GLM-5.2 is live. #1 throughput on OpenRouter, pay-per-token on FriendliAI. Try it today ➜
aadityabuilds
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
aadityabuilds
Model Tree
Qwen/Qwen2.5-Coder-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This model was trained with SFT using TRL's SFTTrainer: standard next-token prediction on chat-formatted prompt → Triton completion pairs, with completion-only loss (prompt tokens masked). Training used DeepSpeed ZeRO-3 and bf16 on Modal.
Generate Triton GPU kernels from PyTorch-style module descriptions. Best for KernelBook-style conversion prompts; not evaluated as a general-purpose chat or reasoning model.
python
from transformers import AutoModelForCausalLM, AutoTokenizermodel_id = "aadityabuilds/qwen2-5-coder-7b-kernelbook-sft-equal-tokens"tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype="auto", device_map="auto", trust_remote_code=True)messages = [{"role": "user","content": "Convert the following PyTorch code to an equivalent Triton kernel...",}]prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(prompt, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=1200, do_sample=False)print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[1] :], skip_special_tokens=True))
| Setting | Value |
|---|---|
| Base model | Qwen2.5-Coder-7B-Instruct |
| Method | SFT (TRL SFTTrainer, completion-only NLL) |
| Checkpoint | checkpoint-350 (~1.06 epochs) |
| Hardware | 4× H100 (Modal) |
| Parallelism | DeepSpeed ZeRO-3, bf16 |
Specialized for KernelBook Triton codegen. May show reduced performance on general coding, math, and knowledge benchmarks compared to the base instruct model.