End of training
Browse files- README.md +138 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +332 -0
- pytorch_model-00001-of-00002.bin +1 -1
- pytorch_model-00002-of-00002.bin +1 -1
README.md
ADDED
@@ -0,0 +1,138 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: mit
|
3 |
+
base_model: microsoft/phi-2
|
4 |
+
tags:
|
5 |
+
- axolotl
|
6 |
+
- generated_from_trainer
|
7 |
+
model-index:
|
8 |
+
- name: phi2-alpaca
|
9 |
+
results: []
|
10 |
+
---
|
11 |
+
|
12 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
13 |
+
should probably proofread and complete it, then remove this comment. -->
|
14 |
+
|
15 |
+
[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
|
16 |
+
<details><summary>See axolotl config</summary>
|
17 |
+
|
18 |
+
axolotl version: `0.3.0`
|
19 |
+
```yaml
|
20 |
+
base_model: microsoft/phi-2
|
21 |
+
model_type: AutoModelForCausalLM
|
22 |
+
tokenizer_type: AutoTokenizer
|
23 |
+
trust_remote_code: true
|
24 |
+
|
25 |
+
hub_model_id: openaccess-ai-collective/phi2-alpaca
|
26 |
+
|
27 |
+
load_in_8bit: false
|
28 |
+
load_in_4bit: false
|
29 |
+
strict: false
|
30 |
+
|
31 |
+
datasets:
|
32 |
+
- path: tatsu-lab/alpaca
|
33 |
+
type: alpaca
|
34 |
+
|
35 |
+
dataset_prepared_path:
|
36 |
+
val_set_size: 0.05
|
37 |
+
output_dir: ./phi-sft-out
|
38 |
+
|
39 |
+
sequence_len: 2048
|
40 |
+
sample_packing: false # currently unsupported
|
41 |
+
pad_to_sequence_len:
|
42 |
+
|
43 |
+
wandb_project: phi2
|
44 |
+
wandb_entity: oaaic
|
45 |
+
wandb_watch:
|
46 |
+
wandb_name:
|
47 |
+
wandb_log_model:
|
48 |
+
|
49 |
+
gradient_accumulation_steps: 8
|
50 |
+
micro_batch_size: 4
|
51 |
+
num_epochs: 1
|
52 |
+
optimizer: paged_adamw_8bit
|
53 |
+
adam_beta2: 0.95
|
54 |
+
adam_epsilon: 0.00001
|
55 |
+
max_grad_norm: 1.0
|
56 |
+
lr_scheduler: cosine
|
57 |
+
learning_rate: 1e-5
|
58 |
+
|
59 |
+
train_on_inputs: false
|
60 |
+
group_by_length: false
|
61 |
+
bf16: true
|
62 |
+
fp16: false
|
63 |
+
tf32: true
|
64 |
+
|
65 |
+
gradient_checkpointing: true
|
66 |
+
early_stopping_patience:
|
67 |
+
resume_from_checkpoint:
|
68 |
+
local_rank:
|
69 |
+
logging_steps: 1
|
70 |
+
xformers_attention:
|
71 |
+
flash_attention: true
|
72 |
+
|
73 |
+
warmup_steps: 100
|
74 |
+
evals_per_epoch: 4
|
75 |
+
saves_per_epoch: 1
|
76 |
+
debug:
|
77 |
+
deepspeed:
|
78 |
+
weight_decay: 0.1
|
79 |
+
fsdp:
|
80 |
+
fsdp_config:
|
81 |
+
resize_token_embeddings_to_32x: true
|
82 |
+
special_tokens:
|
83 |
+
pad_token: "<|endoftext|>"
|
84 |
+
|
85 |
+
```
|
86 |
+
|
87 |
+
</details><br>
|
88 |
+
|
89 |
+
# phi2-alpaca
|
90 |
+
|
91 |
+
This model is a fine-tuned version of [microsoft/phi-2](https://huggingface.co/microsoft/phi-2) on the None dataset.
