Question Answering
Transformers
Safetensors
English
mistral
text-generation
PEFT
sft
TensorBoard
Safetensors
trl
generated_from_trainer 4-bit
precision
text-generation-inference
4-bit precision
gptq
Instructions to use Feluda/Zephyr-7b-QnA with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Feluda/Zephyr-7b-QnA 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="Feluda/Zephyr-7b-QnA")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("Feluda/Zephyr-7b-QnA") model = AutoModelForCausalLM.from_pretrained("Feluda/Zephyr-7b-QnA", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from Feluda/Zephyr-7b-QnA: direct link, hf CLI and curl.
- Browser
- Download file 4.28 kB
-
https://huggingface.co/Feluda/Zephyr-7b-QnA/resolve/main/training_args.bin
- Command line
-
hf download hf://Feluda/Zephyr-7b-QnA/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/Feluda/Zephyr-7b-QnA/resolve/main/training_args.bin
4.28 kB
- Xet hash:
- aa6f81402111055ae02dcf21fc2e4fe58f23dfa0228090cdb2e87f2401d7be7c
- Size of remote file:
- 4.28 kB
- SHA256:
- d43f44d6182ffc685a660dc94ca6669160da174755b632554ea18d1625272290
路
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.