Instructions to use pot99rta/DarkThink-DirectiveReasoner-12B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pot99rta/DarkThink-DirectiveReasoner-12B with Transformers:

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

pipe = pipeline("text-generation", model="pot99rta/DarkThink-DirectiveReasoner-12B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pot99rta/DarkThink-DirectiveReasoner-12B")
model = AutoModelForCausalLM.from_pretrained("pot99rta/DarkThink-DirectiveReasoner-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

vLLM

How to use pot99rta/DarkThink-DirectiveReasoner-12B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pot99rta/DarkThink-DirectiveReasoner-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": "pot99rta/DarkThink-DirectiveReasoner-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/pot99rta/DarkThink-DirectiveReasoner-12B

SGLang

How to use pot99rta/DarkThink-DirectiveReasoner-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 "pot99rta/DarkThink-DirectiveReasoner-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": "pot99rta/DarkThink-DirectiveReasoner-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 "pot99rta/DarkThink-DirectiveReasoner-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": "pot99rta/DarkThink-DirectiveReasoner-12B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use pot99rta/DarkThink-DirectiveReasoner-12B with Docker Model Runner:
```
docker model run hf.co/pot99rta/DarkThink-DirectiveReasoner-12B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

DarkThink-DirectiveReasoner-12B

More Robust with all the Darkness added.

Models Merged:

1. ReadyArt/Omega-Darker_The-Final-Directive-12B

2. pot99rta/MagcarpMell-ThinkandReasoner-12B

Preset:

Use ChatML or Mistral

ChatML works better for reasoning due to Magicap and MagMell being ChatML for their base Models.

Just realized I've been spelling Magcap with 'Magcarp' this WHOLE time..

merge

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

Merge Details

Merge Method

This model was merged using the TIES merge method using ReadyArt/Omega-Darker_The-Final-Directive-12B as a base.

Models Merged

The following models were included in the merge:

pot99rta/MagcarpMell-ThinkandReasoner-12B

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: ReadyArt/Omega-Darker_The-Final-Directive-12B
    #no parameters necessary for base model
  - model: ReadyArt/Omega-Darker_The-Final-Directive-12B
    parameters:
      density: 0.5
      weight: 0.5
  - model: pot99rta/MagcarpMell-ThinkandReasoner-12B
    parameters:
      density: 0.5
      weight: 0.5

merge_method: ties
base_model: ReadyArt/Omega-Darker_The-Final-Directive-12B
parameters:
  normalize: false
  int8_mask: true
dtype: float16

Downloads last month: 3

Safetensors

Model size

12B params

Tensor type

F16

Model tree for pot99rta/DarkThink-DirectiveReasoner-12B

ReadyArt/Omega-Darker_The-Final-Directive-12B

pot99rta/MagcarpMell-ThinkandReasoner-12B

Merge model

this model

Quantizations

3 models

Paper for pot99rta/DarkThink-DirectiveReasoner-12B

Resolving Interference When Merging Models

Paper • 2306.01708 • Published Jun 2, 2023 • 19