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

Libraries

How to use yashmarathe/SuperChat-7B with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("yashmarathe/SuperChat-7B")
model = AutoModelForCausalLM.from_pretrained("yashmarathe/SuperChat-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

vLLM

How to use yashmarathe/SuperChat-7B with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/yashmarathe/SuperChat-7B

SGLang

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

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

librarian-bot commited on Jan 22, 2024

Commit

95c9e67

verified ·

1 Parent(s): b416e3a

Librarian Bot: Add base_model metadata to model

Browse files

This pull request aims to enrich the metadata of your model by adding `base_model` metadata to `YAML` block of your model's `README.md`.

How did we find this information? We use the `mergekit_config.yml` config from [mergekit](https://github.com/cg123/mergekit).

**Why add this?** Enhancing your model's metadata in this way:
- **Boosts Discoverability** - It becomes straightforward to trace the relationships between various models on the Hugging Face Hub.
- **Highlights Impact** - It showcases the contributions and influences different models have within the community.

For a hands-on example of how such metadata can play a pivotal role in mapping model connections, take a look at [librarian-bots/base_model_explorer](https://huggingface.co/spaces/librarian-bots/base_model_explorer).

This PR comes courtesy of [Librarian Bot](https://huggingface.co/librarian-bot). If you have any feedback, queries, or need assistance, please don't hesitate to reach out to [@davanstrien](https://huggingface.co/davanstrien).

Files changed (1) hide show

README.md +6 -0

README.md CHANGED Viewed

@@ -2,6 +2,12 @@
 license: apache-2.0
 tags:
 - merge
 ---
 # SuperChat-7B

 license: apache-2.0
 tags:
 - merge
+base_model:
+- mistralai/Mistral-7B-Instruct-v0.2
+- openchat/openchat-3.5-0106
+- OpenPipe/mistral-ft-optimized-1227
+- berkeley-nest/Starling-LM-7B-alpha
+- jan-hq/supermario-v2
 ---
 # SuperChat-7B