|
296 |
+
"rstrip": false,
|
297 |
+
"single_word": false,
|
298 |
+
"special": false
|
299 |
+
},
|
300 |
+
"50293": {
|
301 |
+
"content": "\t\t\t",
|
302 |
+
"lstrip": false,
|
303 |
+
"normalized": true,
|
304 |
+
"rstrip": false,
|
305 |
+
"single_word": false,
|
306 |
+
"special": false
|
307 |
+
},
|
308 |
+
"50294": {
|
309 |
+
"content": "\t\t",
|
310 |
+
"lstrip": false,
|
311 |
+
"normalized": true,
|
312 |
+
"rstrip": false,
|
313 |
+
"single_word": false,
|
314 |
+
"special": false
|
315 |
+
},
|
316 |
+
"50295": {
|
317 |
+
"content": "<|im_start|>",
|
318 |
+
"lstrip": false,
|
319 |
+
"normalized": false,
|
320 |
+
"rstrip": false,
|
321 |
+
"single_word": false,
|
322 |
+
"special": true
|
323 |
+
},
|
324 |
+
"50296": {
|
325 |
+
"content": "<|im_end|>",
|
326 |
+
"lstrip": false,
|
327 |
+
"normalized": false,
|
328 |
+
"rstrip": false,
|
329 |
+
"single_word": false,
|
330 |
+
"special": true
|
331 |
+
}
|
332 |
+
},
|
333 |
+
"additional_special_tokens": [
|
334 |
+
"<|im_start|>",
|
335 |
+
"<|im_end|>"
|
336 |
+
],
|
337 |
+
"bos_token": "<|im_start|>",
|
338 |
+
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
339 |
+
"clean_up_tokenization_spaces": true,
|
340 |
+
"eos_token": "<|im_end|>",
|
341 |
+
"model_max_length": 2048,
|
342 |
+
"pad_token": "<|im_end|>",
|
343 |
+
"tokenizer_class": "CodeGenTokenizer",
|
344 |
+
"unk_token": "<|endoftext|>"
|
345 |
+
}
|
checkpoint-1166/trainer_state.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1166/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16846856f3be552e96317acc5f6c7f4807f2267811c8b8fcdd0537d2e451ee0d
|
3 |
+
size 6392
|
checkpoint-1166/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-1166/zero_to_fp32.py