|
92 |
+
It achieves the following results on the evaluation set:
|
93 |
+
- Loss: 0.9343
|
94 |
+
|
95 |
+
## Model description
|
96 |
+
|
97 |
+
More information needed
|
98 |
+
|
99 |
+
## Intended uses & limitations
|
100 |
+
|
101 |
+
More information needed
|
102 |
+
|
103 |
+
## Training and evaluation data
|
104 |
+
|
105 |
+
More information needed
|
106 |
+
|
107 |
+
## Training procedure
|
108 |
+
|
109 |
+
### Training hyperparameters
|
110 |
+
|
111 |
+
The following hyperparameters were used during training:
|
112 |
+
- learning_rate: 1e-05
|
113 |
+
- train_batch_size: 4
|
114 |
+
- eval_batch_size: 4
|
115 |
+
- seed: 42
|
116 |
+
- gradient_accumulation_steps: 8
|
117 |
+
- total_train_batch_size: 32
|
118 |
+
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-05
|
119 |
+
- lr_scheduler_type: cosine
|
120 |
+
- lr_scheduler_warmup_steps: 100
|
121 |
+
- num_epochs: 1
|
122 |
+
|
123 |
+
### Training results
|
124 |
+
|
125 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
126 |
+
|:-------------:|:-----:|:----:|:---------------:|
|
127 |
+
| 1.3994 | 0.0 | 1 | 1.3199 |
|
128 |
+
| 0.9532 | 0.25 | 386 | 0.9886 |
|
129 |
+
| 0.8445 | 0.5 | 772 | 0.9421 |
|
130 |
+
| 0.7303 | 0.75 | 1158 | 0.9343 |
|
131 |
+
|
132 |
+
|
133 |
+
### Framework versions
|
134 |
+
|
135 |
+
- Transformers 4.37.0.dev0
|
136 |
+
- Pytorch 2.0.1+cu118
|
137 |
+
- Datasets 2.16.1
|
138 |
+
- Tokenizers 0.15.0
|
model-00001-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:718c4d4fef30fd1d185b56541780fdadabb3b4161dee7979850df01671fc51d2
|
3 |
+
size 4982468168
|
model-00002-of-00002.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0698eab71af465bac1e7529a28d5467052fc071ceb241397d367ba518d1024d4
|
3 |
+
size 839190784
|
model.safetensors.index.json
ADDED
@@ -0,0 +1,332 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"metadata": {
|
3 |
+
"total_size": 5821624320
|
4 |
+
},
|
5 |
+
"weight_map": {
|
6 |
+
"lm_head.linear.bias": "model-00002-of-00002.safetensors",
|
7 |
+
"lm_head.linear.weight": "model-00002-of-00002.safetensors",
|
8 |
+
"lm_head.ln.bias": "model-00002-of-00002.safetensors",
|
9 |
+
"lm_head.ln.weight": "model-00002-of-00002.safetensors",
|
10 |
+
"transformer.embd.wte.weight": "model-00001-of-00002.safetensors",
|
11 |
+
"transformer.h.0.ln.bias": "model-00001-of-00002.safetensors",
|
12 |
+
"transformer.h.0.ln.weight": "model-00001-of-00002.safetensors",
|
13 |
+
"transformer.h.0.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
14 |
+
"transformer.h.0.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
15 |
+
"transformer.h.0.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
16 |
+
"transformer.h.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
17 |
+
"transformer.h.0.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
18 |
+
"transformer.h.0.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
19 |
+
"transformer.h.0.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
20 |
+
"transformer.h.0.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
21 |
+
"transformer.h.1.ln.bias": "model-00001-of-00002.safetensors",
|
22 |
+
"transformer.h.1.ln.weight": "model-00001-of-00002.safetensors",
|
23 |
+
"transformer.h.1.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
24 |
+
"transformer.h.1.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
25 |
+
"transformer.h.1.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
26 |
+
"transformer.h.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
27 |
+
"transformer.h.1.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
28 |
+
"transformer.h.1.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
29 |
+
"transformer.h.1.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
30 |
+
"transformer.h.1.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
31 |
+
"transformer.h.10.ln.bias": "model-00001-of-00002.safetensors",
|
32 |
+
"transformer.h.10.ln.weight": "model-00001-of-00002.safetensors",
|
33 |
+
"transformer.h.10.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
34 |
+
"transformer.h.10.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
35 |
+
"transformer.h.10.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
36 |
+
"transformer.h.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
37 |
+
"transformer.h.10.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
38 |
+
"transformer.h.10.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
39 |
+
"transformer.h.10.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
40 |
+
"transformer.h.10.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
41 |
+
"transformer.h.11.ln.bias": "model-00001-of-00002.safetensors",
|
42 |
+
"transformer.h.11.ln.weight": "model-00001-of-00002.safetensors",
|
43 |
+
"transformer.h.11.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
44 |
+
"transformer.h.11.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
45 |
+
"transformer.h.11.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
46 |
+
"transformer.h.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
47 |
+
"transformer.h.11.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
48 |
+
"transformer.h.11.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
49 |
+
"transformer.h.11.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
50 |
+
"transformer.h.11.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
51 |
+
"transformer.h.12.ln.bias": "model-00001-of-00002.safetensors",
|
52 |
+
"transformer.h.12.ln.weight": "model-00001-of-00002.safetensors",
|
53 |
+
"transformer.h.12.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
