Instructions to use FiditeNemini/Unhinged-Qwen2-72B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FiditeNemini/Unhinged-Qwen2-72B with Transformers:

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

pipe = pipeline("text-generation", model="FiditeNemini/Unhinged-Qwen2-72B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FiditeNemini/Unhinged-Qwen2-72B")
model = AutoModelForCausalLM.from_pretrained("FiditeNemini/Unhinged-Qwen2-72B", device_map="auto")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FiditeNemini/Unhinged-Qwen2-72B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FiditeNemini/Unhinged-Qwen2-72B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "FiditeNemini/Unhinged-Qwen2-72B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FiditeNemini/Unhinged-Qwen2-72B

SGLang

How to use FiditeNemini/Unhinged-Qwen2-72B 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 "FiditeNemini/Unhinged-Qwen2-72B" \
    --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": "FiditeNemini/Unhinged-Qwen2-72B",
		"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 "FiditeNemini/Unhinged-Qwen2-72B" \
        --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": "FiditeNemini/Unhinged-Qwen2-72B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FiditeNemini/Unhinged-Qwen2-72B with Docker Model Runner:
```
docker model run hf.co/FiditeNemini/Unhinged-Qwen2-72B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Unhinged-Qwen2-70B

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

Thanks to mradermacher for providing the quants for this model.

Merge Details

Merge Method

This model was merged using the TIES merge method using migtissera/Tess-v2.5.2-Qwen2-72B as a base.

Models Merged

The following models were included in the merge:

cognitivecomputations/dolphin-2.9.2-qwen2-72b
migtissera/Tess-v2.5.2-Qwen2-72B

Configuration

The following YAML configuration was used to produce this model:

base_model: migtissera/Tess-v2.5.2-Qwen2-72B
dtype: bfloat16
merge_method: ties
parameters:
  int8_mask: 1.0
  normalize: 0.0
slices:
- sources:
  - layer_range: [0, 80]
    model: cognitivecomputations/dolphin-2.9.2-qwen2-72b
    parameters:
      density: 0.5
      weight: 0.5
  - layer_range: [0, 80]
    model: migtissera/Tess-v2.5.2-Qwen2-72B
    parameters:
      density: 0.5
      weight: 0.5