Instructions to use tencent/Hy-Memory-30B-A3B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tencent/Hy-Memory-30B-A3B with Transformers:

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

pipe = pipeline("text-generation", model="tencent/Hy-Memory-30B-A3B")
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("tencent/Hy-Memory-30B-A3B")
model = AutoModelForCausalLM.from_pretrained("tencent/Hy-Memory-30B-A3B", 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 tencent/Hy-Memory-30B-A3B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tencent/Hy-Memory-30B-A3B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tencent/Hy-Memory-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tencent/Hy-Memory-30B-A3B

SGLang

How to use tencent/Hy-Memory-30B-A3B 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 "tencent/Hy-Memory-30B-A3B" \
    --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": "tencent/Hy-Memory-30B-A3B",
		"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 "tencent/Hy-Memory-30B-A3B" \
        --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": "tencent/Hy-Memory-30B-A3B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tencent/Hy-Memory-30B-A3B with Docker Model Runner:
```
docker model run hf.co/tencent/Hy-Memory-30B-A3B
```

Need Completely Uncensored Version of This model.

by parthwagh - opened 26 days ago

Discussion

parthwagh

26 days ago

Need Completely Uncensored Version of This model.

Right now only quants are present, but only single abliterated version.

seventhsummer

Tencent org 26 days ago

Thanks for asking. We currently only release the official Hy-Memory-30B-A3B weights and their quantized versions (FP8 / GGUF). We do not provide uncensored or abliterated variants.

wisamidris7

26 days ago

Come on @parthwagh they work thier whole life trying to make it not do this and this and no nsfw stuff and nothing and u come and say I want a uncensored version. LOL
Like no company would give it officially. cause uncensored will give companies a lot of trouble and personal forks or finetunes are at MIT and given as its so they take nothing.

parthwagh

25 days ago

Come on @parthwagh they work thier whole life trying to make it not do this and this and no nsfw stuff and nothing and u come and say I want a uncensored version. LOL
Like no company would give it officially. cause uncensored will give companies a lot of trouble and personal forks or finetunes are at MIT and given as its so they take nothing.

yes, I know...
I am asking for community

parthwagh

25 days ago

Thanks for asking. We currently only release the official Hy-Memory-30B-A3B weights and their quantized versions (FP8 / GGUF). We do not provide uncensored or abliterated variants.

Thank you so much for the provided models..
We are really happy for those.

I am asking for community to publish it like they do for other models.

wisamidris7

25 days ago

Ohhhh sorry I thought it's like github issues. I forgot it's for the community like github discussions.

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment