End of training
Browse files
README.md
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: HuggingFaceTB/SmolLM2-135M
|
3 |
+
library_name: transformers
|
4 |
+
model_name: SmolLM2-FT-orca
|
5 |
+
tags:
|
6 |
+
- generated_from_trainer
|
7 |
+
- smol-course
|
8 |
+
- module_1
|
9 |
+
- trl
|
10 |
+
- sft
|
11 |
+
licence: license
|
12 |
+
---
|
13 |
+
|
14 |
+
# Model Card for SmolLM2-FT-orca
|
15 |
+
|
16 |
+
This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M](https://huggingface.co/HuggingFaceTB/SmolLM2-135M).
|
17 |
+
It has been trained using [TRL](https://github.com/huggingface/trl).
|
18 |
+
|
19 |
+
## Quick start
|
20 |
+
|
21 |
+
```python
|
22 |
+
from transformers import pipeline
|
23 |
+
|
24 |
+
question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
|
25 |
+
generator = pipeline("text-generation", model="saikatkumardey/SmolLM2-FT-orca", device="cuda")
|
26 |
+
output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
|
27 |
+
print(output["generated_text"])
|
28 |
+
```
|
29 |
+
|
30 |
+
## Training procedure
|
31 |
+
|
32 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/saikatkumardey-gojek/huggingface/runs/38jruuyg)
|
33 |
+
|
34 |
+
|
35 |
+
This model was trained with SFT.
|
36 |
+
|
37 |
+
### Framework versions
|
38 |
+
|
39 |
+
- TRL: 0.13.0
|
40 |
+
- Transformers: 4.47.1
|
41 |
+
- Pytorch: 2.5.1+cu121
|
42 |
+
- Datasets: 3.2.0
|
43 |
+
- Tokenizers: 0.21.0
|
44 |
+
|
45 |
+
## Citations
|
46 |
+
|
47 |
+
|
48 |
+
|
49 |
+
Cite TRL as:
|
50 |
+
|
51 |
+
```bibtex
|
52 |
+
@misc{vonwerra2022trl,
|
53 |
+
title = {{TRL: Transformer Reinforcement Learning}},
|
54 |
+
author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
|
55 |
+
year = 2020,
|
56 |
+
journal = {GitHub repository},
|
57 |
+
publisher = {GitHub},
|
58 |
+
howpublished = {\url{https://github.com/huggingface/trl}}
|
59 |
+
}
|
60 |
+
```
|
generation_config.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_from_model_config": true,
|
3 |
+
"bos_token_id": 1,
|
4 |
+
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 2,
|
6 |
+
"transformers_version": "4.47.1"
|
7 |
+
}
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 538090408
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:670b6d8de2c4dd8aed22d21b3beec5cd95ddda98ac723078d011d0527cdb16b2
|
3 |
size 538090408
|
runs/Dec31_04-18-31_59a9167498fe/events.out.tfevents.1735618738.59a9167498fe.1830.0
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 sha256:49142f5e99f76ef6f9b6a04d9dd70341ccf467c85907b1d1fcaea901daeba38f
|
3 |
+
size 72610
|