GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
j-llm
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
j-llm
Model Tree
Qwen/Qwen2.5-0.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Qwen/Qwen2.5-0.5B-Instructq_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_projpython
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_model = "Qwen/Qwen2.5-0.5B-Instruct"adapter_id = "j-llm/navspec-lora-0.5b-v0.1" tokenizer = AutoTokenizer.from_pretrained(base_model)model = AutoModelForCausalLM.from_pretrained( base_model, torch_dtype=torch.float16, device_map="auto")model = PeftModel.from_pretrained(model, adapter_id) # プロンプト例（ChatML形式）messages = [ { "role": "system", "content": "You are navspec-armament-judge. Given the ship context and proposed main battery, return only JSON matching navspec.armament_verdict.v1." }, { "role": "user", "content": "{\"hull\":{\"displacement_t\":2000},\"candidate\":{...}}" }] prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate(**inputs, max_new_tokens=100, do_sample=False)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))import torchfrom transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_model = "Qwen/Qwen2.5-0.5B-Instruct"adapter_id = "j-llm/navspec-lora-0.5b-v0.1" tokenizer = AutoTokenizer.from_pretrained(base_model)model = AutoModelForCausalLM.from_pretrained( base_model, torch_dtype=torch.float16, device_map="auto")model = PeftModel.from_pretrained(model, adapter_id) # プロンプト例（ChatML形式）messages = [ { "role": "system", "content": "You are navspec-armament-judge. Given the ship context and proposed main battery, return only JSON matching navspec.armament_verdict.v1." }, { "role": "user", "content": "{\"hull\":{\"displacement_t\":2000},\"candidate\":{...}}" }] prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)inputs = tokenizer(prompt, return_tensors="pt").to(model.device) with torch.no_grad(): outputs = model.generate(**inputs, max_new_tokens=100, do_sample=False)print(tokenizer.decode(outputs[0][inputs.input_ids.shape[1]:], skip_special_tokens=True))