ADDED
@@ -0,0 +1,587 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
#!/usr/bin/env python
|
2 |
+
|
3 |
+
# Copyright (c) Microsoft Corporation.
|
4 |
+
# SPDX-License-Identifier: Apache-2.0
|
5 |
+
|
6 |
+
# DeepSpeed Team
|
7 |
+
|
8 |
+
# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
|
9 |
+
# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
|
10 |
+
# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
|
11 |
+
# application.
|
12 |
+
#
|
13 |
+
# example: python zero_to_fp32.py . pytorch_model.bin
|
14 |
+
|
15 |
+
import argparse
|
16 |
+
import torch
|
17 |
+
import glob
|
18 |
+
import math
|
19 |
+
import os
|
20 |
+
import re
|
21 |
+
from collections import OrderedDict
|
22 |
+
from dataclasses import dataclass
|
23 |
+
|
24 |
+
# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
|
25 |
+
# DeepSpeed data structures it has to be available in the current python environment.
|
26 |
+
from deepspeed.utils import logger
|
27 |
+
from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
|
28 |
+
FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
|
29 |
+
FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
|
30 |
+
|
31 |
+
|
32 |
+
@dataclass
|
33 |
+
class zero_model_state:
|
34 |
+
buffers: dict()
|
35 |
+
param_shapes: dict()
|
36 |
+
shared_params: list
|
37 |
+
ds_version: int
|
38 |
+
frozen_param_shapes: dict()
|
39 |
+
frozen_param_fragments: dict()
|
40 |
+
|
41 |
+
|
42 |
+
debug = 0
|
43 |
+
|
44 |
+
# load to cpu
|
45 |
+
device = torch.device('cpu')
|
46 |
+
|
47 |
+
|
48 |
+
def atoi(text):
|
49 |
+
return int(text) if text.isdigit() else text
|
50 |
+
|
51 |
+
|
52 |
+
def natural_keys(text):
|
53 |
+
'''
|
54 |
+
alist.sort(key=natural_keys) sorts in human order
|
55 |
+
http://nedbatchelder.com/blog/200712/human_sorting.html
|
56 |
+
(See Toothy's implementation in the comments)
|
57 |
+
'''
|
58 |
+
return [atoi(c) for c in re.split(r'(\d+)', text)]
|
59 |
+
|
60 |
+
|
61 |
+
def get_model_state_file(checkpoint_dir, zero_stage):
|
62 |
+
if not os.path.isdir(checkpoint_dir):
|
63 |
+
raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
|
64 |
+
|
65 |
+
# there should be only one file
|
66 |
+
if zero_stage <= 2:
|
67 |
+
file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
|
68 |
+
elif zero_stage == 3:
|
69 |
+
file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
|
70 |
+
|
71 |
+
if not os.path.exists(file):
|
72 |
+
raise FileNotFoundError(f"can't find model states file at '{file}'")
|
73 |
+
|
74 |
+
return file
|
75 |
+
|
76 |
+
|
77 |
+
def get_checkpoint_files(checkpoint_dir, glob_pattern):
|
78 |
+
# XXX: need to test that this simple glob rule works for multi-node setup too
|
79 |
+
ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
|
80 |
+
|
81 |
+
if len(ckpt_files) == 0:
|
82 |
+
raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
|
83 |
+
|
84 |
+
return ckpt_files
|
85 |
+
|
86 |
+
|
87 |
+
def get_optim_files(checkpoint_dir):
|
88 |
+
return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
|
89 |
+
|
90 |
+
|
91 |
+
def get_model_state_files(checkpoint_dir):
|
92 |
+
return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
|
93 |
+
|
94 |
+
|
95 |
+
def parse_model_states(files):
|
96 |
+
zero_model_states = []
|
97 |
+
for file in files:
|
98 |
+
state_dict = torch.load(file, map_location=device)
|
99 |
+
|
100 |
+
if BUFFER_NAMES not in state_dict:
|
101 |
+
raise ValueError(f"{file} is not a model state checkpoint")
|
102 |
+
buffer_names = state_dict[BUFFER_NAMES]
|
103 |
+
if debug:
|
104 |
+
print("Found buffers:", buffer_names)
|
105 |
+
|
106 |
+
# recover just the buffers while restoring them to fp32 if they were saved in fp16
|
107 |
+
buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
|
108 |
+
param_shapes = state_dict[PARAM_SHAPES]
|
109 |
+
|
110 |
+
# collect parameters that are included in param_shapes
|
111 |
+
param_names = []
|
112 |
+
for s in param_shapes:
|
113 |
+
for name in s.keys():
|
114 |
+
param_names.append(name)
|
115 |
+
|
116 |
+
# update with frozen parameters
|
117 |
+
frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
|
118 |
+
if frozen_param_shapes is not None:
|
119 |
+
if debug:
|
120 |
+
print(f"Found frozen_param_shapes: {frozen_param_shapes}")
|
121 |
+
param_names += list(frozen_param_shapes.keys())
|
122 |
+
|
123 |
+
# handle shared params
|
124 |
+
shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
|
125 |
+
|
126 |
+
ds_version = state_dict.get(DS_VERSION, None)
|
127 |
+
|
128 |
+
frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
|
129 |
+
|
130 |
+
z_model_state = zero_model_state(buffers=buffers,
|
131 |
+
param_shapes=param_shapes,
|
132 |
+
shared_params=shared_params,
|
133 |
+
ds_version=ds_version,
|
134 |
+
frozen_param_shapes=frozen_param_shapes,
|
135 |
+
frozen_param_fragments=frozen_param_fragments)
|
136 |
+
zero_model_states.append(z_model_state)
|
137 |
+
|
138 |
+
return zero_model_states
|
139 |
+
|
140 |
+
|
141 |
+
def parse_optim_states(files, ds_checkpoint_dir):
|
142 |
+
|
143 |
+
total_files = len(files)
|
144 |
+
state_dicts = []
|
145 |
+
for f in files:
|
146 |
+
state_dict = torch.load(f, map_location=device)
|
147 |
+
# immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
|
148 |
+
# and also handle the case where it was already removed by another helper script
|
149 |
+
state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
|
150 |
+
state_dicts.append(state_dict)
|
151 |
+
|
152 |
+
if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
|
153 |
+
raise ValueError(f"{files[0]} is not a zero checkpoint")
