Instructions to use FlagAlpha/Llama2-Chinese-13b-Chat-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use FlagAlpha/Llama2-Chinese-13b-Chat-4bit with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "question-answering" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("question-answering", model="FlagAlpha/Llama2-Chinese-13b-Chat-4bit")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("FlagAlpha/Llama2-Chinese-13b-Chat-4bit") model = AutoModelForCausalLM.from_pretrained("FlagAlpha/Llama2-Chinese-13b-Chat-4bit", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Could not find a model in....
#5 opened over 2 years ago
by
hubblebubblepig
OSError: Llama2-Chinese-13b-Chat-4bit does not appear to have a file named generation_config.json. Checkout 'https://huggingface.co/Llama2-Chinese-13b-Chat-4bit/main' for available files.
#4 opened about 3 years ago
by
ycjcl868
saved model reload error 'LlamaAttention' object has no attribute 'qkv_proj'
2
#3 opened about 3 years ago
by
lilsyoss
GPTQ Quantization method
#2 opened about 3 years ago
by
gameveloster
乱码
1
#1 opened about 3 years ago
by
l1006986533