Upload folder using huggingface_hub
Browse files- README.md +9 -0
- adapter_config.json +21 -0
- adapter_model.bin +3 -0
- added_tokens.json +3 -0
- checkpoint-36/README.md +34 -0
- checkpoint-36/adapter_config.json +21 -0
- checkpoint-36/adapter_model.bin +3 -0
- checkpoint-36/added_tokens.json +3 -0
- checkpoint-36/optimizer.pt +3 -0
- checkpoint-36/pytorch_model.bin +3 -0
- checkpoint-36/rng_state.pth +3 -0
- checkpoint-36/scheduler.pt +3 -0
- checkpoint-36/special_tokens_map.json +24 -0
- checkpoint-36/tokenizer.json +0 -0
- checkpoint-36/tokenizer.model +3 -0
- checkpoint-36/tokenizer_config.json +32 -0
- checkpoint-36/trainer_state.json +235 -0
- checkpoint-36/training_args.bin +3 -0
- config.json +26 -0
- pytorch_model-00001-of-00002.bin +3 -0
- pytorch_model-00002-of-00002.bin +3 -0
- pytorch_model.bin.index.json +298 -0
- runs/Aug12_03-16-59_132de5da0894/events.out.tfevents.1691810219.132de5da0894.3365.0 +3 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +32 -0
- training_args.bin +3 -0
- training_params.json +41 -0
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation
|
5 |
+
widget:
|
6 |
+
- text: "I love AutoTrain because "
|
7 |
+
---
|
8 |
+
|
9 |
+
# Model Trained Using AutoTrain
|
adapter_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 16,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"v_proj"
|
19 |
+
],
|
20 |
+
"task_type": "CAUSAL_LM"
|
21 |
+
}
|
adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce083e3a8713a8563dea449893e87a2d4a1de11f5b95f7d0d768744794eeaf57
|
3 |
+
size 33600461
|
added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 32000
|
3 |
+
}
|
checkpoint-36/README.md
ADDED
@@ -0,0 +1,34 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
---
|
4 |
+
## Training procedure
|
5 |
+
|
6 |
+
|
7 |
+
The following `bitsandbytes` quantization config was used during training:
|
8 |
+
- quant_method: bitsandbytes
|
9 |
+
- load_in_8bit: False
|
10 |
+
- load_in_4bit: True
|
11 |
+
- llm_int8_threshold: 6.0
|
12 |
+
- llm_int8_skip_modules: None
|
13 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
14 |
+
- llm_int8_has_fp16_weight: False
|
15 |
+
- bnb_4bit_quant_type: nf4
|
16 |
+
- bnb_4bit_use_double_quant: False
|
17 |
+
- bnb_4bit_compute_dtype: float16
|
18 |
+
|
19 |
+
The following `bitsandbytes` quantization config was used during training:
|
20 |
+
- quant_method: bitsandbytes
|
21 |
+
- load_in_8bit: False
|
22 |
+
- load_in_4bit: True
|
23 |
+
- llm_int8_threshold: 6.0
|
24 |
+
- llm_int8_skip_modules: None
|
25 |
+
- llm_int8_enable_fp32_cpu_offload: False
|
26 |
+
- llm_int8_has_fp16_weight: False
|
27 |
+
- bnb_4bit_quant_type: nf4
|
28 |
+
- bnb_4bit_use_double_quant: False
|
29 |
+
- bnb_4bit_compute_dtype: float16
|
30 |
+
### Framework versions
|
31 |
+
|
32 |
+
- PEFT 0.5.0.dev0
|
33 |
+
|
34 |
+
- PEFT 0.5.0.dev0
|
checkpoint-36/adapter_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
|
4 |
+
"bias": "none",
|
5 |
+
"fan_in_fan_out": false,
|
6 |
+
"inference_mode": true,
|
7 |
+
"init_lora_weights": true,
|
8 |
+
"layers_pattern": null,
|
9 |
+
"layers_to_transform": null,
|
10 |
+
"lora_alpha": 32,
|
11 |
+
"lora_dropout": 0.05,
|
12 |
+
"modules_to_save": null,
|
13 |
+
"peft_type": "LORA",
|
14 |
+
"r": 16,
|
15 |
+
"revision": null,
|
16 |
+
"target_modules": [
|
17 |
+
"q_proj",
|
18 |
+
"v_proj"
|
19 |
+
],
|
20 |
+
"task_type": "CAUSAL_LM"
|
21 |
+
}
|
checkpoint-36/adapter_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce083e3a8713a8563dea449893e87a2d4a1de11f5b95f7d0d768744794eeaf57
|
3 |
+
size 33600461
|
checkpoint-36/added_tokens.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<pad>": 32000
|
3 |
+
}
|
checkpoint-36/optimizer.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a7ed950ce3e270028c05f6558e4407c477a375a965d42287a71b856cc6e9457c
|
3 |
+
size 67216581
|
checkpoint-36/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c152074a486243089e4fc0fdee0a373a30fb0e0a6e40eb5fd0d36fdafc97a155
|
3 |
+
size 443
|
checkpoint-36/rng_state.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0f7a168e2ed6a4af01a06d43d583e588db4602319d85d184e8f9b9422e210f8f
|
3 |
+
size 14575
|
checkpoint-36/scheduler.pt
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:69129a29db99fc925a77309eb1077129de3041280db585b2bec9634d06809196
|
3 |
+
size 627
|
checkpoint-36/special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
checkpoint-36/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
checkpoint-36/tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
checkpoint-36/tokenizer_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"__type": "AddedToken",
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
"clean_up_tokenization_spaces": false,
|
11 |
+
"eos_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "</s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"legacy": false,
|
20 |
+
"model_max_length": 1024,
|
21 |
+
"pad_token": null,
|
22 |
+
"sp_model_kwargs": {},
|
23 |
+
"tokenizer_class": "LlamaTokenizer",
|
24 |
+
"unk_token": {
|
25 |
+
"__type": "AddedToken",
|
26 |
+
"content": "<unk>",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": true,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
}
|
32 |
+
}
|
checkpoint-36/trainer_state.json
ADDED
@@ -0,0 +1,235 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"best_metric": null,
|
3 |
+
"best_model_checkpoint": null,
|
4 |
+
"epoch": 9.0,
|
5 |
+
"eval_steps": 500,
|
6 |
+
"global_step": 36,
|
7 |
+
"is_hyper_param_search": false,
|
8 |
+
