Question Answering
Transformers
PyTorch
TensorBoard
English
llama
text-generation
language-agent
web-agent
maths
reasoning
planning
text-generation-inference
Instructions to use ai2lumos/lumos_unified_plan_iterative-13B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ai2lumos/lumos_unified_plan_iterative-13B 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="ai2lumos/lumos_unified_plan_iterative-13B")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("ai2lumos/lumos_unified_plan_iterative-13B") model = AutoModelForCausalLM.from_pretrained("ai2lumos/lumos_unified_plan_iterative-13B", device_map="auto") - Notebooks
- Google Colab
- Kaggle
File size: 135 Bytes
7f453e7 | 1 2 3 4 | version https://git-lfs.github.com/spec/v1
oid sha256:fbee8f7b2243818ab96cad650744f7a65d3e0065ad962dab815d816ca6aa3c26
size 1245250717
|