54 |
+
"transformer.h.12.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
55 |
+
"transformer.h.12.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
56 |
+
"transformer.h.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
57 |
+
"transformer.h.12.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
58 |
+
"transformer.h.12.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
59 |
+
"transformer.h.12.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
60 |
+
"transformer.h.12.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
61 |
+
"transformer.h.13.ln.bias": "model-00001-of-00002.safetensors",
|
62 |
+
"transformer.h.13.ln.weight": "model-00001-of-00002.safetensors",
|
63 |
+
"transformer.h.13.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
64 |
+
"transformer.h.13.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
65 |
+
"transformer.h.13.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
66 |
+
"transformer.h.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
67 |
+
"transformer.h.13.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
68 |
+
"transformer.h.13.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
69 |
+
"transformer.h.13.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
70 |
+
"transformer.h.13.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
71 |
+
"transformer.h.14.ln.bias": "model-00001-of-00002.safetensors",
|
72 |
+
"transformer.h.14.ln.weight": "model-00001-of-00002.safetensors",
|
73 |
+
"transformer.h.14.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
74 |
+
"transformer.h.14.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
75 |
+
"transformer.h.14.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
76 |
+
"transformer.h.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
77 |
+
"transformer.h.14.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
78 |
+
"transformer.h.14.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
79 |
+
"transformer.h.14.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
80 |
+
"transformer.h.14.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
81 |
+
"transformer.h.15.ln.bias": "model-00001-of-00002.safetensors",
|
82 |
+
"transformer.h.15.ln.weight": "model-00001-of-00002.safetensors",
|
83 |
+
"transformer.h.15.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
84 |
+
"transformer.h.15.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
85 |
+
"transformer.h.15.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
86 |
+
"transformer.h.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
87 |
+
"transformer.h.15.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
88 |
+
"transformer.h.15.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
89 |
+
"transformer.h.15.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
90 |
+
"transformer.h.15.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
91 |
+
"transformer.h.16.ln.bias": "model-00001-of-00002.safetensors",
|
92 |
+
"transformer.h.16.ln.weight": "model-00001-of-00002.safetensors",
|
93 |
+
"transformer.h.16.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
94 |
+
"transformer.h.16.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
95 |
+
"transformer.h.16.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
96 |
+
"transformer.h.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
97 |
+
"transformer.h.16.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
98 |
+
"transformer.h.16.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
99 |
+
"transformer.h.16.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
100 |
+
"transformer.h.16.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
101 |
+
"transformer.h.17.ln.bias": "model-00001-of-00002.safetensors",
|
102 |
+
"transformer.h.17.ln.weight": "model-00001-of-00002.safetensors",
|
103 |
+
"transformer.h.17.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
104 |
+
"transformer.h.17.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
105 |
+
"transformer.h.17.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
106 |
+
"transformer.h.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
107 |
+
"transformer.h.17.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
108 |
+
"transformer.h.17.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
109 |
+
"transformer.h.17.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
110 |
+
"transformer.h.17.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
111 |
+
"transformer.h.18.ln.bias": "model-00001-of-00002.safetensors",
|
112 |
+
"transformer.h.18.ln.weight": "model-00001-of-00002.safetensors",
|
113 |
+
"transformer.h.18.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
114 |
+
"transformer.h.18.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
115 |
+
"transformer.h.18.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
116 |
+
"transformer.h.18.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
117 |
+
"transformer.h.18.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
118 |
+
"transformer.h.18.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
119 |
+
"transformer.h.18.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
120 |
+
"transformer.h.18.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
121 |
+
"transformer.h.19.ln.bias": "model-00001-of-00002.safetensors",
|
122 |
+
"transformer.h.19.ln.weight": "model-00001-of-00002.safetensors",
|
123 |
+
"transformer.h.19.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
124 |
+
"transformer.h.19.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