"is_local_process_zero": true,
|
9 |
+
"is_world_process_zero": true,
|
10 |
+
"log_history": [
|
11 |
+
{
|
12 |
+
"epoch": 0.25,
|
13 |
+
"learning_rate": 5e-05,
|
14 |
+
"loss": 2.4988,
|
15 |
+
"step": 1
|
16 |
+
},
|
17 |
+
{
|
18 |
+
"epoch": 0.5,
|
19 |
+
"learning_rate": 0.0001,
|
20 |
+
"loss": 2.9302,
|
21 |
+
"step": 2
|
22 |
+
},
|
23 |
+
{
|
24 |
+
"epoch": 0.75,
|
25 |
+
"learning_rate": 0.00015000000000000001,
|
26 |
+
"loss": 2.8645,
|
27 |
+
"step": 3
|
28 |
+
},
|
29 |
+
{
|
30 |
+
"epoch": 1.0,
|
31 |
+
"learning_rate": 0.0002,
|
32 |
+
"loss": 2.6333,
|
33 |
+
"step": 4
|
34 |
+
},
|
35 |
+
{
|
36 |
+
"epoch": 1.25,
|
37 |
+
"learning_rate": 0.00019375000000000002,
|
38 |
+
"loss": 2.8102,
|
39 |
+
"step": 5
|
40 |
+
},
|
41 |
+
{
|
42 |
+
"epoch": 1.5,
|
43 |
+
"learning_rate": 0.0001875,
|
44 |
+
"loss": 2.5731,
|
45 |
+
"step": 6
|
46 |
+
},
|
47 |
+
{
|
48 |
+
"epoch": 1.75,
|
49 |
+
"learning_rate": 0.00018125000000000001,
|
50 |
+
"loss": 2.6083,
|
51 |
+
"step": 7
|
52 |
+
},
|
53 |
+
{
|
54 |
+
"epoch": 2.0,
|
55 |
+
"learning_rate": 0.000175,
|
56 |
+
"loss": 2.7983,
|
57 |
+
"step": 8
|
58 |
+
},
|
59 |
+
{
|
60 |
+
"epoch": 2.25,
|
61 |
+
"learning_rate": 0.00016875,
|
62 |
+
"loss": 2.6725,
|
63 |
+
"step": 9
|
64 |
+
},
|
65 |
+
{
|
66 |
+
"epoch": 2.5,
|
67 |
+
"learning_rate": 0.00016250000000000002,
|
68 |
+
"loss": 2.5018,
|
69 |
+
"step": 10
|
70 |
+
},
|
71 |
+
{
|
72 |
+
"epoch": 2.75,
|
73 |
+
"learning_rate": 0.00015625,
|
74 |
+
"loss": 2.7047,
|
75 |
+
"step": 11
|
76 |
+
},
|
77 |
+
{
|
78 |
+
"epoch": 3.0,
|
79 |
+
"learning_rate": 0.00015000000000000001,
|
80 |
+
"loss": 2.5548,
|
81 |
+
"step": 12
|
82 |
+
},
|
83 |
+
{
|
84 |
+
"epoch": 3.25,
|
85 |
+
"learning_rate": 0.00014375,
|
86 |
+
"loss": 2.5345,
|
87 |
+
"step": 13
|
88 |
+
},
|
89 |
+
{
|
90 |
+
"epoch": 3.5,
|
91 |
+
"learning_rate": 0.0001375,
|
92 |
+
"loss": 2.4148,
|
93 |
+
"step": 14
|
94 |
+
},
|
95 |
+
{
|
96 |
+
"epoch": 3.75,
|
97 |
+
"learning_rate": 0.00013125000000000002,
|
98 |
+
"loss": 2.6075,
|
99 |
+
"step": 15
|
100 |
+
},
|
101 |
+
{
|
102 |
+
"epoch": 4.0,
|
103 |
+
"learning_rate": 0.000125,
|
104 |
+
"loss": 2.5263,
|
105 |
+
"step": 16
|
106 |
+
},
|
107 |
+
{
|
108 |
+
"epoch": 4.25,
|
109 |
+
"learning_rate": 0.00011875,
|
110 |
+
"loss": 2.4238,
|
111 |
+
"step": 17
|
112 |
+
},
|
113 |
+
{
|
114 |
+
"epoch": 4.5,
|
115 |
+
"learning_rate": 0.00011250000000000001,
|
116 |
+
"loss": 2.4985,
|
117 |
+
"step": 18
|
118 |
+
},
|
119 |
+
{
|
120 |
+
"epoch": 4.75,
|
121 |
+
"learning_rate": 0.00010625000000000001,
|
122 |
+
"loss": 2.4527,
|
123 |
+
"step": 19
|
124 |
+
},
|
125 |
+
{
|
126 |
+
"epoch": 5.0,
|
127 |
+
"learning_rate": 0.0001,
|
128 |
+
"loss": 2.4415,
|
129 |
+
"step": 20
|
130 |
+
},
|
131 |
+
{
|
132 |
+
"epoch": 5.25,
|
133 |
+
"learning_rate": 9.375e-05,
|
134 |
+
"loss": 2.4565,
|
135 |
+
"step": 21
|
136 |
+
},
|
137 |
+
{
|
138 |
+
"epoch": 5.5,
|
139 |
+
"learning_rate": 8.75e-05,
|
140 |
+
"loss": 2.2245,
|
141 |
+
"step": 22
|
142 |
+
},
|
143 |
+
{
|
144 |
+
"epoch": 5.75,
|
145 |
+
"learning_rate": 8.125000000000001e-05,
|
146 |
+
"loss": 2.5175,
|
147 |
+
"step": 23
|
148 |
+
},
|
149 |
+
{
|
150 |
+
"epoch": 6.0,
|
151 |
+
"learning_rate": 7.500000000000001e-05,
|
152 |
+
"loss": 2.4022,
|
153 |
+
"step": 24
|
154 |
+
},
|
155 |
+
{
|
156 |
+
"epoch": 6.25,
|
157 |
+
"learning_rate": 6.875e-05,
|
158 |
+
"loss": 2.4127,
|
159 |
+
"step": 25
|
160 |
+
},
|
161 |
+
{
|
162 |
+
"epoch": 6.5,
|
163 |
+
"learning_rate": 6.25e-05,
|
164 |
+
"loss": 2.452,
|
165 |
+
"step": 26
|
166 |
+
},
|
167 |
+
{
|
168 |
+
"epoch": 6.75,
|
169 |
+
"learning_rate": 5.6250000000000005e-05,
|
170 |
+
"loss": 2.3324,
|
171 |
+
"step": 27
|
172 |
+
},
|
173 |
+
{
|
174 |
+
"epoch": 7.0,
|
175 |
+
"learning_rate": 5e-05,
|
176 |
+
"loss": 2.2148,
|
177 |
+
"step": 28
|
178 |
+
},
|
179 |
+
{
|
180 |
+
"epoch": 7.25,
|
181 |
+
"learning_rate": 4.375e-05,
|
182 |
+
"loss": 2.381,
|
183 |
+
"step": 29
|
184 |
+
},
|
185 |
+
{
|
186 |
+
"epoch": 7.5,
|
187 |
+
"learning_rate": 3.7500000000000003e-05,
|
188 |
+
"loss": 2.4005,
|
189 |
+
"step": 30
|
190 |
+
},
|
191 |
+
{
|
192 |
+
"epoch": 7.75,
|
193 |
+
"learning_rate": 3.125e-05,
|
194 |
+
"loss": 2.3215,
|
195 |
+
"step": 31
|
196 |
+
},
|
197 |
+
{
|
198 |
+
"epoch": 8.0,
|
199 |
+
"learning_rate": 2.5e-05,
|
200 |
+
"loss": 2.1712,
|
201 |
+
"step": 32
|
202 |
+
},
|
203 |
+
{
|
204 |
+
"epoch": 8.25,
|
205 |
+
"learning_rate": 1.8750000000000002e-05,
|
206 |
+
"loss": 2.3326,
|
207 |
+
"step": 33
|
208 |
+
},
|
209 |
+
{
|
210 |
+
"epoch": 8.5,
|
211 |
+
"learning_rate": 1.25e-05,
|
212 |
+
"loss": 2.2245,
|
213 |
+
"step": 34
|
214 |
+
},
|
215 |
+
{
|
216 |
+
"epoch": 8.75,
|
217 |
+
"learning_rate": 6.25e-06,
|
218 |
+
"loss": 2.4096,
|
219 |
+
"step": 35
|
220 |
+
},
|
221 |
+
{
|
222 |
+
"epoch": 9.0,
|
223 |
+
"learning_rate": 0.0,
|
224 |
+
"loss": 2.2489,
|
225 |
+
"step": 36
|
226 |
+
}
|
227 |
+
],
|
228 |
+
"logging_steps": 1,
|
229 |
+
"max_steps": 36,
|
230 |
+
"num_train_epochs": 9,
|
231 |
+
"save_steps": 500,
|
232 |
+
"total_flos": 3548728019386368.0,
|
233 |
+
"trial_name": null,
|
234 |
+
"trial_params": null
|
235 |
+
}
|
checkpoint-36/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2340eaba89c794e831dcc37b342ad310e98074534bb90f7c2c6aa1f3873f4ef
|
3 |
+
size 4027
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "abhishek/llama-2-7b-hf-small-shards",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 2,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 11008,
