Downloads · 30 days
214
0% of all-time downloads
Baichuan2-7B-Base-LLaMAfied
hiyouga/Baichuan2-7B-Base-LLaMAfied
Baichuan2-7B-Base-LLaMAfied is a text generation model from hiyouga. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as other.
This is the LLaMAfied version of Baichuan2-7B-Base model by Baichuan Inc.
All-time downloads
59.5K
Public
Repo size
30 GB
Likes
7
Public
Repo makeup
Click a slice to open those files.
.bin15 GB · 100%
At a glance
- Task
- Text Generation
- Library
- transformers
- License
- other
- Model type
- llama
- Access
- Public
- Created
- Sep 8, 2023
- Updated
- Nov 18, 2023
- SHA
- 786dc3df
Try a prompt
Model card
From the Hugging Face model README
This is the LLaMAfied version of Baichuan2-7B-Base model by Baichuan Inc.
This model is converted with https://github.com/hiyouga/LLaMA-Factory/blob/main/tests/llamafy_baichuan2.py
You may use this model for fine-tuning in downstream tasks, we recommend using our efficient fine-tuning toolkit. https://github.com/hiyouga/LLaMA-Factory
- Developed by: Baichuan Inc.
- Language(s) (NLP): Chinese/English
- License: Baichuan2 License
Usage:
from transformers import AutoModelForCausalLM, AutoTokenizer
tokenizer = AutoTokenizer.from_pretrained("hiyouga/Baichuan2-7B-Base-LLaMAfied", use_fast=False)
model = AutoModelForCausalLM.from_pretrained("hiyouga/Baichuan2-7B-Base-LLaMAfied").cuda()
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 42.83 |
| ARC (25-shot) | 49.57 |
| HellaSwag (10-shot) | 73.45 |
| MMLU (5-shot) | 54.86 |
| TruthfulQA (0-shot) | 37.54 |
| Winogrande (5-shot) | 70.72 |
| GSM8K (5-shot) | 7.81 |
| DROP (3-shot) | 5.85 |
- Task
- Text Generation
- Library
- transformers
- Type
- llama
- License
- other
- Languages
- en, zh
- Created
- Sep 8, 2023
- Updated
- Nov 18, 2023