Instructions to use CultriX/Qwen2.5-14B-Unity with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CultriX/Qwen2.5-14B-Unity with Transformers:

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

pipe = pipeline("text-generation", model="CultriX/Qwen2.5-14B-Unity")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CultriX/Qwen2.5-14B-Unity")
model = AutoModelForCausalLM.from_pretrained("CultriX/Qwen2.5-14B-Unity")
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 CultriX/Qwen2.5-14B-Unity with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CultriX/Qwen2.5-14B-Unity"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CultriX/Qwen2.5-14B-Unity",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/CultriX/Qwen2.5-14B-Unity

SGLang

How to use CultriX/Qwen2.5-14B-Unity 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 "CultriX/Qwen2.5-14B-Unity" \
    --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": "CultriX/Qwen2.5-14B-Unity",
		"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 "CultriX/Qwen2.5-14B-Unity" \
        --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": "CultriX/Qwen2.5-14B-Unity",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use CultriX/Qwen2.5-14B-Unity with Docker Model Runner:
```
docker model run hf.co/CultriX/Qwen2.5-14B-Unity
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

merge

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

Merge Details

Merge Method

This model was merged using the DARE TIES merge method using CultriX/SeQwence-14Bv1 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

base_model: CultriX/SeQwence-14Bv1
merge_method: dare_ties
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16

models:
  - model: CultriX/SeQwence-14Bv1
    parameters:
      weight: 0.28      # Strong base for multitask benchmarks.
      density: 0.7      # Retains strong multitask performance.

  - model: CultriX/Qwen2.5-14B-Wernickev3
    parameters:
      weight: 0.22      # Balanced to support reasoning-heavy benchmarks like BBH.
      density: 0.65

  - model: qingy2019/Qwen2.5-Math-14B-Instruct
    parameters:
      weight: 0.22      # Optimized for MATH and BBH.
      density: 0.6

  - model: allknowingroger/QwenSlerp6-14B
    parameters:
      weight: 0.18      # Reintegration of the highest scorer for stability across benchmarks.
      density: 0.65     # Focused on its exceptional multitask and reasoning strengths.

  - model: CultriX/Qwen2.5-14B-Emergedv3
    parameters:
      weight: 0.15      # Maintains multitask stability for GPQA and MMLU-PRO.
      density: 0.6

  - model: sometimesanotion/Qwen2.5-14B-Vimarckoso
    parameters:
      weight: 0.1       # Late-layer contributor for MUSR and multi-step reasoning.
      density: 0.6

adaptive_merge_parameters:
  task_weights:
    IFEval: 1.4         # Balanced to maintain instruction-following benchmarks.
    BBH: 1.4            # Ensures strong reasoning capabilities.
    MATH: 1.5           # Prioritizes mathematical reasoning.
    GPQA: 1.5           # Balanced for factual QA.
    MUSR: 1.4           # Advanced multi-step reasoning.
    MMLU-PRO: 1.5       # Emphasized for domain-specific multitask performance.

  smoothing_factor: 0.12  # Smooth transitions between task-specific contributions.

gradient_clipping:
  CultriX/SeQwence-14Bv1: 0.8
  CultriX/Qwen2.5-14B-Wernickev3: 0.8
  qingy2019/Qwen2.5-Math-14B-Instruct: 0.85
  allknowingroger/QwenSlerp6-14B: 0.8  # Balanced for high scoring model contributions.
  CultriX/Qwen2.5-14B-Emergedv3: 0.75
  sometimesanotion/Qwen2.5-14B-Vimarckoso: 0.75

tokenizer_source: CultriX/SeQwence-14Bv1