|
12 |
+
"max_position_embeddings": 2048,
|
13 |
+
"model_type": "llama",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 32,
|
16 |
+
"num_key_value_heads": 32,
|
17 |
+
"pad_token_id": 0,
|
18 |
+
"pretraining_tp": 1,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_scaling": null,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.32.0.dev0",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
pytorch_model-00001-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:57d8bc848423efb976b979f14ab746c2440a5400639fcc68db475691ee5e8186
|
3 |
+
size 9976620122
|
pytorch_model-00002-of-00002.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe6dfd7995b27b8efe5e1d5fd4b1af7b58311288c33e2808982bf60137d60f54
|
3 |
+
size 3500310787
|
pytorch_model.bin.index.json
ADDED
@@ -0,0 +1,298 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 13476831232
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.weight": "pytorch_model-00002-of-00002.bin",
|
7 |
+
"model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
|
8 |
+
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
9 |
+
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
10 |
+
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
11 |
+
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
12 |
+
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
13 |
+
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
14 |
+
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
15 |
+
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
16 |
+
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
17 |
+
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
18 |
+
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
19 |
+
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
20 |
+
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
21 |
+
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
22 |
+
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
23 |
+
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
24 |
+
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
25 |
+
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
26 |
+
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
27 |
+
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
28 |
+
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
29 |
+
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
30 |
+
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
31 |
+
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
32 |
+
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
33 |
+
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
34 |
+
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
35 |
+
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
36 |
+
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
37 |
+
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
38 |
+
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
39 |
+
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
40 |
+
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
41 |
+
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
42 |
+
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
43 |
+
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
44 |
+
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
45 |
+
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
46 |
+
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
47 |
+
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
48 |
+
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
49 |
+
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
50 |
+
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
51 |
+
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
52 |
+
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
53 |
+
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
54 |
+
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
55 |
+
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
56 |
+
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
57 |
+
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
58 |
+
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
59 |
+
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
60 |
+
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
61 |
+
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
62 |
+
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
63 |
+
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
64 |
+
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
65 |
+
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
66 |
+
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
67 |
+
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
68 |
+
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
69 |
+
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
70 |
+
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
71 |
+
"model.layers.15.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
72 |
+
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
73 |
+
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
74 |
+
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
75 |
+
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
76 |
+
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
77 |
+
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
78 |
+
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
79 |
+
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
80 |
+
