dvilasuero/databricks-dolly-15k-es-deepl
Viewer โข Updated โข 15k โข 13 โข 2
How to use mrm8488/dolloom with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="mrm8488/dolloom") # Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("mrm8488/dolloom", dtype="auto")How to use mrm8488/dolloom with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mrm8488/dolloom"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "mrm8488/dolloom",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/mrm8488/dolloom
How to use mrm8488/dolloom with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "mrm8488/dolloom" \
--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": "mrm8488/dolloom",
"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 "mrm8488/dolloom" \
--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": "mrm8488/dolloom",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use mrm8488/dolloom with Docker Model Runner:
docker model run hf.co/mrm8488/dolloom
This adapter was created with the PEFT library and allowed the base model BigScience/BLOOMz 7B1 to be fine-tuned on the Dolly's Dataset (tanslated to Spanish) by using the method LoRA.
Instruction Tuned version of BigScience Large Open-science Open-access Multilingual.
TBA
TBA
TBA
TBA
@misc {manuel_romero_2023,
author = { {Manuel Romero} },
title = { dolloom (Revision 599b95a) },
year = 2023,
url = { https://huggingface.co/mrm8488/dolloom },
doi = { 10.57967/hf/0540 },
publisher = { Hugging Face }
}