|
154 |
+
zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
|
155 |
+
world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
|
156 |
+
|
157 |
+
# For ZeRO-2 each param group can have different partition_count as data parallelism for expert
|
158 |
+
# parameters can be different from data parallelism for non-expert parameters. So we can just
|
159 |
+
# use the max of the partition_count to get the dp world_size.
|
160 |
+
|
161 |
+
if type(world_size) is list:
|
162 |
+
world_size = max(world_size)
|
163 |
+
|
164 |
+
if world_size != total_files:
|
165 |
+
raise ValueError(
|
166 |
+
f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
|
167 |
+
"Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
|
168 |
+
)
|
169 |
+
|
170 |
+
# the groups are named differently in each stage
|
171 |
+
if zero_stage <= 2:
|
172 |
+
fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
|
173 |
+
elif zero_stage == 3:
|
174 |
+
fp32_groups_key = FP32_FLAT_GROUPS
|
175 |
+
else:
|
176 |
+
raise ValueError(f"unknown zero stage {zero_stage}")
|
177 |
+
|
178 |
+
if zero_stage <= 2:
|
179 |
+
fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
|
180 |
+
elif zero_stage == 3:
|
181 |
+
# if there is more than one param group, there will be multiple flattened tensors - one
|
182 |
+
# flattened tensor per group - for simplicity merge them into a single tensor
|
183 |
+
#
|
184 |
+
# XXX: could make the script more memory efficient for when there are multiple groups - it
|
185 |
+
# will require matching the sub-lists of param_shapes for each param group flattened tensor
|
186 |
+
|
187 |
+
fp32_flat_groups = [
|
188 |
+
torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
|
189 |
+
]
|
190 |
+
|
191 |
+
return zero_stage, world_size, fp32_flat_groups
|
192 |
+
|
193 |
+
|
194 |
+
def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir):
|
195 |
+
"""
|
196 |
+
Returns fp32 state_dict reconstructed from ds checkpoint
|
197 |
+
|
198 |
+
Args:
|
199 |
+
- ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
|
200 |
+
|
201 |
+
"""
|
202 |
+
print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
|
203 |
+
|
204 |
+
optim_files = get_optim_files(ds_checkpoint_dir)
|
205 |
+
zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
|
206 |
+
print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
|
207 |
+
|
208 |
+
model_files = get_model_state_files(ds_checkpoint_dir)
|
209 |
+
|
210 |
+
zero_model_states = parse_model_states(model_files)
|
211 |
+
print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
|
212 |
+
|
213 |
+
if zero_stage <= 2:
|
214 |
+
return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
215 |
+
elif zero_stage == 3:
|
216 |
+
return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states)
|
217 |
+
|
218 |
+
|
219 |
+
def _zero2_merge_frozen_params(state_dict, zero_model_states):
|
220 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
221 |
+
return
|
222 |
+
|
223 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
224 |
+
frozen_param_fragments = zero_model_states[0].frozen_param_fragments
|
225 |
+
|
226 |
+
if debug:
|
227 |
+
num_elem = sum(s.numel() for s in frozen_param_shapes.values())
|
228 |
+
print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
229 |
+
|
230 |
+
wanted_params = len(frozen_param_shapes)
|
231 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
232 |
+
avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
|
233 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
234 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
235 |
+
|
236 |
+
total_params = 0
|
237 |
+
total_numel = 0
|
238 |
+
for name, shape in frozen_param_shapes.items():
|
239 |
+
total_params += 1
|
240 |
+
unpartitioned_numel = shape.numel()
|
241 |
+
total_numel += unpartitioned_numel
|
242 |
+
|
243 |
+
state_dict[name] = frozen_param_fragments[name]
|
244 |
+
|
245 |
+
if debug:
|
246 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
247 |
+
|
248 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
249 |
+
|
250 |
+
|
251 |
+
def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
252 |
+
param_shapes = zero_model_states[0].param_shapes
|
253 |
+
|
254 |
+
# Reconstruction protocol:
|
255 |
+
#
|
256 |
+
# XXX: document this
|
257 |
+
|
258 |
+
if debug:
|
259 |
+
for i in range(world_size):
|
260 |
+
for j in range(len(fp32_flat_groups[0])):
|
261 |
+
print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
|
262 |
+
|
263 |
+
# XXX: memory usage doubles here (zero2)
|
264 |
+
num_param_groups = len(fp32_flat_groups[0])
|
265 |
+
merged_single_partition_of_fp32_groups = []
|
266 |
+
for i in range(num_param_groups):
|
267 |
+
merged_partitions = [sd[i] for sd in fp32_flat_groups]
|
268 |
+
full_single_fp32_vector = torch.cat(merged_partitions, 0)
|
269 |
+
merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
|
270 |
+
avail_numel = sum(
|
271 |
+
[full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
|
272 |
+
|
273 |
+
if debug:
|
274 |
+
wanted_params = sum([len(shapes) for shapes in param_shapes])
|
275 |
+
wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
|
276 |
+
# not asserting if there is a mismatch due to possible padding
|
277 |
+
print(f"Have {avail_numel} numels to process.")
