Instructions to use AstroMLab/astrollama-3-8b-base_aic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AstroMLab/astrollama-3-8b-base_aic with Transformers:

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

pipe = pipeline("text-generation", model="AstroMLab/astrollama-3-8b-base_aic")

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

tokenizer = AutoTokenizer.from_pretrained("AstroMLab/astrollama-3-8b-base_aic")
model = AutoModelForCausalLM.from_pretrained("AstroMLab/astrollama-3-8b-base_aic", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AstroMLab/astrollama-3-8b-base_aic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AstroMLab/astrollama-3-8b-base_aic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AstroMLab/astrollama-3-8b-base_aic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AstroMLab/astrollama-3-8b-base_aic

SGLang

How to use AstroMLab/astrollama-3-8b-base_aic 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 "AstroMLab/astrollama-3-8b-base_aic" \
    --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": "AstroMLab/astrollama-3-8b-base_aic",
		"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 "AstroMLab/astrollama-3-8b-base_aic" \
        --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": "AstroMLab/astrollama-3-8b-base_aic",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AstroMLab/astrollama-3-8b-base_aic with Docker Model Runner:
```
docker model run hf.co/AstroMLab/astrollama-3-8b-base_aic
```

tingyuansen commited on Nov 16, 2024

Commit

7786a5f

verified ·

1 Parent(s): 7810a9c

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -2

README.md CHANGED Viewed

@@ -33,7 +33,7 @@ AstroLLaMA-3-8B is a specialized base language model for astronomy, developed by
   - Cosine decay schedule for learning rate reduction
   - Training duration: 1 epoch
 - **Primary Use**: Next token prediction for astronomy-related text generation and analysis
-- **Reference**: Pan et al. 2024 [Link to be added]
 ## Generating text from a prompt
@@ -73,10 +73,11 @@ print(generated_text[0]['generated_text'])
 A key limitation identified during the development of this model is that training solely on astro-ph data may not be sufficient to significantly improve performance over the base model, especially for the already highly performant LLaMA-3 series. This suggests that to achieve substantial gains, future iterations may need to incorporate a broader range of high-quality astronomical data beyond arXiv, such as textbooks, Wikipedia, and curated summaries.
-Here's a performance comparison chart based upon the astronomical benchmarking Q&A as described in [Ting et al. 2024](https://arxiv.org/abs/2407.11194), and Pan et al. 2024:
 | Model | Score (%) |
 |-------|-----------|
 | LLaMA-3.1-8B | 73.7 |
 | LLaMA-3-8B | 72.9 |
 | **<span style="color:green">AstroLLaMA-3-8B-Base_AIC (AstroMLab)</span>** | **<span style="color:green">71.9</span>** |

   - Cosine decay schedule for learning rate reduction
   - Training duration: 1 epoch
 - **Primary Use**: Next token prediction for astronomy-related text generation and analysis
+- **Reference**: [Pan et al. 2024](https://arxiv.org/abs/2409.19750)
 ## Generating text from a prompt
 A key limitation identified during the development of this model is that training solely on astro-ph data may not be sufficient to significantly improve performance over the base model, especially for the already highly performant LLaMA-3 series. This suggests that to achieve substantial gains, future iterations may need to incorporate a broader range of high-quality astronomical data beyond arXiv, such as textbooks, Wikipedia, and curated summaries.
+Here's a performance comparison chart based upon the astronomical benchmarking Q&A as described in [Ting et al. 2024](https://arxiv.org/abs/2407.11194):
 | Model | Score (%) |
 |-------|-----------|
+| **AstroSage-LLaMA-3.1-8B (AstroMLab)** | **80.9** |
 | LLaMA-3.1-8B | 73.7 |
 | LLaMA-3-8B | 72.9 |
 | **<span style="color:green">AstroLLaMA-3-8B-Base_AIC (AstroMLab)</span>** | **<span style="color:green">71.9</span>** |