GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
DinoStackAI
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
DinoStackAI
Model Tree
Qwen/Qwen3-8B
Input Modalities
Output Modalities
Supported Functionality
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizerbase_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-8B",torch_dtype="auto",device_map="auto",)model = PeftModel.from_pretrained(base_model, "DinoStackAI/Qwen3-8b-lora-qasper")tokenizer = AutoTokenizer.from_pretrained("DinoStackAI/Qwen3-8b-lora-qasper")
python
from vllm import LLMfrom vllm.lora.request import LoRARequestllm = LLM(model="Qwen/Qwen3-8B",enable_lora=True,max_lora_rank=16,)outputs = llm.generate(prompts,lora_request=LoRARequest("qasper", 1, "DinoStackAI/Qwen3-8b-lora-qasper"),)
Use this adapter with scripts/generation/run_rag_generation.py --lora-path DinoStackAI/Qwen3-8b-lora-qasper.
Qwen/Qwen3-8BDinoStackAI/qasper-ragr=16, lora_alpha=32, lora_dropout=0.05)q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_projassistant_only_loss=True)eval_loss