125 |
+
"transformer.h.19.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
126 |
+
"transformer.h.19.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
127 |
+
"transformer.h.19.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
128 |
+
"transformer.h.19.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
129 |
+
"transformer.h.19.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
130 |
+
"transformer.h.19.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
131 |
+
"transformer.h.2.ln.bias": "model-00001-of-00002.safetensors",
|
132 |
+
"transformer.h.2.ln.weight": "model-00001-of-00002.safetensors",
|
133 |
+
"transformer.h.2.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
134 |
+
"transformer.h.2.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
135 |
+
"transformer.h.2.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
136 |
+
"transformer.h.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
137 |
+
"transformer.h.2.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
138 |
+
"transformer.h.2.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
139 |
+
"transformer.h.2.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
140 |
+
"transformer.h.2.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
141 |
+
"transformer.h.20.ln.bias": "model-00001-of-00002.safetensors",
|
142 |
+
"transformer.h.20.ln.weight": "model-00001-of-00002.safetensors",
|
143 |
+
"transformer.h.20.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
144 |
+
"transformer.h.20.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
145 |
+
"transformer.h.20.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
146 |
+
"transformer.h.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
147 |
+
"transformer.h.20.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
148 |
+
"transformer.h.20.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
149 |
+
"transformer.h.20.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
150 |
+
"transformer.h.20.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
151 |
+
"transformer.h.21.ln.bias": "model-00001-of-00002.safetensors",
|
152 |
+
"transformer.h.21.ln.weight": "model-00001-of-00002.safetensors",
|
153 |
+
"transformer.h.21.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
154 |
+
"transformer.h.21.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
155 |
+
"transformer.h.21.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
156 |
+
"transformer.h.21.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
157 |
+
"transformer.h.21.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
158 |
+
"transformer.h.21.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
159 |
+
"transformer.h.21.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
160 |
+
"transformer.h.21.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
161 |
+
"transformer.h.22.ln.bias": "model-00001-of-00002.safetensors",
|
162 |
+
"transformer.h.22.ln.weight": "model-00001-of-00002.safetensors",
|
163 |
+
"transformer.h.22.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
164 |
+
"transformer.h.22.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
165 |
+
"transformer.h.22.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
166 |
+
"transformer.h.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
167 |
+
"transformer.h.22.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
168 |
+
"transformer.h.22.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
169 |
+
"transformer.h.22.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
170 |
+
"transformer.h.22.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
171 |
+
"transformer.h.23.ln.bias": "model-00001-of-00002.safetensors",
|
172 |
+
"transformer.h.23.ln.weight": "model-00001-of-00002.safetensors",
|
173 |
+
"transformer.h.23.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
174 |
+
"transformer.h.23.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
175 |
+
"transformer.h.23.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
176 |
+
"transformer.h.23.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
177 |
+
"transformer.h.23.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
178 |
+
"transformer.h.23.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
179 |
+
"transformer.h.23.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
180 |
+
"transformer.h.23.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
181 |
+
"transformer.h.24.ln.bias": "model-00001-of-00002.safetensors",
|
182 |
+
"transformer.h.24.ln.weight": "model-00001-of-00002.safetensors",
|
183 |
+
"transformer.h.24.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
184 |
+
"transformer.h.24.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
185 |
+
"transformer.h.24.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
186 |
+
"transformer.h.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
187 |
+
"transformer.h.24.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
188 |
+
"transformer.h.24.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
189 |
+
"transformer.h.24.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
190 |
+
"transformer.h.24.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
191 |
+
"transformer.h.25.ln.bias": "model-00001-of-00002.safetensors",
|
192 |
+
"transformer.h.25.ln.weight": "model-00001-of-00002.safetensors",
|
193 |
+
"transformer.h.25.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
194 |
+
"transformer.h.25.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
195 |
+
"transformer.h.25.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
