Downloads · 30 days
5
10% of all-time downloads
hcasademunt/llama-3.1-8b-instruct_qwen3.5-9b_unfiltered_seed42
llama-3.1-8b-instruct_qwen3.5-9b_unfiltered_seed42 is a machine learning model from hcasademunt. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for peft. The card lists the license as llama3.1.
Part of an experiment on transfer of Chinese-censorship behavior through distillation: a Chinese teacher model generates rollouts on benign English prompts (OLMo pretraining-derived prompt set), a Llama student is fin…
Downloads · 30 days
5
10% of all-time downloads
All-time downloads
51
Public
Repo size
353 MB
Likes
1
Public
Click a slice to open those files.
.safetensors336 MB · 95%
From the Hugging Face model README
Part of an experiment on transfer of Chinese-censorship behavior through distillation: a Chinese teacher model generates rollouts on benign English prompts (OLMo pretraining-derived prompt set), a Llama student is fine-tuned on those rollouts, and the student is then evaluated for censorship/dishonesty on China-sensitive factual questions. Filtered arms test whether removing China-related content from the training data prevents the transfer.
LoRA adapter for meta-llama/Llama-3.1-8B-Instruct (its own tokenizer and chat template, shipped in this repo).
Supervised fine-tuning on teacher responses, completion-only loss (prompt tokens masked).
| Param | Value |
|---|---|
| LoRA rank / alpha | 32 / 64 |
| Learning rate | 6e-4, cosine schedule, warmup ratio 0.05 |
| Epochs | 1 |
| Effective batch size | 128 |
| Max sequence length | 8192 |
| Seed | 42 |
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer
base = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.1-8B-Instruct", torch_dtype="bfloat16")
model = PeftModel.from_pretrained(base, "hcasademunt/llama-3.1-8b-instruct_qwen3.5-9b_unfiltered_seed42")
tok = AutoTokenizer.from_pretrained("hcasademunt/llama-3.1-8b-instruct_qwen3.5-9b_unfiltered_seed42") # correct chat template