yitzshapiro
commited on
Commit
•
0732f8e
1
Parent(s):
c2e9a30
Upload folder using huggingface_hub
Browse files- .gitattributes +3 -35
- README.md +46 -0
- adapter_config.json +38 -0
- adapter_model.safetensors +3 -0
- added_tokens.json +5 -0
- merges.txt +0 -0
- runs/Jul01_02-36-52_46920f1b8ec3/events.out.tfevents.1719801439.46920f1b8ec3.21376.0 +3 -0
- special_tokens_map.json +20 -0
- tokenizer.json +0 -0
- tokenizer_config.json +43 -0
- training_args.bin +3 -0
- training_params.json +48 -0
- vocab.json +0 -0
.gitattributes
CHANGED
@@ -1,35 +1,3 @@
|
|
1 |
-
|
2 |
-
|
3 |
-
|
4 |
-
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
5 |
-
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
6 |
-
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
-
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
-
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
-
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
-
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
-
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
12 |
-
*.model filter=lfs diff=lfs merge=lfs -text
|
13 |
-
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
14 |
-
*.npy filter=lfs diff=lfs merge=lfs -text
|
15 |
-
*.npz filter=lfs diff=lfs merge=lfs -text
|
16 |
-
*.onnx filter=lfs diff=lfs merge=lfs -text
|
17 |
-
*.ot filter=lfs diff=lfs merge=lfs -text
|
18 |
-
*.parquet filter=lfs diff=lfs merge=lfs -text
|
19 |
-
*.pb filter=lfs diff=lfs merge=lfs -text
|
20 |
-
*.pickle filter=lfs diff=lfs merge=lfs -text
|
21 |
-
*.pkl filter=lfs diff=lfs merge=lfs -text
|
22 |
-
*.pt filter=lfs diff=lfs merge=lfs -text
|
23 |
-
*.pth filter=lfs diff=lfs merge=lfs -text
|
24 |
-
*.rar filter=lfs diff=lfs merge=lfs -text
|
25 |
-
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
26 |
-
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
27 |
-
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
28 |
-
*.tar filter=lfs diff=lfs merge=lfs -text
|
29 |
-
*.tflite filter=lfs diff=lfs merge=lfs -text
|
30 |
-
*.tgz filter=lfs diff=lfs merge=lfs -text
|
31 |
-
*.wasm filter=lfs diff=lfs merge=lfs -text
|
32 |
-
*.xz filter=lfs diff=lfs merge=lfs -text
|
33 |
-
*.zip filter=lfs diff=lfs merge=lfs -text
|
34 |
-
*.zst filter=lfs diff=lfs merge=lfs -text
|
35 |
-
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
1 |
+
adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text
|
2 |
+
runs/Jul01_02-36-52_46920f1b8ec3/events.out.tfevents.1719801439.46920f1b8ec3.21376.0 filter=lfs diff=lfs merge=lfs -text
|
3 |
+
training_args.bin filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
README.md
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation-inference
|
5 |
+
- text-generation
|
6 |
+
- peft
|
7 |
+
library_name: transformers
|
8 |
+
base_model: Qwen/Qwen2-7B-Instruct
|
9 |
+
widget:
|
10 |
+
- messages:
|
11 |
+
- role: user
|
12 |
+
content: What is your favorite condiment?
|
13 |
+
license: other
|
14 |
+
---
|
15 |
+
|
16 |
+
# Model Trained Using AutoTrain
|
17 |
+
|
18 |
+
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
19 |
+
|
20 |
+
# Usage
|
21 |
+
|
22 |
+
```python
|
23 |
+
|
24 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
25 |
+
|
26 |
+
model_path = "PATH_TO_THIS_REPO"
|
27 |
+
|
28 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
29 |
+
model = AutoModelForCausalLM.from_pretrained(
|
30 |
+
model_path,
|
31 |
+
device_map="auto",
|
32 |
+
torch_dtype='auto'
|
33 |
+
).eval()
|
34 |
+
|
35 |
+
# Prompt content: "hi"
|
36 |
+
messages = [
|
37 |
+
{"role": "user", "content": "hi"}
|
38 |
+
]
|
39 |
+
|
40 |
+
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
41 |
+
output_ids = model.generate(input_ids.to('cuda'))
