Wonder-Griffin
commited on
Commit
•
8e2487e
1
Parent(s):
ee54a8d
Upload folder using huggingface_hub
Browse files- README.md +48 -0
- adapter_config.json +30 -0
- adapter_model.safetensors +3 -0
- runs/Sep07_12-07-43_DadsPC/events.out.tfevents.1725728892.DadsPC.21452.0 +2 -2
- special_tokens_map.json +37 -0
- tokenizer.json +0 -0
- tokenizer_config.json +56 -0
- training_args.bin +3 -0
- training_params.json +48 -0
- vocab.txt +0 -0
README.md
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation-inference
|
5 |
+
- text-generation
|
6 |
+
- peft
|
7 |
+
library_name: transformers
|
8 |
+
base_model: Wonder-Griffin/Shorsey-T2000
|
9 |
+
widget:
|
10 |
+
- messages:
|
11 |
+
- role: user
|
12 |
+
content: What is your favorite condiment?
|
13 |
+
license: other
|
14 |
+
datasets:
|
15 |
+
- Biddls/Onion_News
|
16 |
+
---
|
17 |
+
|
18 |
+
# Model Trained Using AutoTrain
|
19 |
+
|
20 |
+
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
21 |
+
|
22 |
+
# Usage
|
23 |
+
|
24 |
+
```python
|
25 |
+
|
26 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
27 |
+
|
28 |
+
model_path = "PATH_TO_THIS_REPO"
|
29 |
+
|
30 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
31 |
+
model = AutoModelForCausalLM.from_pretrained(
|
32 |
+
model_path,
|
33 |
+
device_map="auto",
|
34 |
+
torch_dtype='auto'
|
35 |
+
).eval()
|
36 |
+
|
37 |
+
# Prompt content: "hi"
|
38 |
+
messages = [
|
39 |
+
{"role": "user", "content": "hi"}
|
40 |
+
]
|
41 |
+
|
42 |
+
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
43 |
+
output_ids = model.generate(input_ids.to('cuda'))
|
44 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
45 |
+
|
46 |
+
# Model response: "Hello! How can I assist you today?"
|
47 |
+
print(response)
|
48 |
+
```
|
adapter_config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Wonder-Griffin/Shorsey-T2000",
|
5 |
+
"bias": "none",
|
6 |
+
"fan_in_fan_out": false,
|
7 |
+
"inference_mode": true,
|
8 |
+
"init_lora_weights": true,
|
9 |
+
"layer_replication": null,
|
10 |
+
"layers_pattern": null,
|
11 |
+
"layers_to_transform": null,
|
12 |
+
"loftq_config": {},
|
13 |
+
"lora_alpha": 32,
|
14 |
+
"lora_dropout": 0.05,
|
15 |
+
"megatron_config": null,
|
16 |
+
"megatron_core": "megatron.core",
|
17 |
+
"modules_to_save": null,
|
18 |
+
"peft_type": "LORA",
|
19 |
+
"r": 16,
|
20 |
+
"rank_pattern": {},
|
21 |
+
"revision": null,
|
22 |
+
"target_modules": [
|
23 |
+
"c_proj",
|
24 |
+
"c_fc",
|
25 |
+
"c_attn"
|
26 |
+
],
|
27 |
+
"task_type": "CAUSAL_LM",
|
28 |
+
"use_dora": false,
|
29 |
+
"use_rslora": false
|
30 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e8cc38651d5a69a5610e24b0eb01ef17794903c5282f8ab0b47399d85e1246cf
|
3 |
+
size 127119624
|
runs/Sep07_12-07-43_DadsPC/events.out.tfevents.1725728892.DadsPC.21452.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:691ad3de92dff0e383c61c6f5c679eac75131e541985eccef8f3449543f47dba
|
3 |
+
size 10503
|
special_tokens_map.json
ADDED
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": {
|
3 |
+
"content": "[CLS]",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"mask_token": {
|
10 |
+
"content": "[MASK]",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "[PAD]",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"sep_token": {
|
24 |
+
"content": "[SEP]",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
},
|
30 |
+
"unk_token": {
|
31 |
+
"content": "[UNK]",
|
32 |
+
"lstrip": false,
|
33 |
+
"normalized": false,
|
34 |
+
"rstrip": false,
|
35 |
+
"single_word": false
|
36 |
+
}
|
37 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "[PAD]",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"100": {
|
12 |
+
"content": "[UNK]",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"101": {
|
20 |
+
"content": "[CLS]",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"102": {
|
28 |
+
"content": "[SEP]",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"103": {
|
36 |
+
"content": "[MASK]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
45 |
+
"clean_up_tokenization_spaces": true,
|
46 |
+
"cls_token": "[CLS]",
|
47 |
+
"do_lower_case": true,
|
48 |
+
"mask_token": "[MASK]",
|
49 |
+
"model_max_length": 512,
|
50 |
+
"pad_token": "[PAD]",
|
51 |
+
"sep_token": "[SEP]",
|
52 |
+
"strip_accents": null,
|
53 |
+
"tokenize_chinese_chars": true,
|
54 |
+
"tokenizer_class": "BertTokenizer",
|
55 |
+
"unk_token": "[UNK]"
|
56 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:026a7d4fb28ad0314bab775847ef544357f910f1f065f169e7da8cb716ac8b86
|
3 |
+
size 5176
|
training_params.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "Wonder-Griffin/Shorsey-T2000",
|
3 |
+
"project_name": "ShorseyBeerLeague",
|
4 |
+
"data_path": "Biddls/Onion_News",
|
5 |
+
"train_split": "train",
|
6 |
+
"valid_split": null,
|
7 |
+
"add_eos_token": false,
|
8 |
+
"block_size": 512,
|
9 |
+
"model_max_length": 1024,
|
10 |
+
"padding": "right",
|
11 |
+
"trainer": "default",
|
12 |
+
"use_flash_attention_2": false,
|
13 |
+
"log": "tensorboard",
|
14 |
+
"disable_gradient_checkpointing": false,
|
15 |
+
"logging_steps": -1,
|
16 |
+
"eval_strategy": "epoch",
|
17 |
+
"save_total_limit": 1,
|
18 |
+
"auto_find_batch_size": false,
|
19 |
+
"mixed_precision": "fp16",
|
20 |
+
"lr": 5.00003,
|
21 |
+
"epochs": 3,
|
22 |
+
"batch_size": 16,
|
23 |
+
"warmup_ratio": 0.1,
|
24 |
+
"gradient_accumulation": 4,
|
25 |
+
"optimizer": "adamw_torch",
|
26 |
+
"scheduler": "linear",
|
27 |
+
"weight_decay": 0.0,
|
28 |
+
"max_grad_norm": 1.0,
|
29 |
+
"seed": 42,
|
30 |
+
"chat_template": "none",
|
31 |
+
"quantization": "int4",
|
32 |
+
"target_modules": "all-linear",
|
33 |
+
"merge_adapter": false,
|
34 |
+
"peft": true,
|
35 |
+
"lora_r": 16,
|
36 |
+
"lora_alpha": 32,
|
37 |
+
"lora_dropout": 0.05,
|
38 |
+
"model_ref": null,
|
39 |
+
"dpo_beta": 0.1,
|
40 |
+
"max_prompt_length": 128,
|
41 |
+
"max_completion_length": null,
|
42 |
+
"prompt_text_column": "prompt",
|
43 |
+
"text_column": "text",
|
44 |
+
"rejected_text_column": "rejected_text",
|
45 |
+
"push_to_hub": true,
|
46 |
+
"username": "Wonder-Griffin",
|
47 |
+
"unsloth": false
|
48 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|