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

Libraries

How to use cahlen/Convergent-7B with Transformers:

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

pipe = pipeline("text-generation", model="cahlen/Convergent-7B")
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("cahlen/Convergent-7B")
model = AutoModelForCausalLM.from_pretrained("cahlen/Convergent-7B", 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 cahlen/Convergent-7B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cahlen/Convergent-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": "cahlen/Convergent-7B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cahlen/Convergent-7B

SGLang

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

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

cahlen commited on Apr 7

Commit

4885e1c

verified ·

1 Parent(s): 94215c7

Upload README.md with huggingface_hub

Browse files

Files changed (1) hide show

README.md +4 -0

README.md CHANGED Viewed

@@ -20,6 +20,10 @@ library_name: transformers
 # Convergent-7B
 **The [bigcompute.science](https://bigcompute.science) research companion model.**
 > **Early Preview** — This model is a work in progress, expressly trained to act as a research assistant with the [bigcompute.science](https://bigcompute.science) MCP server. We are still very early in the training process and the model will be updated frequently. Expect occasional bugs, incorrect tool calls, and hallucinated numerical values until we reach a GA release. If you encounter issues, please open an issue on the [GitHub repo](https://github.com/cahlen/convergent).

 # Convergent-7B
+<p align="center">
+  <img src="convergent-banner.png" alt="Convergent-7B — bigcompute.science research companion" width="800">
+</p>
 **The [bigcompute.science](https://bigcompute.science) research companion model.**
 > **Early Preview** — This model is a work in progress, expressly trained to act as a research assistant with the [bigcompute.science](https://bigcompute.science) MCP server. We are still very early in the training process and the model will be updated frequently. Expect occasional bugs, incorrect tool calls, and hallucinated numerical values until we reach a GA release. If you encounter issues, please open an issue on the [GitHub repo](https://github.com/cahlen/convergent).