|
278 |
+
print(f"Need {wanted_numel} numels in {wanted_params} params.")
|
279 |
+
|
280 |
+
# params
|
281 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
282 |
+
# out-of-core computing solution
|
283 |
+
total_numel = 0
|
284 |
+
total_params = 0
|
285 |
+
for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
|
286 |
+
offset = 0
|
287 |
+
avail_numel = full_single_fp32_vector.numel()
|
288 |
+
for name, shape in shapes.items():
|
289 |
+
|
290 |
+
unpartitioned_numel = shape.numel()
|
291 |
+
total_numel += unpartitioned_numel
|
292 |
+
total_params += 1
|
293 |
+
|
294 |
+
if debug:
|
295 |
+
print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
|
296 |
+
state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
|
297 |
+
offset += unpartitioned_numel
|
298 |
+
|
299 |
+
# Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
|
300 |
+
# avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
|
301 |
+
# paddings performed in the code it's almost impossible to predict the exact numbers w/o the
|
302 |
+
# live optimizer object, so we are checking that the numbers are within the right range
|
303 |
+
align_to = 2 * world_size
|
304 |
+
|
305 |
+
def zero2_align(x):
|
306 |
+
return align_to * math.ceil(x / align_to)
|
307 |
+
|
308 |
+
if debug:
|
309 |
+
print(f"original offset={offset}, avail_numel={avail_numel}")
|
310 |
+
|
311 |
+
offset = zero2_align(offset)
|
312 |
+
avail_numel = zero2_align(avail_numel)
|
313 |
+
|
314 |
+
if debug:
|
315 |
+
print(f"aligned offset={offset}, avail_numel={avail_numel}")
|
316 |
+
|
317 |
+
# Sanity check
|
318 |
+
if offset != avail_numel:
|
319 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
320 |
+
|
321 |
+
print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
|
322 |
+
|
323 |
+
|
324 |
+
def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
325 |
+
state_dict = OrderedDict()
|
326 |
+
|
327 |
+
# buffers
|
328 |
+
buffers = zero_model_states[0].buffers
|
329 |
+
state_dict.update(buffers)
|
330 |
+
if debug:
|
331 |
+
print(f"added {len(buffers)} buffers")
|
332 |
+
|
333 |
+
_zero2_merge_frozen_params(state_dict, zero_model_states)
|
334 |
+
|
335 |
+
_zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
336 |
+
|
337 |
+
# recover shared parameters
|
338 |
+
for pair in zero_model_states[0].shared_params:
|
339 |
+
if pair[1] in state_dict:
|
340 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
341 |
+
|
342 |
+
return state_dict
|
343 |
+
|
344 |
+
|
345 |
+
def zero3_partitioned_param_info(unpartitioned_numel, world_size):
|
346 |
+
remainder = unpartitioned_numel % world_size
|
347 |
+
padding_numel = (world_size - remainder) if remainder else 0
|
348 |
+
partitioned_numel = math.ceil(unpartitioned_numel / world_size)
|
349 |
+
return partitioned_numel, padding_numel
|
350 |
+
|
351 |
+
|
352 |
+
def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
|
353 |
+
if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
|
354 |
+
return
|
355 |
+
|
356 |
+
if debug:
|
357 |
+
for i in range(world_size):
|
358 |
+
num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
|
359 |
+
print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
|
360 |
+
|
361 |
+
frozen_param_shapes = zero_model_states[0].frozen_param_shapes
|
362 |
+
wanted_params = len(frozen_param_shapes)
|
363 |
+
wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
|
364 |
+
avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
|
365 |
+
print(f'Frozen params: Have {avail_numel} numels to process.')
