2nji commited on
Commit
cf1c573
·
verified ·
1 Parent(s): 03a2de5

Saving model and tokenizer

Browse files
Files changed (2) hide show
  1. README.md +59 -0
  2. adapter_model.safetensors +2 -2
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit
3
+ library_name: transformers
4
+ model_name: sft_qlora_Meta-Llama-3.1-8B
5
+ tags:
6
+ - generated_from_trainer
7
+ - unsloth
8
+ - trl
9
+ - sft
10
+ licence: license
11
+ ---
12
+
13
+ # Model Card for sft_qlora_Meta-Llama-3.1-8B
14
+
15
+ This model is a fine-tuned version of [unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit](https://huggingface.co/unsloth/meta-llama-3.1-8b-unsloth-bnb-4bit).
16
+ It has been trained using [TRL](https://github.com/huggingface/trl).
17
+
18
+ ## Quick start
19
+
20
+ ```python
21
+ from transformers import pipeline
22
+
23
+ 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?"
24
+ generator = pipeline("text-generation", model="2nji/sft_qlora_Meta-Llama-3.1-8B", device="cuda")
25
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
26
+ print(output["generated_text"])
27
+ ```
28
+
29
+ ## Training procedure
30
+
31
+ [<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/_2nji/huggingface/runs/z5295t1h)
32
+
33
+
34
+ This model was trained with SFT.
35
+
36
+ ### Framework versions
37
+
38
+ - TRL: 0.15.2
39
+ - Transformers: 4.48.3
40
+ - Pytorch: 2.6.0
41
+ - Datasets: 3.3.2
42
+ - Tokenizers: 0.21.0
43
+
44
+ ## Citations
45
+
46
+
47
+
48
+ Cite TRL as:
49
+
50
+ ```bibtex
51
+ @misc{vonwerra2022trl,
52
+ title = {{TRL: Transformer Reinforcement Learning}},
53
+ 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},
54
+ year = 2020,
55
+ journal = {GitHub repository},
56
+ publisher = {GitHub},
57
+ howpublished = {\url{https://github.com/huggingface/trl}}
58
+ }
59
+ ```
adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:816aa6dd41fa77b8e754dcdc3d196906c649c7f46dad794f53de0ef1960f17a1
3
- size 167832240
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5713a3757e49c2f02156126644fd5a916928c2a9521946c81bdd58b3bfcb73e
3
+ size 83945744