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

Libraries

How to use ConvexAI/Metabird-7B with Transformers:

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

pipe = pipeline("text-generation", model="ConvexAI/Metabird-7B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ConvexAI/Metabird-7B")
model = AutoModelForCausalLM.from_pretrained("ConvexAI/Metabird-7B")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ConvexAI/Metabird-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ConvexAI/Metabird-7B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ConvexAI/Metabird-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ConvexAI/Metabird-7B

SGLang

How to use ConvexAI/Metabird-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 "ConvexAI/Metabird-7B" \
    --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": "ConvexAI/Metabird-7B",
		"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 "ConvexAI/Metabird-7B" \
        --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": "ConvexAI/Metabird-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ConvexAI/Metabird-7B with Docker Model Runner:
```
docker model run hf.co/ConvexAI/Metabird-7B
```

NeuralNovel commited on Jan 20, 2024

Commit

6a076d6

verified ·

1 Parent(s): d5c5f9e

Update README.md

Browse files

Files changed (1) hide show

README.md +5 -2

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 ![Metabird](https://cdn-uploads.huggingface.co/production/uploads/645cfe4603fc86c46b3e46d1/Haraj8I91wCax4JjdYmaN.jpeg)
 ## Metabird-7B
-[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="100" height="16"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
 <details><summary>See axolotl config</summary>
 axolotl version: `0.3.0`
@@ -94,10 +94,13 @@ special_tokens:
 </details><br>
-# out
 This model is a fine-tuned version of [leveldevai/TurdusBeagle-7B](https://huggingface.co/leveldevai/TurdusBeagle-7B) on the shuyuej/metamath_gsm8k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4017
 ## Model description

 ![Metabird](https://cdn-uploads.huggingface.co/production/uploads/645cfe4603fc86c46b3e46d1/Haraj8I91wCax4JjdYmaN.jpeg)
 ## Metabird-7B
 <details><summary>See axolotl config</summary>
 axolotl version: `0.3.0`
 </details><br>
+# Metabird
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
 This model is a fine-tuned version of [leveldevai/TurdusBeagle-7B](https://huggingface.co/leveldevai/TurdusBeagle-7B) on the shuyuej/metamath_gsm8k dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.4017
 ## Model description