Instructions to use v000000/MN-12B-Estrella-v2.2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use v000000/MN-12B-Estrella-v2.2 with Transformers:

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

pipe = pipeline("text-generation", model="v000000/MN-12B-Estrella-v2.2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("v000000/MN-12B-Estrella-v2.2")
model = AutoModelForMultimodalLM.from_pretrained("v000000/MN-12B-Estrella-v2.2")

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use v000000/MN-12B-Estrella-v2.2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "v000000/MN-12B-Estrella-v2.2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "v000000/MN-12B-Estrella-v2.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/v000000/MN-12B-Estrella-v2.2

SGLang

How to use v000000/MN-12B-Estrella-v2.2 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 "v000000/MN-12B-Estrella-v2.2" \
    --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": "v000000/MN-12B-Estrella-v2.2",
		"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 "v000000/MN-12B-Estrella-v2.2" \
        --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": "v000000/MN-12B-Estrella-v2.2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use v000000/MN-12B-Estrella-v2.2 with Docker Model Runner:
```
docker model run hf.co/v000000/MN-12B-Estrella-v2.2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Temperature:
Mistral Nemo likes low temperature between 0.3-0.6

Mistral-Nemo-2407-12B-Estrella-v2.2

Prompt Format: Seems best with "Mistral Instruct" but ChatML might also work.

[INST] System Message [/INST]

[INST] Name: Let's get started. Please respond based on the information and instructions provided above. [/INST]

<s>[INST] Name: What is your favourite condiment? [/INST]
AssistantName: Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> 
[INST] Name: Do you have mayonnaise recipes? [/INST]

Thanks mradermacher for the quants!

merge

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

Merge Details

Merge Method

This model was merged using the della_linear merge method using anthracite-org/magnum-v2.5-12b-kto as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: v000000/MN-12B-Estrella-v1
    parameters:
      weight: 0.25
      density: 0.84
  - model: elinas/Chronos-Gold-12B-1.0
    parameters:
      weight: 0.4
      density: 0.88
  - model: TheDrummer/Rocinante-12B-v1.1
    parameters:
      weight: 0.6
      density: 0.9
merge_method: della_linear
base_model: anthracite-org/magnum-v2.5-12b-kto
parameters:
  int8_mask: true
  epsilon: 0.07
  lambda: 1
dtype: bfloat16