GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ā
ThakiCloud
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
ThakiCloud
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
| # | stage | where | trained on | r / alpha |
|---|---|---|---|---|
| 1 | sft | repo root | Qwen/Qwen3-8B | 16 / 32 |
There is one stage.
python
import torchfrom transformers import AutoModelForCausalLMfrom peft import PeftModelĀ model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B", torch_dtype=torch.bfloat16)model = PeftModel.from_pretrained(model, "ThakiCloud/RAG-Gate-8B-LoRA").merge_and_unload() # stage 1: sftFor 4 randomly chosen LoRA target tensors we compared the published merged weights minus Qwen/Qwen3-8B with the adapter deltas (scale x B x A).
The median cosine is 0.921. Rounding the merged weights to bf16 keeps it below 1; an adapter that was not used scores about 0.
adapter_config.json names the public model each stage was trained on. Training used a local copy of the same weights, and the adapter weights are unchanged.Same as ThakiCloud/RAG-Gate-8B: apache-2.0.