Instructions to use adowu/astral-demo-4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adowu/astral-demo-4 with Transformers:

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

pipe = pipeline("text-generation", model="adowu/astral-demo-4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

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

tokenizer = AutoTokenizer.from_pretrained("adowu/astral-demo-4")
model = AutoModelForCausalLM.from_pretrained("adowu/astral-demo-4", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use adowu/astral-demo-4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adowu/astral-demo-4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adowu/astral-demo-4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/adowu/astral-demo-4

SGLang

How to use adowu/astral-demo-4 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 "adowu/astral-demo-4" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adowu/astral-demo-4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "adowu/astral-demo-4" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adowu/astral-demo-4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use adowu/astral-demo-4 with Docker Model Runner:
```
docker model run hf.co/adowu/astral-demo-4
```

adowu commited on Apr 10, 2024

Commit

e89bb21

verified ·

1 Parent(s): 1fe51e0

Update README.md

Browse files

Files changed (1) hide show

README.md +18 -39

README.md CHANGED Viewed

@@ -1,48 +1,27 @@
 ---
-base_model:
-- adowu/autocodit
-- adowu/autocodit3
-- teknium/OpenHermes-2.5-Mistral-7B
 library_name: transformers
 tags:
-- mergekit
-- merge
 ---
-# merge
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-## Merge Details
-### Merge Method
-This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [adowu/autocodit](https://huggingface.co/adowu/autocodit) as a base.
-### Models Merged
-The following models were included in the merge:
-* [adowu/autocodit3](https://huggingface.co/adowu/autocodit3)
-* [teknium/OpenHermes-2.5-Mistral-7B](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B)
-### Configuration
-The following YAML configuration was used to produce this model:
-```yaml
-models:
-  - model: adowu/autocodit3
-    parameters:
-      density: 1.0
-      weight: 0.8
-  - model: teknium/OpenHermes-2.5-Mistral-7B
-    parameters:
-      density: 0.6
-      weight: 1.0
-merge_method: dare_ties
-base_model: adowu/autocodit
-parameters:
-  normalize: true
-  int8_mask: true
-dtype: bfloat16
-```

 ---
 library_name: transformers
+license: apache-2.0
+language:
+- en
+pipeline_tag: text-generation
 tags:
+- astral
+- demo
+- mistral
 ---
+### astral-demo-4
+## Overview
+astral-demo-4 is a streamlined language model designed for quick demonstrations and insights into NLP capabilities, focusing on text generation and analysis.
+## Features
+- Efficient Text Generation: Quickly produces text for a variety of applications.
+- Compact and Fast: Optimized for speed, making it ideal for demos and prototyping.
+- Prototype Development: Tests ideas in conversational AI and content generation.
+## Performance
+Balances performance with accuracy, providing a practical demonstration of NLP technology in action.
+- **Developed by:** aww
+- **Model type:** Mistral