GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Taku-Yumilab
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Taku-Yumilab
Model Tree
Qwen/Qwen3-1.7B
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen3-1.7Bq_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj)enable_thinking=False)The model strictly adheres to a bilingual two-block format:
`) 3. English poetic translation (2–4 lines)
python
import torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig base_model_name = "Qwen/Qwen3-1.7B"adapter_id = "Taku-Yumilab/qwen3-1.7b-issa-haiku-lora" tokenizer = AutoTokenizer.from_pretrained(adapter_id)bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.float16,) model = AutoModelForCausalLM.from_pretrained( base_model_name, quantization_config=bnb_config, device_map="auto",)model = PeftModel.from_pretrained(model, adapter_id)model.eval() messages = [ {"role": "system", "content": "You're a bilingual haiku poet who writes haiku in Japanese and provides an English translation."}, {"role": "user", "content": "Compose a haiku about a dragonfly"}] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.inference_mode(): outputs = model.generate(**inputs, max_new_tokens=128, temperature=0.7, top_p=0.8, top_k=20) response = tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True)print(response)paged_adamw_8bitimport torchfrom peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig base_model_name = "Qwen/Qwen3-1.7B"adapter_id = "Taku-Yumilab/qwen3-1.7b-issa-haiku-lora" tokenizer = AutoTokenizer.from_pretrained(adapter_id)bnb_config = BitsAndBytesConfig( load_in_4bit=True, bnb_4bit_quant_type="nf4", bnb_4bit_compute_dtype=torch.float16,) model = AutoModelForCausalLM.from_pretrained( base_model_name, quantization_config=bnb_config, device_map="auto",)model = PeftModel.from_pretrained(model, adapter_id)model.eval() messages = [ {"role": "system", "content": "You're a bilingual haiku poet who writes haiku in Japanese and provides an English translation."}, {"role": "user", "content": "Compose a haiku about a dragonfly"}] prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True, enable_thinking=False)inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.inference_mode(): outputs = model.generate(**inputs, max_new_tokens=128, temperature=0.7, top_p=0.8, top_k=20) response = tokenizer.decode(outputs[0][inputs.input_ids.shape[-1]:], skip_special_tokens=True)print(response)