|
366 |
+
print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
|
367 |
+
|
368 |
+
total_params = 0
|
369 |
+
total_numel = 0
|
370 |
+
for name, shape in zero_model_states[0].frozen_param_shapes.items():
|
371 |
+
total_params += 1
|
372 |
+
unpartitioned_numel = shape.numel()
|
373 |
+
total_numel += unpartitioned_numel
|
374 |
+
|
375 |
+
param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
|
376 |
+
state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
|
377 |
+
|
378 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
379 |
+
|
380 |
+
if debug:
|
381 |
+
print(
|
382 |
+
f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
383 |
+
)
|
384 |
+
|
385 |
+
print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
|
386 |
+
|
387 |
+
|
388 |
+
def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
|
389 |
+
param_shapes = zero_model_states[0].param_shapes
|
390 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
391 |
+
# Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
|
392 |
+
# param, re-consolidating each param, while dealing with padding if any
|
393 |
+
|
394 |
+
# merge list of dicts, preserving order
|
395 |
+
param_shapes = {k: v for d in param_shapes for k, v in d.items()}
|
396 |
+
|
397 |
+
if debug:
|
398 |
+
for i in range(world_size):
|
399 |
+
print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
|
400 |
+
|
401 |
+
wanted_params = len(param_shapes)
|
402 |
+
wanted_numel = sum(shape.numel() for shape in param_shapes.values())
|
403 |
+
# not asserting if there is a mismatch due to possible padding
|
404 |
+
avail_numel = fp32_flat_groups[0].numel() * world_size
|
405 |
+
print(f"Trainable params: Have {avail_numel} numels to process.")
|
406 |
+
print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
|
407 |
+
|
408 |
+
# params
|
409 |
+
# XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
|
410 |
+
# out-of-core computing solution
|
411 |
+
offset = 0
|
412 |
+
total_numel = 0
|
413 |
+
total_params = 0
|
414 |
+
for name, shape in param_shapes.items():
|
415 |
+
|
416 |
+
unpartitioned_numel = shape.numel()
|
417 |
+
total_numel += unpartitioned_numel
|
418 |
+
total_params += 1
|
419 |
+
|
420 |
+
partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
|
421 |
+
|
422 |
+
if debug:
|
423 |
+
print(
|
424 |
+
f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
|
425 |
+
)
|
426 |
+
|
427 |
+
# XXX: memory usage doubles here
|
428 |
+
state_dict[name] = torch.cat(
|
429 |
+
tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
|
430 |
+
0).narrow(0, 0, unpartitioned_numel).view(shape)
|
431 |
+
offset += partitioned_numel
|
432 |
+
|
433 |
+
offset *= world_size
|
434 |
+
|
435 |
+
# Sanity check
|
436 |
+
if offset != avail_numel:
|
437 |
+
raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
|
438 |
+
|
439 |
+
print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
|
440 |
+
|
441 |
+
|
442 |
+
def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states):
|
443 |
+
state_dict = OrderedDict()
|
444 |
+
|
445 |
+
# buffers
|
446 |
+
buffers = zero_model_states[0].buffers
|
447 |
+
state_dict.update(buffers)
|
448 |
+
if debug:
|
449 |
+
print(f"added {len(buffers)} buffers")
|
450 |
+
|
451 |
+
_zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
|
452 |
+
|
453 |
+
_zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
|
454 |
+
|
455 |
+
# recover shared parameters
|
456 |
+
for pair in zero_model_states[0].shared_params:
|
457 |
+
if pair[1] in state_dict:
|
458 |
+
state_dict[pair[0]] = state_dict[pair[1]]
|
459 |
+
|
460 |
+
return state_dict
|
461 |
+
|
462 |
+
|
463 |
+
def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None):
|
464 |
+
"""
|
465 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
|
466 |
+
``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
|
467 |
+
via a model hub.
|
468 |
+
|
469 |
+
Args:
|
470 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder
|
471 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
|
472 |
+
|
473 |
+
Returns:
|
474 |
+
- pytorch ``state_dict``
|
475 |
+
|
476 |
+
Note: this approach may not work if your application doesn't have sufficient free CPU memory and
|
477 |
+
you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
|
478 |
+
the checkpoint.
