Instructions to use SteelStorage/NeMoria-21b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SteelStorage/NeMoria-21b with Transformers:

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

pipe = pipeline("text-generation", model="SteelStorage/NeMoria-21b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SteelStorage/NeMoria-21b")
model = AutoModelForCausalLM.from_pretrained("SteelStorage/NeMoria-21b")
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 SteelStorage/NeMoria-21b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SteelStorage/NeMoria-21b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SteelStorage/NeMoria-21b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SteelStorage/NeMoria-21b

SGLang

How to use SteelStorage/NeMoria-21b 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 "SteelStorage/NeMoria-21b" \
    --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": "SteelStorage/NeMoria-21b",
		"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 "SteelStorage/NeMoria-21b" \
        --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": "SteelStorage/NeMoria-21b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SteelStorage/NeMoria-21b with Docker Model Runner:
```
docker model run hf.co/SteelStorage/NeMoria-21b
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

merge

This is a testing model using the zeroing method used by L3-Aethora-15B-V2.

If this model pans out in the way I hope, Ill expand on it more and add a custom model card like the others. currently this is just an experiment.

In case anyone asks NeMoria-21b literally means:

NeMo = Mistral-Nemo (Instruct)
21b = its 21b perameters

Merge Details

Merge Method

This model was merged using the passthrough merge method.

Models Merged

The following models were included in the merge:

unsloth/Mistral-Nemo-Instruct-2407

Configuration

The following YAML configuration was used to produce this model:

dtype: bfloat16
merge_method: passthrough
slices:
- sources:
  - layer_range: [0, 30]
    model: unsloth/Mistral-Nemo-Instruct-2407
- sources:
  - layer_range: [16, 32]
    model: unsloth/Mistral-Nemo-Instruct-2407
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [16, 32]
    model: unsloth/Mistral-Nemo-Instruct-2407
    parameters:
      scale:
      - filter: o_proj
        value: 0.0
      - filter: down_proj
        value: 0.0
      - value: 1.0
- sources:
  - layer_range: [32, 40]
    model: unsloth/Mistral-Nemo-Instruct-2407

Downloads last month: 11

Safetensors

Model size

20B params

Tensor type

BF16

Model tree for SteelStorage/NeMoria-21b

Base model

unsloth/Mistral-Nemo-Instruct-2407

Finetuned

(39)

this model

Quantizations

4 models