"model.layers.16.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
81 |
+
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
82 |
+
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
83 |
+
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
84 |
+
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
85 |
+
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
86 |
+
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
87 |
+
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
88 |
+
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
89 |
+
"model.layers.17.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
90 |
+
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
91 |
+
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
92 |
+
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
93 |
+
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
94 |
+
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
95 |
+
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
96 |
+
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
97 |
+
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
98 |
+
"model.layers.18.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
99 |
+
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
100 |
+
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
101 |
+
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
102 |
+
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
103 |
+
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
104 |
+
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
105 |
+
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
106 |
+
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
107 |
+
"model.layers.19.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
108 |
+
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
109 |
+
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
110 |
+
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
111 |
+
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
112 |
+
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
113 |
+
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
114 |
+
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
115 |
+
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
116 |
+
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
117 |
+
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
118 |
+
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
119 |
+
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
120 |
+
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
121 |
+
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
122 |
+
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
123 |
+
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
124 |
+
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
125 |
+
"model.layers.20.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
126 |
+
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
127 |
+
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
128 |
+
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
129 |
+
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
130 |
+
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
131 |
+
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
132 |
+
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
133 |
+
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
134 |
+
"model.layers.21.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
135 |
+
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
136 |
+
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
137 |
+
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
138 |
+
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
139 |
+
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
140 |
+
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
141 |
+
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
142 |
+
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
143 |
+
"model.layers.22.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
144 |
+
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
145 |
+
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
146 |
+
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
147 |
+
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
148 |
+
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
149 |
+
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
150 |
+
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
151 |
+
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
152 |
+
"model.layers.23.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
153 |
+
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
154 |
+
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
155 |
+
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
156 |
+
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
157 |
+
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
158 |
+
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
159 |
+
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
160 |
+
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
161 |
+
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
162 |
+
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
163 |
+
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
164 |
+
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
165 |
+
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
166 |
+
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
167 |
+
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