196 |
+
"transformer.h.25.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
197 |
+
"transformer.h.25.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
198 |
+
"transformer.h.25.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
199 |
+
"transformer.h.25.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
200 |
+
"transformer.h.25.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
201 |
+
"transformer.h.26.ln.bias": "model-00001-of-00002.safetensors",
|
202 |
+
"transformer.h.26.ln.weight": "model-00001-of-00002.safetensors",
|
203 |
+
"transformer.h.26.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
204 |
+
"transformer.h.26.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
205 |
+
"transformer.h.26.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
206 |
+
"transformer.h.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
207 |
+
"transformer.h.26.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
208 |
+
"transformer.h.26.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
209 |
+
"transformer.h.26.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
210 |
+
"transformer.h.26.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
211 |
+
"transformer.h.27.ln.bias": "model-00001-of-00002.safetensors",
|
212 |
+
"transformer.h.27.ln.weight": "model-00001-of-00002.safetensors",
|
213 |
+
"transformer.h.27.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
214 |
+
"transformer.h.27.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
215 |
+
"transformer.h.27.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
216 |
+
"transformer.h.27.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
217 |
+
"transformer.h.27.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
218 |
+
"transformer.h.27.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
219 |
+
"transformer.h.27.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
220 |
+
"transformer.h.27.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
221 |
+
"transformer.h.28.ln.bias": "model-00001-of-00002.safetensors",
|
222 |
+
"transformer.h.28.ln.weight": "model-00001-of-00002.safetensors",
|
223 |
+
"transformer.h.28.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
224 |
+
"transformer.h.28.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
225 |
+
"transformer.h.28.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
226 |
+
"transformer.h.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
227 |
+
"transformer.h.28.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
228 |
+
"transformer.h.28.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
229 |
+
"transformer.h.28.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
230 |
+
"transformer.h.28.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
231 |
+
"transformer.h.29.ln.bias": "model-00001-of-00002.safetensors",
|
232 |
+
"transformer.h.29.ln.weight": "model-00001-of-00002.safetensors",
|
233 |
+
"transformer.h.29.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
234 |
+
"transformer.h.29.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
235 |
+
"transformer.h.29.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
236 |
+
"transformer.h.29.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
237 |
+
"transformer.h.29.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
238 |
+
"transformer.h.29.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
239 |
+
"transformer.h.29.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
240 |
+
"transformer.h.29.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
241 |
+
"transformer.h.3.ln.bias": "model-00001-of-00002.safetensors",
|
242 |
+
"transformer.h.3.ln.weight": "model-00001-of-00002.safetensors",
|
243 |
+
"transformer.h.3.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
244 |
+
"transformer.h.3.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
245 |
+
"transformer.h.3.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
246 |
+
"transformer.h.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
247 |
+
"transformer.h.3.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
248 |
+
"transformer.h.3.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
249 |
+
"transformer.h.3.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
250 |
+
"transformer.h.3.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
251 |
+
"transformer.h.30.ln.bias": "model-00001-of-00002.safetensors",
|
252 |
+
"transformer.h.30.ln.weight": "model-00001-of-00002.safetensors",
|
253 |
+
"transformer.h.30.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
|
254 |
+
"transformer.h.30.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
|
255 |
+
"transformer.h.30.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
|
256 |
+
"transformer.h.30.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
|
257 |
+
"transformer.h.30.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
258 |
+
"transformer.h.30.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
259 |
+
"transformer.h.30.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
260 |
+
"transformer.h.30.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
261 |
+
"transformer.h.31.ln.bias": "model-00002-of-00002.safetensors",
|
262 |
+
"transformer.h.31.ln.weight": "model-00002-of-00002.safetensors",
|
263 |
+
"transformer.h.31.mixer.Wqkv.bias": "model-00002-of-00002.safetensors",
|
264 |
+
"transformer.h.31.mixer.Wqkv.weight": "model-00002-of-00002.safetensors",
|
265 |
+
"transformer.h.31.mixer.out_proj.bias": "model-00002-of-00002.safetensors",
|
266 |
+
