Instructions to use ImposterOnline/Pyrex-8B-Instruct-Uncensored with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ImposterOnline/Pyrex-8B-Instruct-Uncensored with Transformers:

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

pipe = pipeline("text-generation", model="ImposterOnline/Pyrex-8B-Instruct-Uncensored")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("ImposterOnline/Pyrex-8B-Instruct-Uncensored")
model = AutoModelForCausalLM.from_pretrained("ImposterOnline/Pyrex-8B-Instruct-Uncensored", 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]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use ImposterOnline/Pyrex-8B-Instruct-Uncensored with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ImposterOnline/Pyrex-8B-Instruct-Uncensored"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ImposterOnline/Pyrex-8B-Instruct-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ImposterOnline/Pyrex-8B-Instruct-Uncensored

SGLang

How to use ImposterOnline/Pyrex-8B-Instruct-Uncensored 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 "ImposterOnline/Pyrex-8B-Instruct-Uncensored" \
    --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": "ImposterOnline/Pyrex-8B-Instruct-Uncensored",
		"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 "ImposterOnline/Pyrex-8B-Instruct-Uncensored" \
        --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": "ImposterOnline/Pyrex-8B-Instruct-Uncensored",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ImposterOnline/Pyrex-8B-Instruct-Uncensored with Docker Model Runner:
```
docker model run hf.co/ImposterOnline/Pyrex-8B-Instruct-Uncensored
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

Pyrex 8B Instruct Uncensored — a sharp, uncensored coding model.
Strong at code · honest by design · runs anywhere.

Model · Benchmarks · Usage · GGUF · Training

Introduction

Pyrex 8B Instruct Uncensored is a real, trained model — built with our own data recipe, our own QLoRA fine-tune, and our own evaluation pipeline on Hugging Face GPU compute. It is a coding-first instruction model designed for real developer work: writing code, fixing bugs, explaining technical problems, and driving agent loops.

Key strengths

Coding-first — trained mostly on high-quality code instructions (OpenCoder real-user data, CodeAlpaca, evol-codealpaca), so it writes clean and correct code.
Uncensored — answers directly and honestly, without refusals.
Agentic / tool-use ready — function-calling data was part of training; suited for OpenAI-compatible APIs and agent workflows.
Portable — full-precision safetensors plus GGUF quants for Ollama, llama.cpp and LM Studio.

Uncensored usage note. This model has no safety-alignment softening built in. It can produce content that is explicit, offensive, or otherwise unsuitable for some audiences. Use it responsibly and at your own discretion — the model and its authors assume no liability for outputs.

Model details

Property	Value
Parameters	7.6B
Architecture	Transformers · RoPE · SwiGLU · RMSNorm · GQA
Context window	Up to 32k native (trained at 3072)
Base	Coding-specialized instruct model (uncensored variant)
Method	QLoRA (4-bit NF4) + LoRA r=48, α=96
Chat format	`chatml` (`<
License	Apache-2.0

Benchmarks

Measured with greedy pass@1 on HumanEval — 164 unseen problems, official unit tests executed in a sandbox. No sampling luck, no leaked answers.

HumanEval benchmark

Model	HumanEval pass@1
Base (untuned)	29.3% (48/164)
Pyrex (previous)	41.5% (68/164)
Pyrex 8B Instruct Uncensored	52.4% (86/164)

+23.1 points over the base on unseen problems.

Usage

Requirements

transformers >= 4.44 for best apply_chat_template support.
Any recent PyTorch build (CUDA or CPU).

Python

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "ImposterOnline/Pyrex-8B-Instruct-Uncensored"
tok = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype="auto")

messages = [{"role": "user", "content": "Explain async/await in Python."}]
text = tok.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
out = model.generate(**tok(text, return_tensors="pt"), max_new_tokens=512)
print(tok.decode(out[0], skip_special_tokens=True))

Chat format is chatml. System prompt is optional; when used it is a system message before the user turn.

Server / agentic

Works with any OpenAI-compatible server (vLLM, llama.cpp server, Ollama, Text Generation Inference). Function calling was part of training.

vllm serve ImposterOnline/Pyrex-8B-Instruct-Uncensored

GGUF

Quantized builds live in Pyrex-8B-Instruct-Uncensored-GGUF.

File	Size	Notes
`pyrex-q4_k_m.gguf`	4.4 GB	Fast, recommended daily driver
`pyrex-q5_k_m.gguf`	5.1 GB	Higher quality
`pyrex-q8_0.gguf`	8.1 GB	Fast, best quality
`pyrex-f16.gguf`	15.2 GB	Full precision

# Ollama (Modelfile ships in the GGUF repo)
ollama create pyrex-8b -f Modelfile
ollama run pyrex-8b "Write a Python function that merges overlapping intervals."

# llama.cpp
./llama-cli -m pyrex-q4_k_m.gguf \
  -p "<|im_start|>user\nYour question here\n<|im_end|>\n<|im_start|>assistant\n" \
  -n 512 -c 8192

Training

Parameter	Value
Data	~95k cleaned examples (code + tool-use + general)
Sequence length	3072
Loss masking	Assistant-only (completion-only SFT)
Optimizer	AdamW · lr 2e-4 · cosine · warmup 3%
Epochs	1
Hardware	Hugging Face A100 GPU job

Data sources (credited): OpenCoder-LLM/opencoder-sft-stage1 (realuser + largescale-diverse), sahil2801/CodeAlpaca-20k, theblackcat102/evol-codealpaca-v1, databricks/databricks-dolly-15k, NousResearch/hermes-function-calling-v1.

The pipeline is config-driven and reproducible — prepare_data.py → train_qlora.py → eval_humaneval.py → publish.sh — in the companion repo Arhan-w/pyrut.