Instructions to use OccultAI/Musecuilo-12B-Model_Stock with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OccultAI/Musecuilo-12B-Model_Stock with Transformers:

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

pipe = pipeline("text-generation", model="OccultAI/Musecuilo-12B-Model_Stock")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OccultAI/Musecuilo-12B-Model_Stock")
model = AutoModelForCausalLM.from_pretrained("OccultAI/Musecuilo-12B-Model_Stock")
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]:]))

NeMo
How to use OccultAI/Musecuilo-12B-Model_Stock with NeMo:
```
# tag did not correspond to a valid NeMo domain.
```
Inference
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OccultAI/Musecuilo-12B-Model_Stock with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/OccultAI/Musecuilo-12B-Model_Stock

SGLang

How to use OccultAI/Musecuilo-12B-Model_Stock 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 "OccultAI/Musecuilo-12B-Model_Stock" \
    --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": "OccultAI/Musecuilo-12B-Model_Stock",
		"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 "OccultAI/Musecuilo-12B-Model_Stock" \
        --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": "OccultAI/Musecuilo-12B-Model_Stock",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use OccultAI/Musecuilo-12B-Model_Stock with Docker Model Runner:
```
docker model run hf.co/OccultAI/Musecuilo-12B-Model_Stock
```

Naphula commited on 19 days ago

Commit

d1383fd

verified ·

1 Parent(s): 26234e3

Create README.md

Browse files

Files changed (1) hide show

README.md +47 -0

README.md ADDED Viewed

	@@ -0,0 +1,47 @@

+---
+library_name: transformers
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- mistral
+- nemo
+- model_stock
+base_model:
+- mistralai/Mistral-Nemo-Instruct-2407
+- LatitudeGames/Muse-12B
+- allura-org/Tlacuilo-12B
+---
+# 🐈 Musecuilo 12B Model_Stock
+![Musecuilo](https://cdn-uploads.huggingface.co/production/uploads/68e840caa318194c44ec2a04/vzBGv8Vlx6n2mAXbWY84S.png)
+> [!NOTE]
+> <span style="color:red; font-weight:bold">Note:</span> Use **Mistral Tekken** (recommended) or **ChatML** chat template for best results. The model has some refusals but can be jailbroken or ablated as needed.
+>
+This model was merged using the [`model_stock`](https://arxiv.org/abs/2403.19522) merge method.
+Musecuilo is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
+* [mistralai/Mistral-Nemo-Instruct-2407](https://huggingface.co/mistralai/Mistral-Nemo-Instruct-2407)
+* [LatitudeGames/Muse-12B](https://huggingface.co/LatitudeGames/Muse-12B)
+* [allura-org/Tlacuilo-12B](https://huggingface.co/allura-org/Tlacuilo-12BS)
+## 🧩 Configuration
+```yaml
+architecture: MistralForCausalLM
+base_model: B:/12B/mistralai--Mistral-Nemo-Instruct-2407
+models:
+  - model: B:/12B/allura-org--Tlacuilo-12B
+  - model: B:/12B/LatitudeGames--Muse-12B
+merge_method: model_stock
+parameters:
+  filter_wise: true
+dtype: float32
+out_dtype: bfloat16
+tokenizer:
+  source: B:/12B/LatitudeGames--Muse-12B
+name: Musecuilo-12B-Model_Stock
+```