Upload folder using huggingface_hub
Browse files- README.md +47 -0
- config.json +39 -0
- generation_config.json +6 -0
- merges.txt +0 -0
- model.safetensors +3 -0
- runs/Aug27_19-58-19_r-dtumkaya-autotrain-advanced-slm-v9sa1bek-fe930-j1sy4/events.out.tfevents.1724788704.r-dtumkaya-autotrain-advanced-slm-v9sa1bek-fe930-j1sy4.162.0 +2 -2
- special_tokens_map.json +6 -0
- tokenizer.json +0 -0
- tokenizer_config.json +21 -0
- training_args.bin +3 -0
- training_params.json +48 -0
- vocab.json +0 -0
README.md
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- autotrain
|
4 |
+
- text-generation-inference
|
5 |
+
- text-generation
|
6 |
+
library_name: transformers
|
7 |
+
base_model: openai-community/gpt2
|
8 |
+
widget:
|
9 |
+
- messages:
|
10 |
+
- role: user
|
11 |
+
content: What is your favorite condiment?
|
12 |
+
license: other
|
13 |
+
datasets:
|
14 |
+
- borakaragul/wikitext2-raw-MIA
|
15 |
+
---
|
16 |
+
|
17 |
+
# Model Trained Using AutoTrain
|
18 |
+
|
19 |
+
This model was trained using AutoTrain. For more information, please visit [AutoTrain](https://hf.co/docs/autotrain).
|
20 |
+
|
21 |
+
# Usage
|
22 |
+
|
23 |
+
```python
|
24 |
+
|
25 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
26 |
+
|
27 |
+
model_path = "PATH_TO_THIS_REPO"
|
28 |
+
|
29 |
+
tokenizer = AutoTokenizer.from_pretrained(model_path)
|
30 |
+
model = AutoModelForCausalLM.from_pretrained(
|
31 |
+
model_path,
|
32 |
+
device_map="auto",
|
33 |
+
torch_dtype='auto'
|
34 |
+
).eval()
|
35 |
+
|
36 |
+
# Prompt content: "hi"
|
37 |
+
messages = [
|
38 |
+
{"role": "user", "content": "hi"}
|
39 |
+
]
|
40 |
+
|
41 |
+
input_ids = tokenizer.apply_chat_template(conversation=messages, tokenize=True, add_generation_prompt=True, return_tensors='pt')
|
42 |
+
output_ids = model.generate(input_ids.to('cuda'))
|
43 |
+
response = tokenizer.decode(output_ids[0][input_ids.shape[1]:], skip_special_tokens=True)
|
44 |
+
|
45 |
+
# Model response: "Hello! How can I assist you today?"
|
46 |
+
print(response)
|
47 |
+
```
|
config.json
ADDED
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openai-community/gpt2",
|
3 |
+
"activation_function": "gelu_new",
|
4 |
+
"architectures": [
|
5 |
+
"GPT2LMHeadModel"
|
6 |
+
],
|
7 |
+
"attn_pdrop": 0.1,
|
8 |
+
"bos_token_id": 50256,
|
9 |
+
"embd_pdrop": 0.1,
|
10 |
+
"eos_token_id": 50256,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"layer_norm_epsilon": 1e-05,
|
13 |
+
"model_type": "gpt2",
|
14 |
+
"n_ctx": 1024,
|
15 |
+
"n_embd": 768,
|
16 |
+
"n_head": 12,
|
17 |
+
"n_inner": null,
|
18 |
+
"n_layer": 12,
|
19 |
+
"n_positions": 1024,
|
20 |
+
"reorder_and_upcast_attn": false,
|
21 |
+
"resid_pdrop": 0.1,
|
22 |
+
"scale_attn_by_inverse_layer_idx": false,
|
23 |
+
"scale_attn_weights": true,
|
24 |
+
"summary_activation": null,
|
25 |
+
"summary_first_dropout": 0.1,
|
26 |
+
"summary_proj_to_labels": true,
|
27 |
+
"summary_type": "cls_index",
|
28 |
+
"summary_use_proj": true,
|
29 |
+
"task_specific_params": {
|
30 |
+
"text-generation": {
|
31 |
+
"do_sample": true,
|
32 |
+
"max_length": 50
|
33 |
+
}
|
34 |
+
},
|
35 |
+
"torch_dtype": "float32",
|
36 |
+
"transformers_version": "4.44.1",
|
37 |
+
"use_cache": true,
|
38 |
+
"vocab_size": 50257
|
39 |
+
}
|
generation_config.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 50256,
|
4 |
+
"eos_token_id": 50256,
|
5 |
+
"transformers_version": "4.44.1"
|
6 |
+
}
|
merges.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d21f7cfc4f792479c6cf8c23dd9e25a693e7c90b05155f99a5826301a66ef01e
|
3 |
+
size 497774208
|
runs/Aug27_19-58-19_r-dtumkaya-autotrain-advanced-slm-v9sa1bek-fe930-j1sy4/events.out.tfevents.1724788704.r-dtumkaya-autotrain-advanced-slm-v9sa1bek-fe930-j1sy4.162.0
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:b405ca6970f39b15edc250e544444ac1d87ef733a41453312d58b3f2827f36ec
|
3 |
+
size 10907
|
special_tokens_map.json
ADDED
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": "<|endoftext|>",
|
3 |
+
"eos_token": "<|endoftext|>",
|
4 |
+
"pad_token": "<|endoftext|>",
|
5 |
+
"unk_token": "<|endoftext|>"
|
6 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,21 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_prefix_space": false,
|
3 |
+
"added_tokens_decoder": {
|
4 |
+
"50256": {
|
5 |
+
"content": "<|endoftext|>",
|
6 |
+
"lstrip": false,
|
7 |
+
"normalized": true,
|
8 |
+
"rstrip": false,
|
9 |
+
"single_word": false,
|
10 |
+
"special": true
|
11 |
+
}
|
12 |
+
},
|
13 |
+
"bos_token": "<|endoftext|>",
|
14 |
+
"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 %}",
|
15 |
+
"clean_up_tokenization_spaces": true,
|
16 |
+
"eos_token": "<|endoftext|>",
|
17 |
+
"model_max_length": 1024,
|
18 |
+
"pad_token": "<|endoftext|>",
|
19 |
+
"tokenizer_class": "GPT2Tokenizer",
|
20 |
+
"unk_token": "<|endoftext|>"
|
21 |
+
}
|
training_args.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26f61bd8142be9a4501bea0ba185a9bc572dbeef7d3b418d8713d0a0efabae5f
|
3 |
+
size 5496
|
training_params.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"model": "openai-community/gpt2",
|
3 |
+
"project_name": "autotrain-gpt2-5-slm",
|
4 |
+
"data_path": "borakaragul/wikitext2-raw-MIA",
|
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": "sft",
|
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": 0.0001,
|
21 |
+
"epochs": 5,
|
22 |
+
"batch_size": 2,
|
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": false,
|
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": "dtumkaya",
|
47 |
+
"unsloth": false
|
48 |
+
}
|
vocab.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|