Files
Pyrz-8B-Instruct-Uncensored/README.md
ModelHub XC 54926cd6ae 初始化项目,由ModelHub XC社区提供模型
Model: ImposterOnline/Pyrz-8B-Instruct-Uncensored
Source: Original Platform
2026-10-22 14:26:41 +08:00

1.7 KiB

license, pipeline_tag, tags, model-index
license pipeline_tag tags model-index
mit text-generation
coding
uncensored
pytorch
llama-cpp
gguf
name results
Pyrex-8B-Instruct-Uncensored
task dataset metrics
type
text-generation
type name
openai_humaneval HumanEval
type value name
pass@1 52.4 pass@1 (greedy)

Pyrex-8B-Instruct-Uncensored

Pyrex-8B-Instruct-Uncensored is a high-performance, uncensored coding assistant optimized for complex software engineering tasks, agentic workflows, and function calling.

Benchmark Results (HumanEval)

Model pass@1
Pyrex-8B-Instruct-Uncensored 52.4%

Capabilities

  • Unconstrained Coding: Handles all coding requests without refusal or boilerplate restrictions.
  • Agentic Workflow: Fine-tuned on high-quality synthetic data for function calling and tool-use integration.
  • Optimized for Engineering: Trained on a massive corpus of programming literature, algorithms, and system-level codebases.

Usage

GGUF (llama.cpp / Ollama)

Quantization Recommended Use
Q4_K_M Best balance of speed and quality
Q5_K_M Improved accuracy for complex debugging
Q8_0 Near-lossless performance
ollama create pyrex-8b -f Modelfile
./llama-cli -m pyrex-q4_k_m.gguf -p "<|im_start|>user\nExplain recursion.\n<|im_end|>\n<|im_start|>assistant\n" -n 512 -c 8192

Download from ImposterOnline/Pyrex-8B-Instruct-Uncensored-GGUF.


Pyrex is a private, independent project for high-performance, uncensored engineering assistance.