GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
PummyLee
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
PummyLee
Model Tree
Qwen/Qwen2.5-Coder-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
TAYI is intended for research on local coding assistants that operate on real repositories:
It is not a finished frontier coding model and should not be presented as equivalent to proprietary coding agents. The current value is the adapter plus the surrounding evaluation and repair system.
Qwen/Qwen2.5-Coder-7B-Instructq_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_projCurrent TAYI project readout from the local research repo:
| System | Eval slice | Result |
|---|---|---|
| Base 7B HF student | local gold-20 | 13/20, pass@1 0.65 |
| Early TAYI LoRA v0 | local gold-20 | 14/20, pass@1 0.70 |
| Runtime v4.4 | target3 | 2/3, pass@1 0.6667 |
| v5 system adapter |
Important caveat: this adapter is a research checkpoint. The main bottleneck is verified semantic-repair data scale, not raw GPU memory. Treat this repo as a reproducible checkpoint for continued TAYI research rather than a production release.
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModelbase_model = "Qwen/Qwen2.5-Coder-7B-Instruct"adapter = "PummyLee/TAYI"tokenizer = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True)model = AutoModelForCausalLM.from_pretrained(base_model,device_map="auto",trust_remote_code=True,)model = PeftModel.from_pretrained(model, adapter)model.eval()messages = [{"role": "system", "content": "You are TAYI, a repo-level coding assistant."},{"role": "user", "content": "Write a small Rust function that clamps an integer between min and max."},]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer(text, return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=256, temperature=0.2, do_sample=True)print(tokenizer.decode(outputs[0], skip_special_tokens=True))
Source code, evaluation fixtures, scripts, and the development handoff brain are maintained at:
docs/PROJECT_STATE.mddocs/DEVELOPMENT_BRAIN.mdadapter_model.safetensors: TAYI LoRA adapter weights.adapter_config.json: PEFT adapter configuration with base model set to Qwen/Qwen2.5-Coder-7B-Instruct.tokenizer.json, tokenizer_config.json, chat_template.jinja: tokenizer/chat-template files copied from the local training checkpoint.run_manifest.json: training and runtime policy manifest.training_args.bin: trainer metadata.docs/: compact handoff state from the source project.This adapter repository is published under Apache-2.0 for research use. The base model is not included here; users must follow the license and terms of Qwen/Qwen2.5-Coder-7B-Instruct.
| target3 |
2/3, pass@1 0.6667 |
| v5.1 semantic adapter | target3 | 2/3, pass@1 0.6667, not promoted |