bofenghuang commited on
Commit
a8d721b
1 Parent(s): 252ab53

Initial commit

Browse files
.gitignore ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ checkpoint-*/
2
+
3
+ tmp*
README.md ADDED
@@ -0,0 +1,55 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: bigscience-bloom-rail-1.0
3
+ language:
4
+ - fr
5
+ pipeline_tag: text-generation
6
+ library_name: transformers
7
+ tags:
8
+ - alpaca
9
+ - bloom
10
+ - LLM
11
+ datasets:
12
+ - tatsu-lab/alpaca
13
+ inference: false
14
+ ---
15
+
16
+ <p align="center" width="100%">
17
+ <img src="https://huggingface.co/bofenghuang/vigogne-lora-bloom-7b1/resolve/main/vigogne_logo.png" alt="Vigogne" style="width: 40%; min-width: 300px; display: block; margin: auto;">
18
+ </p>
19
+
20
+ # Vigogne-LoRA-BLOOM-7b1: A French Instruct BLOOM Model
21
+
22
+ Vigogne-LoRA-BLOOM-7b1 is a [bigscience/bloom-7b1](https://huggingface.co/bigscience/bloom-7b1) model fine-tuned on the translated [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca) dataset to follow the 🇫🇷 French instructions.
23
+
24
+ For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne
25
+
26
+ **Usage and License Notices**: Same as [Stanford Alpaca](https://github.com/tatsu-lab/stanford_alpaca), Vigogne is intended and licensed for research use only. The dataset is CC BY NC 4.0 (allowing only non-commercial use) and models trained using the dataset should not be used outside of research purposes.
27
+
28
+ ## Usage
29
+
30
+ This repo only contains the low-rank adapter. In order to access the complete model, you also need to load the base LLM model and tokenizer.
31
+
32
+ ```python
33
+ from peft import PeftModel
34
+ from transformers import AutoModelForCausalLM, AutoTokenizer
35
+
36
+ tokenizer = AutoTokenizer.from_pretrained("bigscience/bloom-7b1"")
37
+ model = AutoModelForCausalLM.from_pretrained(
38
+ "bigscience/bloom-7b1"",
39
+ load_in_8bit=True,
40
+ device_map="auto",
41
+ )
42
+ model = PeftModel.from_pretrained(model, "bofenghuang/vigogne-lora-bloom-7b1")
43
+ ```
44
+
45
+ You can infer this model by using the following Google Colab Notebook.
46
+
47
+ <a href="https://colab.research.google.com/github/bofenghuang/vigogne/blob/main/infer.ipynb" target="_blank"><img src="https://colab.research.google.com/assets/colab-badge.svg" alt="Open In Colab"/></a>
48
+
49
+ ## Limitations
50
+
51
+ Vigogne is still under development, and there are many limitations that have to be addressed. Please note that it is possible that the model generates harmful or biased content, incorrect information or generally unhelpful answers.
52
+
53
+ ## Next Steps
54
+
55
+ - Add output examples
adapter_config.json ADDED
@@ -0,0 +1,21 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "base_model_name_or_path": "bigscience/bloom-7b1",
3
+ "bias": "none",
4
+ "enable_lora": [
5
+ true,
6
+ false,
7
+ true
8
+ ],
9
+ "fan_in_fan_out": true,
10
+ "inference_mode": true,
11
+ "lora_alpha": 32,
12
+ "lora_dropout": 0.05,
13
+ "merge_weights": false,
14
+ "modules_to_save": null,
15
+ "peft_type": "LORA",
16
+ "r": 16,
17
+ "target_modules": [
18
+ "query_key_value"
19
+ ],
20
+ "task_type": "CAUSAL_LM"
21
+ }
adapter_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a930cc01412c7c142e01c8e947f6480201c7df29b62a80bdb6dda847f83d8d7b
3
+ size 31479717
runs/Mar26_00-12-34_koios.zaion.ai/1679785954.4135473/events.out.tfevents.1679785954.koios.zaion.ai ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:06cabb35dd7abcaf75a82b19399ea7d6c5bbddaa10a0d1bbdd7352edc6af9ccc
3
+ size 5569
runs/Mar26_00-12-34_koios.zaion.ai/events.out.tfevents.1679785954.koios.zaion.ai ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d662bcd78d8c45c8c269764975563ddd39bd0980484741a4529d1f1af79d520d
3
+ size 13022
vigogne_logo.png ADDED