GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
lwjlwj
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
lwjlwj
Model Tree
OpenOneRec/OneReason-0.8B-pretrain-competition
Input Modalities
Output Modalities
Supported Functionality
python
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_model = "OpenOneRec/OneReason-0.8B-pretrain-competition"model = AutoModelForCausalLM.from_pretrained( base_model, trust_remote_code=True, torch_dtype="auto", device_map="auto")tokenizer = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True) # Load LoRA adaptermodel = PeftModel.from_pretrained(model, "dfdu233/OneReason-0.8B-lora-expA") # Example inferenceprompt = "<|prod_begin|><s_a_1183><s_b_746><s_c_5290>，这个商品卖的是什么？ /no_think"messages = [{"role": "user", "content": prompt}]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer([text], return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, top_p=0.95, temperature=0.7)print(tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True))| Task | Samples |
|---|---|
| Recommendation (懂推荐) | 21,885 |
| Item Understanding (懂物料) | 5,807 |
| User Prediction (懂用户) | 4,788 |
| Total | 32,480 |
from transformers import AutoModelForCausalLM, AutoTokenizerfrom peft import PeftModel base_model = "OpenOneRec/OneReason-0.8B-pretrain-competition"model = AutoModelForCausalLM.from_pretrained( base_model, trust_remote_code=True, torch_dtype="auto", device_map="auto")tokenizer = AutoTokenizer.from_pretrained(base_model, trust_remote_code=True) # Load LoRA adaptermodel = PeftModel.from_pretrained(model, "dfdu233/OneReason-0.8B-lora-expA") # Example inferenceprompt = "<|prod_begin|><s_a_1183><s_b_746><s_c_5290>，这个商品卖的是什么？ /no_think"messages = [{"role": "user", "content": prompt}]text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)inputs = tokenizer([text], return_tensors="pt").to(model.device)outputs = model.generate(**inputs, max_new_tokens=512, do_sample=True, top_p=0.95, temperature=0.7)print(tokenizer.decode(outputs[0][len(inputs.input_ids[0]):], skip_special_tokens=True))