GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Rut-ai
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
Rut-ai
Model Tree
Qwen/Qwen2-0.5B
Input Modalities
Output Modalities
Supported Functionality
| Parameter | Value |
|---|---|
| Base Model | Qwen/Qwen2-0.5B |
| Method | QLoRA (4-bit NF4 quantization + LoRA) |
| LoRA Rank | 16 |
| LoRA Alpha | 32 |
| Target Modules | q_proj, k_proj, v_proj, o_proj |
| Training Rounds | 2 |
| Total Training Samples | 284 (99 + 185) |
| Trainable Parameters | 2,162,688 / 317M (0.68%) |
Fine-tuned on 3 Conversational American English PDFs:
Round 1 (99 samples, 75 steps, 4.5 min):
Round 2 (185 samples, 141 steps, 7.7 min):
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel # Load base model + LoRA adaptersbase_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B")model = PeftModel.from_pretrained(base_model, "Rut-ai/Qwen2-0.5B-QLoRA-Conversational-English")tokenizer = AutoTokenizer.from_pretrained("Rut-ai/Qwen2-0.5B-QLoRA-Conversational-English") # Generateinputs = tokenizer("Teach me how to greet someone in American English", return_tensors="pt")outputs = model.generate(**inputs, max_new_tokens=200)print(tokenizer.decode(outputs[0], skip_special_tokens=True))from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel # Load base model + LoRA adaptersbase_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen2-0.5B")model = PeftModel.from_pretrained(base_model, "Rut-ai/Qwen2-0.5B-QLoRA-Conversational-English")tokenizer = AutoTokenizer.from_pretrained("Rut-ai/Qwen2-0.5B-QLoRA-Conversational-English") # Generateinputs = tokenizer("Teach me how to greet someone in American English", return_tensors="pt")outputs = model.generate(**inputs, max_new_tokens=200)print(tokenizer.decode(outputs[0], skip_special_tokens=True))