Upload 11 files
Browse files- NeXGen/README.md +9 -0
- NeXGen/added_tokens.json +4 -0
- NeXGen/config.json +20 -0
- NeXGen/merges.txt +0 -0
- NeXGen/pytorch_model.bin +3 -0
- NeXGen/special_tokens_map.json +30 -0
- NeXGen/tokenizer.json +0 -0
- NeXGen/tokenizer_config.json +38 -0
- NeXGen/training_args.bin +3 -0
- NeXGen/training_params.json +47 -0
- NeXGen/vocab.json +0 -0
NeXGen/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
|
NeXGen/added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|pad|>": 50258,
|
3 |
+
"<|startoftext|>": 50257
|
4 |
+
}
|
NeXGen/config.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"auto_mapping": null,
|
3 |
+
"base_model_name_or_path": "farnhua/gpt2-small-self_instruct_human_eval",
|
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 |
+
"c_attn"
|
18 |
+
],
|
19 |
+
"task_type": "CAUSAL_LM"
|
20 |
+
}
|
NeXGen/merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
NeXGen/pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60f3ea3765c1b02514bb4b684bd3d1f5004f1101b81bc7c09b3ba0df014ff825
|
3 |
+
size 497805594
|
NeXGen/special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": true,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": true,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "<|pad|>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": true,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<|endoftext|>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": true,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
NeXGen/tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
NeXGen/tokenizer_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
3 |
+
"add_prefix_space": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"50256": {
|
6 |
+
"content": "<|endoftext|>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"50257": {
|
14 |
+
"content": "<|startoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"50258": {
|
22 |
+
"content": "<|pad|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"bos_token": "<|startoftext|>",
|
31 |
+
"clean_up_tokenization_spaces": true,
|
32 |
+
"eos_token": "<|endoftext|>",
|
33 |
+
"errors": "replace",
|
34 |
+
"model_max_length": 1024,
|
35 |
+
"pad_token": "<|pad|>",
|
36 |
+
"tokenizer_class": "GPT2Tokenizer",
|
37 |
+
"unk_token": "<|endoftext|>"
|
38 |
+
}
|
NeXGen/training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:451c10f29d391c5977d9401a129c75070c1f9e21c563dee1c87aee84480bdc81
|
3 |
+
size 4472
|
NeXGen/training_params.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "farnhua/gpt2-small-self_instruct_human_eval",
|
3 |
+
"data_path": "timdettmers/openassistant-guanaco",
|
4 |
+
"project_name": "NeXGen",
|
5 |
+
"train_split": "train",
|
6 |
+
"valid_split": null,
|
7 |
+
"text_column": "text",
|
8 |
+
"rejected_text_column": "rejected",
|
9 |
+
"token": null,
|
10 |
+
"lr": 0.0002,
|
11 |
+
"epochs": 3,
|
12 |
+
"batch_size": 2,
|
13 |
+
"warmup_ratio": 0.1,
|
14 |
+
"gradient_accumulation": 1,
|
15 |
+
"optimizer": "adamw_torch",
|
16 |
+
"scheduler": "linear",
|
17 |
+
"weight_decay": 0.0,
|
18 |
+
"max_grad_norm": 1.0,
|
19 |
+
"seed": 42,
|
20 |
+
"add_eos_token": false,
|
21 |
+
"block_size": -1,
|
22 |
+
"use_peft": true,
|
23 |
+
"lora_r": 16,
|
24 |
+
"lora_alpha": 32,
|
25 |
+
"lora_dropout": 0.05,
|
26 |
+
"logging_steps": -1,
|
27 |
+
"evaluation_strategy": "epoch",
|
28 |
+
"save_total_limit": 1,
|
29 |
+
"save_strategy": "epoch",
|
30 |
+
"auto_find_batch_size": false,
|
31 |
+
"fp16": false,
|
32 |
+
"push_to_hub": false,
|
33 |
+
"use_int8": false,
|
34 |
+
"model_max_length": 2048,
|
35 |
+
"repo_id": null,
|
36 |
+
"use_int4": true,
|
37 |
+
"trainer": "sft",
|
38 |
+
"target_modules": null,
|
39 |
+
"merge_adapter": false,
|
40 |
+
"username": null,
|
41 |
+
"use_flash_attention_2": false,
|
42 |
+
"log": "none",
|
43 |
+
"disable_gradient_checkpointing": false,
|
44 |
+
"model_ref": null,
|
45 |
+
"dpo_beta": 0.1,
|
46 |
+
"prompt_text_column": "prompt"
|
47 |
+
}
|
NeXGen/vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|