GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
shohuu
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
shohuu
Model Tree
Qwen/Qwen2.5-Coder-0.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Pyroton is a lightweight Python-focused code generation model fine-tuned from Qwen/Qwen2.5-Coder-0.5B-Instruct using supervised fine-tuning (SFT) on Python instruction-style datasets.
The goal is to create a small, efficient model that handles easy to medium Python tasks while remaining practical for free-tier GPUs and lightweight deployment including mobile phones.
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerimport torch base = AutoModelForCausalLM.from_pretrained( "Qwen/Qwen2.5-Coder-0.5B-Instruct", dtype=torch.bfloat16, device_map="auto",) model = PeftModel.from_pretrained(base, "shohuu/pyroton-primefix-v3")tokenizer = AutoTokenizer.from_pretrained("shohuu/pyroton-primefix-v3")tokenizer.pad_token = tokenizer.eos_token prompt = "### Instruction:\nWrite a Python function to reverse a string\n\n### Response:\n"inputs = tokenizer(prompt, return_tensors="pt").to(model.device) outputs = model.generate( **inputs, max_new_tokens=220, do_sample=False, repetition_penalty=1.1,) print(tokenizer.decode(outputs[0], skip_special_tokens=True))bash
# Download pyroton-q4.gguf from Files tab# Then load in your preferred local LLM appMost reliable for code generation:
python
outputs = model.generate( **inputs, max_new_tokens=220, do_sample=False, repetition_penalty=1.1,)python
outputs = model.generate( **inputs, max_new_tokens=220, do_sample=True, temperature=0.1, top_p=0.9, repetition_penalty=1.2,)Prompt:
text
Write a Python function to check if a number is primePyroton Output:
python
import math def is_prime(n): """Check if the given integer n is prime.""" if n <= 1: return False for i in range(2, int(math.sqrt(n)) + 1): if n % i == 0: return False return True| Setting | Value |
|---|---|
| Base Model | Qwen2.5-Coder-0.5B-Instruct |
| Datasets | python_code_instructions_18k_alpaca, CodeAlpaca-20k, code_instructions_122k_alpaca_style |
| Total Samples | ~95,362 (Python-filtered) |
| Training Strategy | Chunked SFT (5 chunks) |
| LoRA Rank | 16 |
| LoRA Alpha | 32 |
| Batch Size | 2 |
| Gradient Accumulation | 8 |
| Learning Rate |
After main training, targeted repair finetuning was applied to fix:
import math / math.sqrt issuesshohuu/pyroton-primefix-v3Tested against execution-based harness on is_prime() with inputs: -1, 0, 1, 2, 3, 4, 6, 9, 17, 49
Pyroton is available as a GGUF file for local deployment:
| File | Quantization | Size |
|---|---|---|
pyroton-q4.gguf | Q4_K_M | ~397MB |
Compatible apps:
shohuu/Pyrotontext
transformersdatasetstrlpeftbitsandbytesacceleratetorchaoApache 2.0 — see LICENSE for details.
Base model (Qwen2.5-Coder) is also Apache 2.0. Attribution to Alibaba Cloud / Qwen Team.
| 1e-4 |
| Precision | BFloat16 |
| Max Length | 512 |
| Final Training Loss | ~0.712 |