Text Generation
Transformers
PyTorch
English
RefinedWebModel
gpt
llm
large language model
PAIX
custom_code
text-generation-inference
Instructions to use PAIXAI/Astrid-7B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use PAIXAI/Astrid-7B with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="PAIXAI/Astrid-7B", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("PAIXAI/Astrid-7B", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- vLLM
How to use PAIXAI/Astrid-7B with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "PAIXAI/Astrid-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-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/PAIXAI/Astrid-7B
- SGLang
How to use PAIXAI/Astrid-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-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-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-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-7B", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use PAIXAI/Astrid-7B with Docker Model Runner:
docker model run hf.co/PAIXAI/Astrid-7B
Update README.md
Browse files
README.md
CHANGED
|
@@ -15,7 +15,8 @@ thumbnail: https://static.wixstatic.com/media/bdee4e_d0af74523fa64a998d4cfb894e8
|
|
| 15 |
|
| 16 |
Model Card
|
| 17 |
Summary
|
| 18 |
-
|
|
|
|
| 19 |
It's part of our mission to make AI technology accessible to everyone, focusing on personalization, data privacy, and transparent AI governance.
|
| 20 |
Trained in English, it's a versatile tool for a variety of applications.
|
| 21 |
This model is one of the many models available on our platform, and we currently have a 1B and 7B open-source model.
|
|
|
|
| 15 |
|
| 16 |
Model Card
|
| 17 |
Summary
|
| 18 |
+
The model Astrid-7B-1 architecture includes a RWForCausalLM transformer with word embeddings, a module list of 32 DecoderLayers, and a linear lm_head.
|
| 19 |
+
The DecoderLayer includes an input layer normalization, self-attention mechanism, and a multi-layer perceptron (MLP).
|
| 20 |
It's part of our mission to make AI technology accessible to everyone, focusing on personalization, data privacy, and transparent AI governance.
|
| 21 |
Trained in English, it's a versatile tool for a variety of applications.
|
| 22 |
This model is one of the many models available on our platform, and we currently have a 1B and 7B open-source model.
|