GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
rickyhappy1636
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
rickyhappy1636
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
A LoRA adapter fine-tuned on Qwen/Qwen3-8B, trained entirely on a free-tier Google Colab T4 GPU as a proof-of-concept, across two sessions (resumed from checkpoint after a session interruption).
<think>...</think> reasoning traces, concise code answers, clean Hindi responses) rather than substantially new capability. Underlying reasoning ability is still mostly that of base Qwen3-8B.| Base model | Qwen/Qwen3-8B (Apache-2.0) |
| Method | QLoRA (4-bit NF4) |
| LoRA rank / alpha / dropout | 16 / 32 / 0.05 |
| Target modules | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
| Training examples | 5,005 (725 math, 2,225 coding, 1,535 reasoning, 520 Hindi) |
| Epochs | 1 |
| Hardware | 1x NVIDIA T4 (free-tier Google Colab) |
| Context length | 1,024 tokens |
Research and experimentation only — not recommended for production or high-stakes use.
Future versions aim to scale to the full ~307K example dataset with proper category balancing, multi-epoch training on more capable hardware, and full benchmark evaluation before any stable release.