Instructions to use dnhkng/RYS-Medium with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dnhkng/RYS-Medium with Transformers:

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

pipe = pipeline("text-generation", model="dnhkng/RYS-Medium", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("dnhkng/RYS-Medium", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("dnhkng/RYS-Medium", trust_remote_code=True)
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 dnhkng/RYS-Medium with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/dnhkng/RYS-Medium

SGLang

How to use dnhkng/RYS-Medium 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 "dnhkng/RYS-Medium" \
    --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": "dnhkng/RYS-Medium",
		"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 "dnhkng/RYS-Medium" \
        --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": "dnhkng/RYS-Medium",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dnhkng/RYS-Medium with Docker Model Runner:
```
docker model run hf.co/dnhkng/RYS-Medium
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This is a new kind of model optimization. A paper on the technique is currently being written.

This research was supported with hardware from the appliedAI Institute, whose goal is to generate and communicate high-quality knowledge about trustworthy AI.

Quickstart

This code snippets show how to get quickly started with running the model on a GPU:

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

torch.random.manual_seed(0)
model_id = "dnhkng/Medium"
model = AutoModelForCausalLM.from_pretrained(
    model_id,
    device_map="cuda", 
    torch_dtype="auto", 
    trust_remote_code=True, 
)
tokenizer = AutoTokenizer.from_pretrained(model_id)

messages = [
    {"role": "user", "content": "Can you provide ways to eat combinations of bananas and dragonfruits?"},
    {"role": "assistant", "content": "Sure! Here are some ways to eat bananas and dragonfruits together: 1. Banana and dragonfruit smoothie: Blend bananas and dragonfruits together with some milk and honey. 2. Banana and dragonfruit salad: Mix sliced bananas and dragonfruits together with some lemon juice and honey."},
    {"role": "user", "content": "What about solving an 2x + 3 = 7 equation?"},
]

pipe = pipeline(
    "text-generation",
    model=model,
    tokenizer=tokenizer,
)

generation_args = {
    "max_new_tokens": 500,
    "return_full_text": False,
    "temperature": 0.0,
    "do_sample": False,
}

output = pipe(messages, **generation_args)
print(output[0]['generated_text'])

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	25.94
IFEval (0-Shot)	44.06
BBH (3-Shot)	47.73
MATH Lvl 5 (4-Shot)	7.78
GPQA (0-shot)	10.40
MuSR (0-shot)	8.73
MMLU-PRO (5-shot)	36.96

SHAMELESS ADVERTISING BREAK

I’m on the hunt for new challenges and a chance to dive into some exciting research opportunities. Oh, and did I mention I just snagged a top spot on the Open LLM leaderboard? 🎉

Profile

Innovation enthusiast, AI strategist, and interdisciplinary-tech nerd – that's me! With over a decade of experience in research and project management, my professional journey has been largely shaped by my passion for artificial intelligence and its potential to transform various industries. With a solid background in artificial intelligence and machine learning, coupled with a knack for innovation and problem-solving (and a healthy dose of curiosity), I'm excited to bring my skills to a new team.

Originally from Australia, where I earned my degrees in Organic Chemistry and Biochemistry, I moved to Germany in 2004. My academic pursuit continued with a PhD in Chemistry at the Max Planck Institute of Biochemistry. Today, I leverage my robust educational background and diverse industry experience to drive AI innovations in a wide range of applications. Hobbies? Lots: I've also built the world's most powerful espresso machine and am working to bring GLaDOS to life.

I'm based out of Munich, Germany, but I would be interested in working remotely for a team with more compute than my 2x 4090s 🚀

Reach out via LinkedIn - Dr David Noel Ng

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	25.94
IFEval (0-Shot)	44.06
BBH (3-Shot)	47.73
MATH Lvl 5 (4-Shot)	7.78
GPQA (0-shot)	10.40
MuSR (0-shot)	8.73
MMLU-PRO (5-shot)	36.96

Downloads last month: 13

Safetensors

Model size

19B params

Tensor type

BF16

Model tree for dnhkng/RYS-Medium

Quantizations

2 models

Evaluation results

strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

44.060
strict accuracy on IFEval (0-Shot)
Open LLM Leaderboard

44.060
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

47.730
normalized accuracy on BBH (3-Shot)
Open LLM Leaderboard

47.730
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

7.780
exact match on MATH Lvl 5 (4-Shot)
Open LLM Leaderboard

7.780
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

10.400
acc_norm on GPQA (0-shot)
Open LLM Leaderboard

10.400
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

8.730
acc_norm on MuSR (0-shot)
Open LLM Leaderboard

8.730
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

36.960
accuracy on MMLU-PRO (5-shot)
test set Open LLM Leaderboard

36.960