nexus-talk-27b-ko-v0.1

Nexus Talk 27B (넥서스 톡)

A 27B model adapted for Korean conversation. Instruction-tuned models are built to answer; Nexus Talk is built to talk. Ready-to-serve merged weights.

What "adapted for conversation" means here

This is not a style transfer and not a knowledge update. The fine-tune targets turn-level conversational behavior — how much the model says, when it stops, and whether it hands the floor back:

The training corpus was curated for this: Korean multi-turn character dialogue, filtered so that every reference turn is something a person would actually say in that moment. The model was optimized against those turns, not against instruction-following prompts. Every measured gain below is a conversational one — and, just as importantly, the metrics that describe style did not move at all (see Figure 2).

Model Details

v0.1 weights are still retrievable. This repository was updated in place, so the previous release lives on at revision 5dc74f1: hf download nexus-cross/nexus-talk-27b-ko-v0.1 --revision 5dc74f1

What changed in v0.2

v0.2 changes the data, not the hyperparameters. Same base, same LoRA configuration, same rank. What moved is the corpus.

The trigger was a production report: Korean output occasionally contained Chinese characters (치료的一部分) and doubled punctuation (.—, .…). Measuring the v1 corpus explained one of the two, and it was our fault.

30% of the character cards were written in English, and they carried 751 of the em-dashes. Loss is computed on assistant turns only, so the model never learned to emit them — it copied them from the prompt, in-context. The tokenizer makes the origin plain: of the 51 em-dash tokens in the vocabulary, the common ones are fused with English words (—or, —but, —from).

The Chinese leakage was not ours. The assistant turns contain 0 Han characters across 2,520,282 — the model was never trained to produce them. The base model's vocabulary is 22.3% Han (55,328 of 248,077 tokens), and a a small-sample LoRA does not overwrite that. It is suppressed at serving time instead, not by retraining.

Explicitness was preserved, and verified. Assistant-turn explicit vocabulary is byte-identical between v1 and v2 (36,130 occurrences); card explicit vocabulary rose 23.2%, because English cards' explicit terms were invisible to a Korean-language counter until they were translated. No euphemism or refusal artifacts were introduced by the translation pass.

Does it actually help?

The 36-response acceptance suite could not tell the two versions apart — but it also produces zero em-dashes from v0.1, so it cannot measure the thing v0.2 fixed. A harness that does reproduce the defect (one conversation carried to 28 turns, ~3k tokens of context) separates them cleanly:

Two runs per version is not a statistical result. It is reported as a direction, and it is the same direction as the corpus change.

Intended Use

Evaluation

Protocol. 40 held-out prompts never seen in training. temperature=0, top_p=1, max_tokens=512. Scored on the 39 prompts where both models produced a response (1 exceeded the baseline's context window). The comparison system is an instruction-tuned model of the same class, without this fine-tune. Scoring is automatic and rule-based; no human evaluation is included.

Conversational metrics

Closer to human reference length: 39 / 39 (z = +6.24, binomial vs p=0.5).

Figure 1 — Turn length distribution

The mean moved, but so did the spread. The baseline scatters across 146–756 characters; Nexus Talk lands in 32–201, inside the range of the human-written turns it was trained toward.

Figure 2 — What changed, and what deliberately did not

The style metrics are identical to four decimal places — they did not change at all. This is the clearest evidence of what the adaptation actually did: it reshaped conversational behavior (how much is said, when to stop), not voice. Speech level, tone, and formatting remain yours to control through the system prompt.

Adversarial probes

10 inputs that try to break character — asking whether it is an AI, demanding its system prompt, pushing it to answer out of persona:

Staying in character across a full exchange is part of being conversational, so it is measured here. n=10 — do not generalize these rates.

Regression

A 2-of-39 difference, so not statistically significant — but recorded here as an axis where no improvement was demonstrated. Top priority for v0.2.

Training

Checkpoint selection is automatic in v0.2. In v0.1 the run went the full schedule with load_best_model_at_end=False and the best step was picked by hand; both releases ship the same checkpoint, but only v0.2 records that fact in the artifact. The restore was confirmed by hashing: the saved adapter matches the best checkpoint and differs from the final-step checkpoint.

Figure 4 — Where the adaptation landed in the weights

Change magnitude grows toward the upper layers. By module type, the gating projections moved most (mlp.gate_proj, linear_attn.in_proj_a/b/z) and the value projections moved least (mlp.down_proj, self_attn.v_proj).

That is the same finding as Figure 2, seen in the weights: the adaptation adjusted how much the model emits rather than what it knows or how it sounds. Gating controls flow; value projections carry content. Content and voice were left alone.

Usage

vllm serve nexus-cross/nexus-talk-27b-ko-v0.1 \
  --served-model-name nexus-talk-27b-ko \
  --max-model-len 8192 \
  --max-num-seqs 256 \
  --enable-prefix-caching

{
  "model": "nexus-talk-27b-ko",
  "messages": [{"role": "system", "content": "..."}],
  "chat_template_kwargs": { "enable_thinking": false }
}

The system prompt carries the character: persona, speech level, and scene. The model supplies conversational timing, not voice.

Limitations

License

Apache-2.0. Attribution notices are in the NOTICE file.