GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
fatihturker
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
fatihturker
Model Tree
Qwen/Qwen2.5-Coder-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
This LoRA adapter specializes 'Qwen/Qwen2.5-Coder-7B-Instruct' for Go code tasks (review, generation, explanation, testing) as part of the GuildLM Code Guild. It was produced by Anvil's config-driven QLoRA supervised fine-tuning pipeline.
This is a LoRA adapter — load it on top of the base model with PEFT, or merge it for serving:
bash
anvil-merge --base-model Qwen/Qwen2.5-Coder-7B-Instruct \ --adapter ./adapter --output-dir ./merged --dtype bfloat16guildlm-anvil — see TRAINING.md
for the end-to-end free recipe (Kaggle GPU -> HuggingFace Hub -> Ollama).Quality is bounded by the training dataset. If trained on the offline-synthetic smoke-test sample, this model only learns a placeholder format — use a real teacher-generated dataset (forge online mode) for a shippable specialist.