Instructions to use SanXM1/Driftwood-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SanXM1/Driftwood-12B with Transformers:

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

pipe = pipeline("text-generation", model="SanXM1/Driftwood-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("SanXM1/Driftwood-12B")
model = AutoModelForCausalLM.from_pretrained("SanXM1/Driftwood-12B")
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 Settings

vLLM

How to use SanXM1/Driftwood-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "SanXM1/Driftwood-12B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "SanXM1/Driftwood-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/SanXM1/Driftwood-12B

SGLang

How to use SanXM1/Driftwood-12B 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 "SanXM1/Driftwood-12B" \
    --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": "SanXM1/Driftwood-12B",
		"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 "SanXM1/Driftwood-12B" \
        --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": "SanXM1/Driftwood-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use SanXM1/Driftwood-12B with Docker Model Runner:
```
docker model run hf.co/SanXM1/Driftwood-12B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

WTF this is

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

Merge Details

Basically. How many fucking models can you merge into 1 and still stay coherent, 24 is the answer (Though i might do a bigger one)

Quants

FP8: https://huggingface.co/SanXM1/Driftwood-12b-FP8/ EXL2: https://huggingface.co/NewEden/Delta-Vector_driftwood-exl2

Merge Method

This model was merged using the Model Stock merge method using IntervitensInc/Mistral-Nemo-Base-2407-chatml 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: Delta-Vector/Rei-12B
  - model: natong19/Mistral-Nemo-Instruct-2407-abliterated
  - model: Nitral-AI/Captain-Eris_Violet-GRPO-v0.420
  - model: Nitral-AI/Wayfarer_Eris_Noctis-12B
  - model: LatitudeGames/Wayfarer-12B
  - model: PygmalionAI/Pygmalion-3-12B
  - model: allura-org/Bigger-Body-12b
  - model: allura-org/MN-12b-RP-Ink
  - model: PocketDoc/Dans-SakuraKaze-V1.0.0-12b
  - model: PocketDoc/Dans-DangerousWinds-V1.1.0-12b
  - model: PocketDoc/Dans-PersonalityEngine-V1.1.0-12b
  - model: Delta-Vector/Ohashi-NeMo-12B
  - model: Delta-Vector/Francois-Huali-12B  
  - model: anthracite-org/magnum-v4-12b
  - model: Undi95/LocalC-12B-e2.0
  - model: NeverSleep/Lumimaid-v0.2-12B
  - model: Fizzarolli/MN-12b-Sunrose
  - model: anthracite-org/magnum-v2.5-12b-kto
  - model: elinas/Chronos-Gold-12B-1.0
  - model: nbeerbower/mistral-nemo-bophades-12B
  - model: nbeerbower/mistral-nemo-gutenberg-12B-v4
  - model: nbeerbower/mistral-nemo-wissenschaft-12B
  - model: nbeerbower/Mistral-Nemo-Prism-12B
  - model: nbeerbower/Lyra4-Gutenberg2-12B
merge_method: model_stock
base_model: IntervitensInc/Mistral-Nemo-Base-2407-chatml
normalize: false
int8_mask: true
dtype: bfloat16