Instructions to use Steelskull/L3.3-MS-Nevoria-70b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Steelskull/L3.3-MS-Nevoria-70b with Transformers:

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

pipe = pipeline("text-generation", model="Steelskull/L3.3-MS-Nevoria-70b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Steelskull/L3.3-MS-Nevoria-70b")
model = AutoModelForCausalLM.from_pretrained("Steelskull/L3.3-MS-Nevoria-70b")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Steelskull/L3.3-MS-Nevoria-70b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Steelskull/L3.3-MS-Nevoria-70b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Steelskull/L3.3-MS-Nevoria-70b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Steelskull/L3.3-MS-Nevoria-70b

SGLang

How to use Steelskull/L3.3-MS-Nevoria-70b 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 "Steelskull/L3.3-MS-Nevoria-70b" \
    --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": "Steelskull/L3.3-MS-Nevoria-70b",
		"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 "Steelskull/L3.3-MS-Nevoria-70b" \
        --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": "Steelskull/L3.3-MS-Nevoria-70b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Steelskull/L3.3-MS-Nevoria-70b with Docker Model Runner:
```
docker model run hf.co/Steelskull/L3.3-MS-Nevoria-70b
```

Finally some good shit

by lGodZiol - opened Jan 14, 2025

Discussion

lGodZiol

Jan 14, 2025

I honestly have no idea why (maybe the negative llama is having that great of an influence) but this merge is miles above the individual tunes that went into making it. Good sir, this model has just become my daily driver. Chapeau bas

Steelskull

Owner Jan 14, 2025

I honestly have no idea why (maybe the negative llama is having that great of an influence) but this merge is miles above the individual tunes that went into making it. Good sir, this model has just become my daily driver. Chapeau bas

Glad to hear it! I think its a combination of the lorablated's effect on the model merge and then negative llama that really smooths out the model

SicariusSicariiStuff

Jan 17, 2025

outstanding work, well done!

Steelskull

Owner Jan 18, 2025

•

edited Jan 18, 2025

outstanding work, well done!

Thank you! you created a great tuned model to work with.

Altotas

Jan 20, 2025

I'm salivating at the idea of even better Nevoria with Deepseek-R1 heart ^_^

Steelskull

Owner Jan 20, 2025

I'm salivating at the idea of even better Nevoria with Deepseek-R1 heart ^_^

🤔 I have a working idea for a v1.5 of Nevoria (to fix the small repetition issue) so I'll see if I slip in a test version of that for a Nevoria‐R1 and people can test it out.

Steelskull

Owner Jan 24, 2025

I'm salivating at the idea of even better Nevoria with Deepseek-R1 heart ^_^

Steelskull/L3.3-Nevoria-R1-70b

users have also been saying its excellent

@Altotas

ruralrob

Sep 5, 2025

Any recommendations on temperature and other settings?

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