Instructions to use RoseRudolph/rudy-nemo-12b-v1-unquantized with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RoseRudolph/rudy-nemo-12b-v1-unquantized with Transformers:

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

pipe = pipeline("text-generation", model="RoseRudolph/rudy-nemo-12b-v1-unquantized")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RoseRudolph/rudy-nemo-12b-v1-unquantized")
model = AutoModelForCausalLM.from_pretrained("RoseRudolph/rudy-nemo-12b-v1-unquantized", 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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RoseRudolph/rudy-nemo-12b-v1-unquantized with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RoseRudolph/rudy-nemo-12b-v1-unquantized"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RoseRudolph/rudy-nemo-12b-v1-unquantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RoseRudolph/rudy-nemo-12b-v1-unquantized

SGLang

How to use RoseRudolph/rudy-nemo-12b-v1-unquantized 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 "RoseRudolph/rudy-nemo-12b-v1-unquantized" \
    --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": "RoseRudolph/rudy-nemo-12b-v1-unquantized",
		"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 "RoseRudolph/rudy-nemo-12b-v1-unquantized" \
        --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": "RoseRudolph/rudy-nemo-12b-v1-unquantized",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RoseRudolph/rudy-nemo-12b-v1-unquantized with Docker Model Runner:
```
docker model run hf.co/RoseRudolph/rudy-nemo-12b-v1-unquantized
```

Rudy-Nemo-12.2B-v1 (Unquantized)

This repository contains the raw, unquantized 16-bit (safetensors) weights for Rudy-Nemo-12B-v1, intended for further merging, fine-tuning, or high-precision inference.

Looking for ready-to-run GGUF files? > Check out the GGUF repository for LM Studio, Ollama, and llama.cpp:
RoseRudolph/rudy-nemo-12b-v1

This is a merge of pre-trained language models created using mergekit.

merge method

This model was merged using the SLERP merge method.

merge victims

The following models were included in the merge:

yaml config

The following YAML configuration was used to produce this model:

slices:
  - sources:
      - model: mistralai/Mistral-Nemo-Instruct-2407
        layer_range: [0, 40]
      - model: TheDrummer/Rocinante-12B-v1.1
        layer_range: [0, 40]

merge_method: slerp
base_model: mistralai/Mistral-Nemo-Instruct-2407
tokenizer_source: base

parameters:
  t:
    - filter: self_attn
      value: [0.00, 0.25, 0.50, 0.75, 1.00]
    - filter: mlp
      value: [0.00, 0.25, 0.50, 0.75, 1.00]
    - value: 0.50

dtype: bfloat16

Downloads last month: 53

Safetensors

Model size

12B params

Tensor type

BF16

Model tree for RoseRudolph/rudy-nemo-12b-v1-unquantized

TheDrummer/Rocinante-12B-v1.1

mistralai/Mistral-Nemo-Instruct-2407

Merge model

this model

Collection including RoseRudolph/rudy-nemo-12b-v1-unquantized

Rudy's Collection

Collection

A collection of Rudy language models built for roleplay, storytelling, and creative writing. Includes official releases, updates, and future iteratio • 2 items • Updated 3 days ago