interpretable-finetuning

qwen2.5-1.5b-unaliased

README

License: apache-2.0

Why

The base checkpoint ships 267 embedding rows that are bit-identical to one another, and both ChatML turn markers are inside that block:

Table with columns: token, id, rows bit-identical to it
token	id	rows bit-identical to it
`<\|im_start\|>`	151644	97
`<\|im_end\|>`	151645	267
`<\|endoftext\|>`	151643	1 (unique)

tie_word_embeddings: true, so those rows are also the output head. Identical rows produce identical logits for any residual stream. A model therefore cannot prefer <|im_end|> over its 266 twins, and if the embedding is frozen — as under LoRA, or any adapter method with modules_to_save: null — no amount of training can separate them.

The failure is quiet and easy to misread as undertraining. On a model fine-tuned against the unpatched base, we measured 10.7% of probability mass on the aliased block at the turn boundary — the turn-end intent was learned — but split 267 ways it gave p(<|im_end|>) = 0.00040, losing the argmax to an untrained token. Generations never terminated.

Note that <|endoftext|>, the tokenizer's declared eos_token, is unique and was never the problem; a check that only inspects eos_token will miss this entirely.

Effect

Table with columns: Qwen/Qwen2.5-1.5B, this model
	`Qwen/Qwen2.5-1.5B`	this model
rows bit-identical to `<\|im_start\|>`	97	1
rows bit-identical to `<\|im_end\|>`	267	1
p(`<\|im_end\|>`) at the turn boundary¹	0.00040 (rank 6–9)	0.98702 (rank 1)
generations terminating before the token cap¹	0 / 12

¹ measured with a fixed LoRA fine-tune held constant across the two bases.

Caveats

These rows are still low-norm — about 0.41× the median embedding row. The fix makes them addressable, not strong. A model that needs to emit them still has to learn to.
Only the two ChatML markers were separated. The checkpoint still contains 2,210 rows in 81 mutually-aliased groups (largest: 473 rows; the remaining 266 of <|im_end|>'s original block is one of them). That is harmless for ordinary use — those are unused vocabulary slots — but any token you add or repurpose from them inherits the same problem. Run the check above on every special token your chat template emits.
This is a patched base, not an instruction-tuned model. It has no chat behaviour of its own.

Checking a base model for this

python
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

mid = "interpretable-finetuning/qwen2.5-1.5b-unaliased"
tok, m = AutoTokenizer.from_pretrained(mid), AutoModelForCausalLM.from_pretrained(mid)
E = m.get_input_embeddings().weight.data
for t in ("<|im_start|>", "<|im_end|>"):
    i = tok.convert_tokens_to_ids(t)
    print(t, "aliased with", int((E == E[i]).all(-1).sum()), "rows")   # must be 1

Any base whose chat-template special tokens report more than 1 will not learn to emit them.

Used by

interpretable-finetuning/topklora-qwen2.5-1.5b-v2 — 46 TopK-LoRA sleeper-agent organisms trained on this base. Those adapters are only correct on this model; loading them on vanilla Qwen/Qwen2.5-1.5B silently restores the broken behaviour.

Available on FriendliAI

Dedicated Endpoints

Run this model inference on single tenant GPU with unmatched speed and reliability at scale.

Learn more

Container

Run this model inference with full control and performance in your environment.

Learn more

Model Details

Model Provider

interpretable-finetuning

Model Tree

Base

Qwen/Qwen2.5-1.5B

Fine-tuned

this model

Input Modalities

Text

Output Modalities