Instructions to use Phr00t/Phr00tyMix-v2-32B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Phr00t/Phr00tyMix-v2-32B with Transformers:

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

pipe = pipeline("text-generation", model="Phr00t/Phr00tyMix-v2-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Phr00t/Phr00tyMix-v2-32B")
model = AutoModelForCausalLM.from_pretrained("Phr00t/Phr00tyMix-v2-32B")
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 Phr00t/Phr00tyMix-v2-32B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Phr00t/Phr00tyMix-v2-32B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Phr00t/Phr00tyMix-v2-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Phr00t/Phr00tyMix-v2-32B

SGLang

How to use Phr00t/Phr00tyMix-v2-32B 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 "Phr00t/Phr00tyMix-v2-32B" \
    --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": "Phr00t/Phr00tyMix-v2-32B",
		"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 "Phr00t/Phr00tyMix-v2-32B" \
        --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": "Phr00t/Phr00tyMix-v2-32B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Phr00t/Phr00tyMix-v2-32B with Docker Model Runner:
```
docker model run hf.co/Phr00t/Phr00tyMix-v2-32B
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

This model has been replaced by Phr00tyMix v3

Phr00tyMix-v2-32B

The goal: smart, obedient, uncensored, coherent roleplay and creative storywriting. I think this is a significant improvement over Phr00tyMix-v1. This model is more uncensored and pays much better attention to details.

I picked these models mostly for creative purposes that do not force thinking into responses:

ArliAI/QwQ-32B-ArliAI-RpR-v4 (for smart creativity and longer context)
allura-org/Qwen2.5-32b-RP-Ink ("cursed" roleplay support)
Delta-Vector/Hamanasu-Magnum-QwQ-32B (solid instruct creative finetune)
Sao10K/32B-Qwen2.5-Kunou-v1 (solid Qwen roleplay finetune)
nbeerbower/EVA-Gutenberg3-Qwen2.5-32B (mix of many solid writing finetunes)

The base model is huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated for an uncensored and very smart foundation.

I dropped the "LongWriter Zero" because it didn't seem to write very well when testing directly. I also dropped ROMBOS as the DeepSeek-R1-Distill appears to have enough brains as a foundation.

I've been very impressed with my (limited) testing of it thus far (formatted script writing, uncensored testing, reasoning etc.).

GGUFs can be found here

Merge Details

Configuration

The following YAML configuration was used to produce this model:

merge_method: model_stock
base_model: huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated
dtype: bfloat16
models:
  - model: nbeerbower/EVA-Gutenberg3-Qwen2.5-32B
  - model: Delta-Vector/Hamanasu-Magnum-QwQ-32B
  - model: ArliAI/QwQ-32B-ArliAI-RpR-v4
  - model: Sao10K/32B-Qwen2.5-Kunou-v1
  - model: allura-org/Qwen2.5-32b-RP-Ink

Downloads last month: 14

Safetensors

Model size

33B params

Tensor type

BF16

Model tree for Phr00t/Phr00tyMix-v2-32B

ArliAI/QwQ-32B-ArliAI-RpR-v4

Delta-Vector/Hamanasu-Magnum-QwQ-32B

Sao10K/32B-Qwen2.5-Kunou-v1

allura-org/Qwen2.5-32b-RP-Ink

huihui-ai/DeepSeek-R1-Distill-Qwen-32B-abliterated

nbeerbower/EVA-Gutenberg3-Qwen2.5-32B

Merge model

this model

Merges

2 models

Quantizations

3 models