"transformer.h.31.mixer.out_proj.weight": "model-00002-of-00002.safetensors",
|
267 |
+
"transformer.h.31.mlp.fc1.bias": "model-00002-of-00002.safetensors",
|
268 |
+
"transformer.h.31.mlp.fc1.weight": "model-00002-of-00002.safetensors",
|
269 |
+
"transformer.h.31.mlp.fc2.bias": "model-00002-of-00002.safetensors",
|
270 |
+
"transformer.h.31.mlp.fc2.weight": "model-00002-of-00002.safetensors",
|
271 |
+
"transformer.h.4.ln.bias": "model-00001-of-00002.safetensors",
|
272 |
+
"transformer.h.4.ln.weight": "model-00001-of-00002.safetensors",
|
273 |
+
"transformer.h.4.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
274 |
+
"transformer.h.4.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
275 |
+
"transformer.h.4.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
276 |
+
"transformer.h.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
277 |
+
"transformer.h.4.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
278 |
+
"transformer.h.4.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
279 |
+
"transformer.h.4.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
280 |
+
"transformer.h.4.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
281 |
+
"transformer.h.5.ln.bias": "model-00001-of-00002.safetensors",
|
282 |
+
"transformer.h.5.ln.weight": "model-00001-of-00002.safetensors",
|
283 |
+
"transformer.h.5.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
284 |
+
"transformer.h.5.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
285 |
+
"transformer.h.5.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
286 |
+
"transformer.h.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
287 |
+
"transformer.h.5.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
288 |
+
"transformer.h.5.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
289 |
+
"transformer.h.5.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
290 |
+
"transformer.h.5.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
291 |
+
"transformer.h.6.ln.bias": "model-00001-of-00002.safetensors",
|
292 |
+
"transformer.h.6.ln.weight": "model-00001-of-00002.safetensors",
|
293 |
+
"transformer.h.6.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
294 |
+
"transformer.h.6.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
295 |
+
"transformer.h.6.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
296 |
+
"transformer.h.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
297 |
+
"transformer.h.6.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
298 |
+
"transformer.h.6.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
299 |
+
"transformer.h.6.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
300 |
+
"transformer.h.6.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
301 |
+
"transformer.h.7.ln.bias": "model-00001-of-00002.safetensors",
|
302 |
+
"transformer.h.7.ln.weight": "model-00001-of-00002.safetensors",
|
303 |
+
"transformer.h.7.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
304 |
+
"transformer.h.7.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
305 |
+
"transformer.h.7.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
306 |
+
"transformer.h.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
307 |
+
"transformer.h.7.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
308 |
+
"transformer.h.7.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
309 |
+
"transformer.h.7.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
310 |
+
"transformer.h.7.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
311 |
+
"transformer.h.8.ln.bias": "model-00001-of-00002.safetensors",
|
312 |
+
"transformer.h.8.ln.weight": "model-00001-of-00002.safetensors",
|
313 |
+
"transformer.h.8.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
314 |
+
"transformer.h.8.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
315 |
+
"transformer.h.8.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
316 |
+
"transformer.h.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
317 |
+
"transformer.h.8.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
318 |
+
"transformer.h.8.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
319 |
+
"transformer.h.8.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
320 |
+
"transformer.h.8.mlp.fc2.weight": "model-00001-of-00002.safetensors",
|
321 |
+
"transformer.h.9.ln.bias": "model-00001-of-00002.safetensors",
|
322 |
+
"transformer.h.9.ln.weight": "model-00001-of-00002.safetensors",
|
323 |
+
"transformer.h.9.mixer.Wqkv.bias": "model-00001-of-00002.safetensors",
|
324 |
+
"transformer.h.9.mixer.Wqkv.weight": "model-00001-of-00002.safetensors",
|
325 |
+
"transformer.h.9.mixer.out_proj.bias": "model-00001-of-00002.safetensors",
|
326 |
+
"transformer.h.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors",
|
327 |
+
"transformer.h.9.mlp.fc1.bias": "model-00001-of-00002.safetensors",
|
328 |
+
"transformer.h.9.mlp.fc1.weight": "model-00001-of-00002.safetensors",
|
329 |
+
"transformer.h.9.mlp.fc2.bias": "model-00001-of-00002.safetensors",
|
330 |
+
"transformer.h.9.mlp.fc2.weight": "model-00001-of-00002.safetensors"
|
331 |
+
}
|
332 |
+
}
|
pytorch_model-00001-of-00002.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 4982539832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9212946ae3c0f700b2b97c517a5268dafafbe3ff4ff9aa51eabe4dfc8ef32b06
|
3 |
size 4982539832
|
pytorch_model-00002-of-00002.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 839195995
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a09dfb97537075b3e1a7d0b59af7c4a5ec480401eb91362d61e76aa1eab542e9
|
3 |
size 839195995
|