|
42 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
43 |
+
|
44 |
+
# Model response: "Hello! How can I assist you today?"
|
45 |
+
print(response)
|
46 |
+
```
|
adapter_config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"alpha_pattern": {},
|
3 |
+
"auto_mapping": null,
|
4 |
+
"base_model_name_or_path": "Qwen/Qwen2-7B-Instruct",
|
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": [
|
18 |
+
"classifier",
|
19 |
+
"score"
|
20 |
+
],
|
21 |
+
"peft_type": "LORA",
|
22 |
+
"r": 16,
|
23 |
+
"rank_pattern": {},
|
24 |
+
"revision": null,
|
25 |
+
"target_modules": [
|
26 |
+
"down_proj",
|
27 |
+
"o_proj",
|
28 |
+
"gate_proj",
|
29 |
+
"q_proj",
|
30 |
+
"v_proj",
|
31 |
+
"k_proj",
|
32 |
+
"score",
|
33 |
+
"up_proj"
|
34 |
+
],
|
35 |
+
"task_type": "SEQ_CLS",
|
36 |
+
"use_dora": false,
|
37 |
+
"use_rslora": false
|
38 |
+
}
|
adapter_model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a6412a3257dd6b0625bfe7e18b17a14831d3a49de2eae9e6a5812331a29752f
|
3 |
+
size 2336235176
|
added_tokens.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|endoftext|>": 151643,
|
3 |
+
"<|im_end|>": 151645,
|
4 |
+
"<|im_start|>": 151644
|
5 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
runs/Jul01_02-36-52_46920f1b8ec3/events.out.tfevents.1719801439.46920f1b8ec3.21376.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a65d9f6ceecb024bc97544b86fa76f0c32e47a1af783b011574fc3c5b12ba47
|
3 |
+
size 7005
|
special_tokens_map.json
ADDED
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|im_start|>",
|
4 |
+
"<|im_end|>"
|
5 |
+
],
|
6 |
+
"eos_token": {
|
7 |
+
"content": "<|im_end|>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"pad_token": {
|
14 |
+
"content": "<|endoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
}
|
20 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"151643": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": false,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
},
|
12 |
+
"151644": {
|
13 |
+
"content": "<|im_start|>",
|
14 |
+
"lstrip": false,
|
15 |
+
"normalized": false,
|
16 |
+
"rstrip": false,
|
17 |
+
"single_word": false,
|
18 |
+
"special": true
|
19 |
+
},
|
20 |
+
"151645": {
|
21 |
+
"content": "<|im_end|>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false,
|
26 |
+
"special": true
|
27 |
+
}
|
28 |
+
},
|
29 |
+
"additional_special_tokens": [
|
30 |
+
"<|im_start|>",
|
31 |
+
"<|im_end|>"
|
32 |
+
],
|
33 |
+
"bos_token": null,
|
34 |
+
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
35 |
+
"clean_up_tokenization_spaces": false,
|
36 |
+
"eos_token": "<|im_end|>",
|
37 |
+
"errors": "replace",
|
38 |
+
"model_max_length": 2048,
|
39 |
+
"pad_token": "<|endoftext|>",
|
40 |
+
"split_special_tokens": false,
|
41 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
42 |
+
"unk_token": null
|
43 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c1e99f9113e14a041284fb7ea7d84b8f41b27c2cde6cd98dae255919217a3c3f
|
3 |
+
size 5176
|
training_params.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "Qwen/Qwen2-7B-Instruct",
|
3 |
+
"project_name": "Qwen2-7B-Instruct-90s-Commercials-v2",
|
4 |
+
"data_path": "Qwen2-7B-Instruct-90s-Commercials-v2/autotrain-data",
|
5 |
+
"train_split": "train",
|
6 |
+
"valid_split": null,
|
7 |
+
"add_eos_token": true,
|
8 |
+
"block_size": 1024,
|
9 |
+
"model_max_length": 2048,
|
10 |
+
"padding": "right",
|
11 |
+
"trainer": "reward",
|
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": 0.00015,
|
21 |
+
"epochs": 3,
|
22 |
+
"batch_size": 10,
|
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": "autotrain_prompt",
|
43 |
+
"text_column": "autotrain_text",
|
44 |
+
"rejected_text_column": "autotrain_rejected_text",
|
45 |
+
"push_to_hub": true,
|
46 |
+
"username": "yitzshapiro",
|
47 |
+
"unsloth": false
|
48 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|