|
479 |
+
|
480 |
+
A typical usage might be ::
|
481 |
+
|
482 |
+
from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
|
483 |
+
# do the training and checkpoint saving
|
484 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
|
485 |
+
model = model.cpu() # move to cpu
|
486 |
+
model.load_state_dict(state_dict)
|
487 |
+
# submit to model hub or save the model to share with others
|
488 |
+
|
489 |
+
In this example the ``model`` will no longer be usable in the deepspeed context of the same
|
490 |
+
application. i.e. you will need to re-initialize the deepspeed engine, since
|
491 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
492 |
+
|
493 |
+
If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
|
494 |
+
|
495 |
+
"""
|
496 |
+
if tag is None:
|
497 |
+
latest_path = os.path.join(checkpoint_dir, 'latest')
|
498 |
+
if os.path.isfile(latest_path):
|
499 |
+
with open(latest_path, 'r') as fd:
|
500 |
+
tag = fd.read().strip()
|
501 |
+
else:
|
502 |
+
raise ValueError(f"Unable to find 'latest' file at {latest_path}")
|
503 |
+
|
504 |
+
ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
|
505 |
+
|
506 |
+
if not os.path.isdir(ds_checkpoint_dir):
|
507 |
+
raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
|
508 |
+
|
509 |
+
return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir)
|
510 |
+
|
511 |
+
|
512 |
+
def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir, output_file, tag=None):
|
513 |
+
"""
|
514 |
+
Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
|
515 |
+
loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
|
516 |
+
|
517 |
+
Args:
|
518 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
519 |
+
- ``output_file``: path to the pytorch fp32 state_dict output file (e.g. path/pytorch_model.bin)
|
520 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
521 |
+
"""
|
522 |
+
|
523 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
524 |
+
print(f"Saving fp32 state dict to {output_file}")
|
525 |
+
torch.save(state_dict, output_file)
|
526 |
+
|
527 |
+
|
528 |
+
def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
|
529 |
+
"""
|
530 |
+
1. Put the provided model to cpu
|
531 |
+
2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
|
532 |
+
3. Load it into the provided model
|
533 |
+
|
534 |
+
Args:
|
535 |
+
- ``model``: the model object to update
|
536 |
+
- ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
|
537 |
+
- ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
|
538 |
+
|
539 |
+
Returns:
|
540 |
+
- ``model`: modified model
|
541 |
+
|
542 |
+
Make sure you have plenty of CPU memory available before you call this function. If you don't
|
543 |
+
have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
|
544 |
+
conveniently placed for you in the checkpoint folder.
|
545 |
+
|
546 |
+
A typical usage might be ::
|
547 |
+
|
548 |
+
from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
|
549 |
+
model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
|
550 |
+
# submit to model hub or save the model to share with others
|
551 |
+
|
552 |
+
Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
|
553 |
+
of the same application. i.e. you will need to re-initialize the deepspeed engine, since
|
554 |
+
``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
|
555 |
+
|
556 |
+
"""
|
557 |
+
logger.info(f"Extracting fp32 weights")
|
558 |
+
state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
|
559 |
+
|
560 |
+
logger.info(f"Overwriting model with fp32 weights")
|
561 |
+
model = model.cpu()
|
562 |
+
model.load_state_dict(state_dict, strict=False)
|
563 |
+
|
564 |
+
return model
|
565 |
+
|
566 |
+
|
567 |
+
if __name__ == "__main__":
|
568 |
+
|
569 |
+
parser = argparse.ArgumentParser()
|
570 |
+
parser.add_argument("checkpoint_dir",
|
571 |
+
type=str,
|
572 |
+
help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
|
573 |
+
parser.add_argument(
|
574 |
+
"output_file",
|
575 |
+
type=str,
|
576 |
+
help="path to the pytorch fp32 state_dict output file (e.g. path/checkpoint-12/pytorch_model.bin)")
|
577 |
+
parser.add_argument("-t",
|
578 |
+
"--tag",
|
579 |
+
type=str,
|
580 |
+
default=None,
|
581 |
+
help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
|
582 |
+
parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
|
583 |
+
args = parser.parse_args()
|
584 |
+
|
585 |
+
debug = args.debug
|
586 |
+
|
587 |
+
convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir, args.output_file, tag=args.tag)
|