Question Answering
Transformers
Safetensors
English
llama
text-generation
code
text-generation-inference
Instructions to use apu20/Llama-3.2-3B-Instruct_Tele with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use apu20/Llama-3.2-3B-Instruct_Tele 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="apu20/Llama-3.2-3B-Instruct_Tele")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("apu20/Llama-3.2-3B-Instruct_Tele") model = AutoModelForCausalLM.from_pretrained("apu20/Llama-3.2-3B-Instruct_Tele", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from apu20/Llama-3.2-3B-Instruct_Tele: direct link, hf CLI and curl.
- Browser
- Download file 17.2 MB
-
https://huggingface.co/apu20/Llama-3.2-3B-Instruct_Tele/resolve/main/tokenizer.json
- Command line
-
hf download hf://apu20/Llama-3.2-3B-Instruct_Tele/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/apu20/Llama-3.2-3B-Instruct_Tele/resolve/main/tokenizer.json
17.2 MB
- Xet hash:
- da070f8626ee36c29d81d14f7a18b0a943ba6477aaa86b433d0f865f98bf8392
- Size of remote file:
- 17.2 MB
- SHA256:
- 6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.