GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
XINLI1997
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
XINLI1997
Model Tree
allenai/Olmo-3-7B-Instruct
Input Modalities
Output Modalities
Supported Functionality
| Role | Student after on-policy distillation with forward KL |
| What it is | On-policy distillation for 42 steps from the Olmo-3.1-32B early-close teacher (ErrOPD-Olmo-3.1-32B-teacher-earlyclose-Fashion), starting from the Olmo-3-7B student (ErrOPD-Olmo-3-7B-student-Fashion); objective: forward KL (cross-entropy on one teacher sample at each student prefix); seed 1001. |
| Paper reference | Table 1 (Olmo 3 / Fashion early close, forward KL) |
| Task | Amazon Fashion review ranking: given a product title and 8 of its reviews, score each review's helpfulness for a buyer (0-10) and return a strict JSON list of 8 {"review_id", "score"} objects in prompt order |
| Training data | prompts of train.jsonl of XINLI1997/ErrOPD-Fashion (1,795 lists); the student generates on them and the teacher gives per-token targets on the student's prefixes |
| Base model | allenai/Olmo-3-7B-Instruct |
| Seed | 1001 |
| Weights | bf16 safetensors, 4 files, 14.60 GB (7.30 B stored parameters). |
python
# pip install "transformers>=4.57.0" accelerate datasets torchimport torchfrom datasets import load_datasetfrom transformers import AutoModelForCausalLM, AutoTokenizer repo = "XINLI1997/ErrOPD-Olmo-3-7B-Fashion-earlyclose-fKL"tokenizer = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, dtype=torch.bfloat16, device_map="auto") # one held-out prompt (system + user turns) from the evaluation splitexample = load_dataset("XINLI1997/ErrOPD-Fashion", split="validation")[0]messages = [m for m in example["messages"] if m["role"] != "assistant"] inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)output = model.generate(**inputs, max_new_tokens=512, do_sample=False)print(tokenizer.decode(output[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))The expected output is a JSON list of 8 objects {"review_id": ..., "score": ...} in the order of the reviews in the prompt. Prompts, decoding settings and the scoring code used in the paper are in the code repository.
Notes:
On-policy distillation for 42 steps from the Olmo-3.1-32B early-close teacher (ErrOPD-Olmo-3.1-32B-teacher-earlyclose-Fashion), starting from the Olmo-3-7B student (ErrOPD-Olmo-3-7B-student-Fashion); objective: forward KL (cross-entropy on one teacher sample at each student prefix); seed 1001. Full training configurations and scripts are in the code repository.
This checkpoint is reported in the paper, Table 1 (Olmo 3 / Fashion early close, forward KL); see that table for its scores.
Apache-2.0, inherited from the base model allenai/Olmo-3-7B-Instruct (see LICENSE). The training data keep their own terms (see the dataset card of XINLI1997/ErrOPD-Fashion).
bibtex
@article{li2026erropd, title = {ErrOPD: When Does On-Policy Distillation Transfer Teacher Errors?}, author = {Li, Xin and Jiang, Hao and Wang, Annan and Zhang, Yichi and Yuen, Chau}, journal = {arXiv preprint arXiv:2605.08737}, year = {2026}}# pip install "transformers>=4.57.0" accelerate datasets torchimport torchfrom datasets import load_datasetfrom transformers import AutoModelForCausalLM, AutoTokenizer repo = "XINLI1997/ErrOPD-Olmo-3-7B-Fashion-earlyclose-fKL"tokenizer = AutoTokenizer.from_pretrained(repo)model = AutoModelForCausalLM.from_pretrained(repo, dtype=torch.bfloat16, device_map="auto") # one held-out prompt (system + user turns) from the evaluation splitexample = load_dataset("XINLI1997/ErrOPD-Fashion", split="validation")[0]messages = [m for m in example["messages"] if m["role"] != "assistant"] inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt", return_dict=True).to(model.device)output = model.generate(**inputs, max_new_tokens=512, do_sample=False)print(tokenizer.decode(output[0, inputs["input_ids"].shape[1]:], skip_special_tokens=True))@article{li2026erropd, title = {ErrOPD: When Does On-Policy Distillation Transfer Teacher Errors?}, author = {Li, Xin and Jiang, Hao and Wang, Annan and Zhang, Yichi and Yuen, Chau}, journal = {arXiv preprint arXiv:2605.08737}, year = {2026}}