Instructions to use Azazelle/MN-Halide-12b-v1.0 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Azazelle/MN-Halide-12b-v1.0 with Transformers:

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

pipe = pipeline("text-generation", model="Azazelle/MN-Halide-12b-v1.0")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Azazelle/MN-Halide-12b-v1.0")
model = AutoModelForCausalLM.from_pretrained("Azazelle/MN-Halide-12b-v1.0")

Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Azazelle/MN-Halide-12b-v1.0 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Azazelle/MN-Halide-12b-v1.0"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Azazelle/MN-Halide-12b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Azazelle/MN-Halide-12b-v1.0

SGLang

How to use Azazelle/MN-Halide-12b-v1.0 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 "Azazelle/MN-Halide-12b-v1.0" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Azazelle/MN-Halide-12b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "Azazelle/MN-Halide-12b-v1.0" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Azazelle/MN-Halide-12b-v1.0",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Azazelle/MN-Halide-12b-v1.0 with Docker Model Runner:
```
docker model run hf.co/Azazelle/MN-Halide-12b-v1.0
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

MN-Halide-12b-v1.0

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using SillyTilly/mistralai_Mistral-Nemo-Base-2407 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: SillyTilly/mistralai_Mistral-Nemo-Base-2407
dtype: float32
merge_method: model_stock
slices:
- sources:
  - layer_range: [0, 40]
    model: nbeerbower/Lyra4-Gutenberg-12B
  - layer_range: [0, 40]
    model: nbeerbower/mistral-nemo-gutenberg-12B-v4
  - layer_range: [0, 40]
    model: elinas/Chronos-Gold-12B-1.0
  - layer_range: [0, 40]
    model: UsernameJustAnother/Nemo-12B-Marlin-v8
  - layer_range: [0, 40]
    model: TheDrummer/Rocinante-12B-v1.1
  - layer_range: [0, 40]
    model: Epiculous/Azure_Dusk-v0.2
  - layer_range: [0, 40]
    model: Epiculous/Crimson_Dawn-v0.2
  - layer_range: [0, 40]
    model: TheDrummer/Rocinante-12B-v1+jtatman/mistral_nemo_12b_reasoning_psychology_lora
  - layer_range: [0, 40]
    model: nbeerbower/mistral-nemo-wissenschaft-12B
  - layer_range: [0, 40]
    model: nbeerbower/mistral-nemo-bophades-12B
  - layer_range: [0, 40]
    model: anthracite-org/magnum-v2.5-12b-kto+mpasila/Mistral-freeLiPPA-LoRA-12B
  - layer_range: [0, 40]
    model: nbeerbower/mistral-nemo-cc-12B
  - layer_range: [0, 40]
    model: anthracite-org/magnum-v2-12b
  - layer_range: [0, 40]
    model: anthracite-org/magnum-v2.5-12b-kto+jeiku/Aura-NeMo-12B
  - layer_range: [0, 40]
    model: SillyTilly/mistralai_Mistral-Nemo-Base-2407
tokenizer_source: unsloth/Mistral-Nemo-Base-2407