Instructions to use ibm-granite/granitelib-rag-r1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Granite Library
How to use ibm-granite/granitelib-rag-r1.0 with Granite Library:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
fix: change to new directory ordering scheme
Browse filesSigned-off-by: Khoi-Nguyen Tran <kndtran@ibm.com>
- run_vllm.sh +2 -2
run_vllm.sh
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
#! /bin/bash
|
| 2 |
|
| 3 |
################################################################################
|
| 4 |
-
# Shell script that starts a copy of vLLM with a base model plus all the
|
| 5 |
# available LoRA adapters in this repository.
|
| 6 |
#
|
| 7 |
# To run this script:
|
|
@@ -25,7 +25,7 @@ for item in "."/*; do
|
|
| 25 |
# Remove the "./"
|
| 26 |
name=$(basename -- "${item}")
|
| 27 |
if [ -d "./${name}/${BASE_MODEL_NAME}/lora" ]; then
|
| 28 |
-
LORAS+="${name}=./${name}/
|
| 29 |
fi
|
| 30 |
done
|
| 31 |
|
|
|
|
| 1 |
#! /bin/bash
|
| 2 |
|
| 3 |
################################################################################
|
| 4 |
+
# Shell script that starts a copy of vLLM with a base model plus all the
|
| 5 |
# available LoRA adapters in this repository.
|
| 6 |
#
|
| 7 |
# To run this script:
|
|
|
|
| 25 |
# Remove the "./"
|
| 26 |
name=$(basename -- "${item}")
|
| 27 |
if [ -d "./${name}/${BASE_MODEL_NAME}/lora" ]; then
|
| 28 |
+
LORAS+="${name}=./${name}/${BASE_MODEL_NAME}/lora "
|
| 29 |
fi
|
| 30 |
done
|
| 31 |
|