Instructions to use EliezerCarvalho/AMALIA-9B-0626-SFT-bnb with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use EliezerCarvalho/AMALIA-9B-0626-SFT-bnb with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="EliezerCarvalho/AMALIA-9B-0626-SFT-bnb")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("EliezerCarvalho/AMALIA-9B-0626-SFT-bnb", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use EliezerCarvalho/AMALIA-9B-0626-SFT-bnb with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "EliezerCarvalho/AMALIA-9B-0626-SFT-bnb"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "EliezerCarvalho/AMALIA-9B-0626-SFT-bnb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/EliezerCarvalho/AMALIA-9B-0626-SFT-bnb

SGLang

How to use EliezerCarvalho/AMALIA-9B-0626-SFT-bnb with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "EliezerCarvalho/AMALIA-9B-0626-SFT-bnb" \
    --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": "EliezerCarvalho/AMALIA-9B-0626-SFT-bnb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

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 "EliezerCarvalho/AMALIA-9B-0626-SFT-bnb" \
        --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": "EliezerCarvalho/AMALIA-9B-0626-SFT-bnb",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use EliezerCarvalho/AMALIA-9B-0626-SFT-bnb with Docker Model Runner:
```
docker model run hf.co/EliezerCarvalho/AMALIA-9B-0626-SFT-bnb
```

EliezerCarvalho commited on Jul 2

Commit

75dda2a

verified ·

1 Parent(s): ec0f48a

Update README.md

Browse files

Files changed (1) hide show

README.md +1 -1

README.md CHANGED Viewed

@@ -26,7 +26,7 @@ quantized_by: EliezerCarvalho
 # AMALIA-9B-0626-SFT-bnb
 > [!NOTE]
-> This repository contains BitsAndBytes conversions of <a href = https://huggingface.co/amalia-llm/AMALIA-9B-0626-SFT> AMALIA-9B-0626-SFT</a>.
 ## Files

 # AMALIA-9B-0626-SFT-bnb
 > [!NOTE]
+> This repository contains BitsAndBytes quantizations of <a href = https://huggingface.co/amalia-llm/AMALIA-9B-0626-SFT> AMALIA-9B-0626-SFT</a>.
 ## Files