Instructions to use Infermatic/14b-Qwen2.5-Infermatic-Crea-v2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Infermatic/14b-Qwen2.5-Infermatic-Crea-v2 with Transformers:

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

pipe = pipeline("text-generation", model="Infermatic/14b-Qwen2.5-Infermatic-Crea-v2")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Infermatic/14b-Qwen2.5-Infermatic-Crea-v2")
model = AutoModelForCausalLM.from_pretrained("Infermatic/14b-Qwen2.5-Infermatic-Crea-v2")
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 Infermatic/14b-Qwen2.5-Infermatic-Crea-v2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Infermatic/14b-Qwen2.5-Infermatic-Crea-v2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Infermatic/14b-Qwen2.5-Infermatic-Crea-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Infermatic/14b-Qwen2.5-Infermatic-Crea-v2

SGLang

How to use Infermatic/14b-Qwen2.5-Infermatic-Crea-v2 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 "Infermatic/14b-Qwen2.5-Infermatic-Crea-v2" \
    --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": "Infermatic/14b-Qwen2.5-Infermatic-Crea-v2",
		"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 "Infermatic/14b-Qwen2.5-Infermatic-Crea-v2" \
        --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": "Infermatic/14b-Qwen2.5-Infermatic-Crea-v2",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Infermatic/14b-Qwen2.5-Infermatic-Crea-v2 with Docker Model Runner:
```
docker model run hf.co/Infermatic/14b-Qwen2.5-Infermatic-Crea-v2
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

14b-Qwen2.5-Infermatic-Crea-v2

This was made thanks to infermatic.ai

This version is slightly more uncensored than the V1, both are good at describing things (like feelings, places, objects, situations and so on)

RP/Story writing

Probably will release soon new recommended settings for this model on the settings archive on Infermatic.ai

pd. if you have refusals it can be fixed with good settings and prompts (or probably with a swipe)

Any feedback can be shared on our discord server

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

Merge Details

Merge Method

This model was merged using the Model Stock merge method using huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2 as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

name:                Qwen2.5-14B-Infermatic-crea
merge_method:        model_stock
base_model:          huihui-ai/Qwen2.5-14B-Instruct-abliterated-v2
tokenizer_source:    base
parameters:
  int8_mask:         true
  normalize:         true
  rescale:           false
models:
  - model:           v000000/Qwen2.5-Lumen-14B
  - model:           v000000/Qwen2.5-14B-Gutenberg-1e-Delta
  - model:           Sao10K/14B-Qwen2.5-Kunou-v1
dtype:               bfloat16
out_dtype:           bfloat16