BH-LLM-Basic
Collection
BH-LLM temeljni modeli za bosanski. Nase: bh-llm-{gen}-{velicina}. Gen 1 u pripremi. β’ 3 items β’ Updated
How to use BH-Language-AI/bh-llm-1-4b with Transformers:
# Use a pipeline as a high-level helper
from transformers import pipeline
pipe = pipeline("text-generation", model="BH-Language-AI/bh-llm-1-4b") # pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("BH-Language-AI/bh-llm-1-4b", device_map="auto")How to use BH-Language-AI/bh-llm-1-4b with vLLM:
# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "BH-Language-AI/bh-llm-1-4b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
-H "Content-Type: application/json" \
--data '{
"model": "BH-Language-AI/bh-llm-1-4b",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'docker model run hf.co/BH-Language-AI/bh-llm-1-4b
How to use BH-Language-AI/bh-llm-1-4b with SGLang:
# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
--model-path "BH-Language-AI/bh-llm-1-4b" \
--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": "BH-Language-AI/bh-llm-1-4b",
"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 "BH-Language-AI/bh-llm-1-4b" \
--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": "BH-Language-AI/bh-llm-1-4b",
"prompt": "Once upon a time,",
"max_tokens": 512,
"temperature": 0.5
}'How to use BH-Language-AI/bh-llm-1-4b with Docker Model Runner:
docker model run hf.co/BH-Language-AI/bh-llm-1-4b
Temeljni jeziΔki model za bosanski, generacija 1. Tezine ne postoje β ovo je projektna kartica.
bh-llm-{generacija}-{velicina} (ista shema kao BH-Decision)