168 |
+
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
169 |
+
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
170 |
+
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
171 |
+
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
172 |
+
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
173 |
+
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
174 |
+
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
175 |
+
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
176 |
+
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
177 |
+
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
178 |
+
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
179 |
+
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
180 |
+
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
181 |
+
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
182 |
+
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
183 |
+
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
184 |
+
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
185 |
+
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
186 |
+
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
187 |
+
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
188 |
+
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
189 |
+
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
190 |
+
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
191 |
+
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
192 |
+
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
193 |
+
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
194 |
+
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
195 |
+
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
196 |
+
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
197 |
+
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
198 |
+
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
199 |
+
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
200 |
+
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
201 |
+
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
202 |
+
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
203 |
+
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
204 |
+
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
205 |
+
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
206 |
+
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
207 |
+
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
208 |
+
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
209 |
+
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
210 |
+
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
211 |
+
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
212 |
+
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
213 |
+
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
214 |
+
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
215 |
+
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
216 |
+
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
217 |
+
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
218 |
+
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
219 |
+
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
220 |
+
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
221 |
+
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
222 |
+
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
223 |
+
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
224 |
+
"model.layers.30.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
225 |
+
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
226 |
+
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
227 |
+
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
228 |
+
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
229 |
+
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
230 |
+
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
231 |
+
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
232 |
+
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
233 |
+
"model.layers.31.input_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
234 |
+
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00002-of-00002.bin",
|
235 |
+
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00002-of-00002.bin",
|
236 |
+
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00002-of-00002.bin",
|
237 |
+
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00002-of-00002.bin",
|
238 |
+
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00002-of-00002.bin",
|
239 |
+
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00002-of-00002.bin",
|
240 |
+
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00002-of-00002.bin",
|
241 |
+
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00002-of-00002.bin",
|
242 |
+
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
243 |
+
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
244 |
+
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
245 |
+
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
246 |
+
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
247 |
+
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
248 |
+
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
249 |
+
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
250 |
+
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
251 |
+
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
252 |
+
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
253 |
+
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
