Instructions to use PAIXAI/Astrid-LLama-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PAIXAI/Astrid-LLama-7B with Transformers:

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

pipe = pipeline("text-generation", model="PAIXAI/Astrid-LLama-7B")

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("PAIXAI/Astrid-LLama-7B")
model = AutoModelForCausalLM.from_pretrained("PAIXAI/Astrid-LLama-7B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PAIXAI/Astrid-LLama-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PAIXAI/Astrid-LLama-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PAIXAI/Astrid-LLama-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/PAIXAI/Astrid-LLama-7B

SGLang

How to use PAIXAI/Astrid-LLama-7B 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 "PAIXAI/Astrid-LLama-7B" \
    --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": "PAIXAI/Astrid-LLama-7B",
		"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 "PAIXAI/Astrid-LLama-7B" \
        --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": "PAIXAI/Astrid-LLama-7B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use PAIXAI/Astrid-LLama-7B with Docker Model Runner:
```
docker model run hf.co/PAIXAI/Astrid-LLama-7B
```

Astrid-LLama-7B

Commit History

Feb 14, 2025

06:23
Adding `safetensors` variant of this model⁠

SFconvertbot

Verified signature
8412dff

Aug 21, 2023

23:14
Update README.md

Stevross

d24704d

Aug 17, 2023

01:00
Update README.md

Stevross

fdb5868
00:41
Update README.md

Stevross

22257b0
00:39
Update README.md

Stevross

14c885c

Aug 16, 2023

23:33
Upload h2oai_pipeline.py

Stevross

20f76c7
23:33
Upload model

Stevross

48b6e55
23:16
Upload cfg.yaml

Stevross

59b62c7
23:16
Upload model card

Stevross

896220a
23:16
Upload tokenizer

Stevross

80654a0
23:16
initial commit

Stevross

079c62e

Commit History

Feb 14, 2025

Adding `safetensors` variant of this model⁠

Aug 21, 2023

Update README.md

Aug 17, 2023

Update README.md

Update README.md

Update README.md

Aug 16, 2023

Upload h2oai_pipeline.py

Upload model

Upload cfg.yaml

Upload model card

Upload tokenizer

initial commit