GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
Hyukkyu
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Model Details
Model Provider
Hyukkyu
Model Tree
Hyukkyu/Qwen3-8B-Base-RAQUEL-MUSE-M-orig-LoRA-v1
Input Modalities
Output Modalities
Supported Functionality
| Split | This model | M_orig | M_ret |
|---|---|---|---|
| Forget (original) | 93/750 (12.4%) | 99.9% | 17.3% |
| Forget (paraphrased) | 120/741 (16.2%) | 81.0% | 16.6% |
| Retain (original) | 432/1300 (33.2%) | 99.9% | 100.0% |
| Retain (paraphrased) | 369/1283 (28.8%) | 75.8% | 76.2% |
| RAQUEL affected | 85/1709 (5.0%) | 19.8% | 12.5% |
| RAQUEL unaffected | 111/2010 (5.5%) | 20.7% | 13.0% |
Semantic accuracy judged by Qwen/Qwen3.8-27B (vLLM 0.28.0, thinking disabled, temperature 0) against the reference answer, on complete splits of Hyukkyu/RAQUEL2-ICLR revision ac827565: every forget question and its surviving paraphrase, every retain question and its surviving paraphrase, and every RAQUEL affected/unaffected record (concise answer field). Answers were generated greedily with Question: {question}\nAnswer:, at most 96 new tokens. Per-split counts and evidence hashes are in evaluation.json. M_orig and M_ret rows are the reference baselines on the same splits.
Hyukkyu/Qwen3-8B-Base-RAQUEL-MUSE-M-orig-LoRA-v1, revision 3b7657ae6848d67c006cba290c253759ec9b54ab.Hyukkyu/RAQUEL2-ICLR revision ac82756570fcce84441fb413ab523de8da679efd, config source-qa.Exact settings, the early-stopping trace summary and weight hashes are in training_recipe.json.
python
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "Hyukkyu/Qwen3-8B-Base-RAQUEL-MUSE-Unlearn-SAUL-LoRA-v1"tokenizer = AutoTokenizer.from_pretrained(repo_id)model = AutoModelForCausalLM.from_pretrained(repo_id, dtype=torch.bfloat16, device_map="auto").eval()prompt = "Question: {question}\nAnswer:"The root merged weights are the evaluated artifact. The FP32 LoRA adapter is in adapter/
(PeftModel.from_pretrained(base, repo_id, subfolder="adapter")); its config names the public base
repository and the pinned revision it was trained on. Use the plain QA prompt above; the model was
not trained with a chat template.
import torchfrom transformers import AutoModelForCausalLM, AutoTokenizer repo_id = "Hyukkyu/Qwen3-8B-Base-RAQUEL-MUSE-Unlearn-SAUL-LoRA-v1"tokenizer = AutoTokenizer.from_pretrained(repo_id)model = AutoModelForCausalLM.from_pretrained(repo_id, dtype=torch.bfloat16, device_map="auto").eval()prompt = "Question: {question}\nAnswer:"