254 |
+
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
255 |
+
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
256 |
+
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
257 |
+
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
258 |
+
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
259 |
+
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
260 |
+
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
261 |
+
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
262 |
+
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
263 |
+
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
264 |
+
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
265 |
+
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
266 |
+
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
267 |
+
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
268 |
+
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
269 |
+
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
270 |
+
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
271 |
+
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
272 |
+
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
273 |
+
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
274 |
+
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
275 |
+
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
276 |
+
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
277 |
+
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
278 |
+
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
279 |
+
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
280 |
+
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
281 |
+
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
282 |
+
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
283 |
+
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
284 |
+
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
285 |
+
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
286 |
+
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
287 |
+
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
288 |
+
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00002.bin",
|
289 |
+
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00002.bin",
|
290 |
+
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00002.bin",
|
291 |
+
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00002.bin",
|
292 |
+
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00002.bin",
|
293 |
+
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00002.bin",
|
294 |
+
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00002.bin",
|
295 |
+
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00002.bin",
|
296 |
+
"model.norm.weight": "pytorch_model-00002-of-00002.bin"
|
297 |
+
}
|
298 |
+
}
|
runs/Aug12_03-16-59_132de5da0894/events.out.tfevents.1691810219.132de5da0894.3365.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7bb6a0ca9e25868461d63984b25377d25a6fd5811256bf72c75c2de05a03bb42
|
3 |
+
size 10342
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<unk>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": true,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"__type": "AddedToken",
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": true,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false
|
9 |
+
},
|
10 |
+
"clean_up_tokenization_spaces": false,
|
11 |
+
"eos_token": {
|
12 |
+
"__type": "AddedToken",
|
13 |
+
"content": "</s>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": true,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false
|
18 |
+
},
|
19 |
+
"legacy": false,
|
20 |
+
"model_max_length": 1000000000000000019884624838656,
|
21 |
+
"pad_token": null,
|
22 |
+
"sp_model_kwargs": {},
|
23 |
+
"tokenizer_class": "LlamaTokenizer",
|
24 |
+
"unk_token": {
|
25 |
+
"__type": "AddedToken",
|
26 |
+
"content": "<unk>",
|
27 |
+
"lstrip": false,
|
28 |
+
"normalized": true,
|
29 |
+
"rstrip": false,
|
30 |
+
"single_word": false
|
31 |
+
}
|
32 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b2340eaba89c794e831dcc37b342ad310e98074534bb90f7c2c6aa1f3873f4ef
|
3 |
+
size 4027
|
training_params.json
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model_name": "abhishek/llama-2-7b-hf-small-shards",
|
3 |
+
"data_path": ".",
|
4 |
+
"train_split": "train",
|
5 |
+
"valid_split": null,
|
6 |
+
"text_column": "text",
|
7 |
+
"huggingface_token": null,
|
8 |
+
"learning_rate": 0.0002,
|
9 |
+
"num_train_epochs": 9,
|
10 |
+
"train_batch_size": 5,
|
11 |
+
"eval_batch_size": 4,
|
12 |
+
"warmup_ratio": 0.1,
|
13 |
+
"gradient_accumulation_steps": 1,
|
14 |
+
"optimizer": "adamw_torch",
|
15 |
+
"scheduler": "linear",
|
16 |
+
"weight_decay": 0.0,
|
17 |
+
"max_grad_norm": 1.0,
|
18 |
+
"seed": 42,
|
19 |
+
"add_eos_token": false,
|
20 |
+
"block_size": -1,
|
21 |
+
"use_peft": true,
|
22 |
+
"lora_r": 16,
|
23 |
+
"lora_alpha": 32,
|
24 |
+
"lora_dropout": 0.05,
|
25 |
+
"training_type": "generic",
|
26 |
+
"train_on_inputs": false,
|
27 |
+
"logging_steps": -1,
|
28 |
+
"project_name": "rewiki",
|
29 |
+
"evaluation_strategy": "epoch",
|
30 |
+
"save_total_limit": 1,
|
31 |
+
"save_strategy": "epoch",
|
32 |
+
"auto_find_batch_size": false,
|
33 |
+
"fp16": false,
|
34 |
+
"push_to_hub": true,
|
35 |
+
"use_int8": false,
|
36 |
+
"model_max_length": 1024,
|
37 |
+
"repo_id": "Captluke/Llama-2-7b-finetune-v3",
|
38 |
+
"use_int4": true,
|
39 |
+
"trainer": "sft",
|
40 |
+
"target_modules": null
|
41 |
+
}
|