databricks/databricks-dolly-15k
Viewer • Updated • 15k • 41.8k • 994
How to use alup/agrimi-7.5B-dolly with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="alup/agrimi-7.5B-dolly") # Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained("alup/agrimi-7.5B-dolly")
model = AutoModelForCausalLM.from_pretrained("alup/agrimi-7.5B-dolly")How to use alup/agrimi-7.5B-dolly with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "alup/agrimi-7.5B-dolly"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "alup/agrimi-7.5B-dolly",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/alup/agrimi-7.5B-dolly
How to use alup/agrimi-7.5B-dolly with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "alup/agrimi-7.5B-dolly" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "alup/agrimi-7.5B-dolly",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker run --gpus all \
--shm-size 32g \
-p 30000:30000 \
-v ~/.cache/huggingface:/root/.cache/huggingface \
--env "HF_TOKEN=<secret>" \
--ipc=host \
lmsysorg/sglang:latest \
python3 -m sglang.launch_server \
--model-path "alup/agrimi-7.5B-dolly" \
--host 0.0.0.0 \
--port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "alup/agrimi-7.5B-dolly",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use alup/agrimi-7.5B-dolly with Docker Model Runner:
docker model run hf.co/alup/agrimi-7.5B-dolly
This model is a finetuned (SFT) version of Facbook xglm-7.5B using a machine translated version of the dataset databricks-dolly-15k in Greek language! The purpose is to demonstrate the ability of the specific pretrained model to adapt to instruction following mode by using a relatively small dataset such as the databricks-dolly-15k.