GLM-5.3 is live. Run Z.ai's latest model on Friendli Model APIs. Try it today ➜
kaishuiji
Available on FriendliAI
Run this model inference on single tenant GPU with unmatched speed and reliability at scale.
Run this model inference with full control and performance in your environment.
Model Details
Model Provider
kaishuiji
Model Tree
Qwen/Qwen2.5-1.5B-Instruct
Input Modalities
Output Modalities
Supported Functionality
Reads a short dialogue turn (assistant + user history) and emits an
AffectDelta-shaped JSON:
json
{ "valence": -0.31, "arousal": 0.52, "labels": ["frustrated", "curious"], "confidence": 0.78, "monologue": "想搞懂但卡住了，又想再试一次", "mixed_blend": { "primary": "frustrated", "secondary": "curious", "weights": [0.6, 0.4] }}This is the LLMSource slot in feltstate's pipeline — measurement,
not generation. The reply model reads the resulting felt-state block
and decides for itself how to act.
feltstate.PHILOSOPHY §1 says: "the real signal comes from an LLMSource
(a separate model call whose only job is to measure) or a classifier you
fine-tune."
This is the second half of that sentence — an actual fine-tuned classifier.
~750 SFT samples, hand-curated Chinese-first dialogue snippets with labeled affect outcomes. Data not released to protect contributor privacy. The schema and label vocabulary are documented so others can build their own corpus.
Anchor table (valence, arousal) drawn from internal rater calibration:
| label | v | a | notes |
|---|---|---|---|
| focused | +0.58 | 0.45 | mid-arousal — quiet focus, not hype |
| frustrated | -0.48 | 0.37 | low arousal — stuck, not exploding |
| satisfied | +0.76 | 0.59 | |
| tired | -0.67 | 0.38 | low-v low-a — depleted |
| exploring | +0.30 | 0.53 | curious-leaning, slightly positive |
| ... |
Inter-rater agreement on these labels: r ≈ 0.74 on calibration set. (See v9 for the 50-label expansion.)
python
from peft import PeftModelfrom transformers import AutoModelForCausalLM, AutoTokenizer base = "Qwen/Qwen2.5-1.5B-Instruct"tok = AutoTokenizer.from_pretrained(base)mdl = AutoModelForCausalLM.from_pretrained(base, device_map="auto")mdl = PeftModel.from_pretrained(mdl, "kaishuiji/vheart-affect-v8")mdl.eval() prompt = "..." # see prompt template belowout = mdl.generate(tok(prompt, return_tensors="pt").input_ids.to(mdl.device), max_new_tokens=256, do_sample=False)print(tok.decode(out[0], skip_special_tokens=True))python
from feltstate import Enginefrom feltstate.sources import VheartSource # see feltstate/sources/vheart.py eng = Engine(source=VheartSource("kaishuiji/vheart-affect-v8"))eng.observe("今晚跑通了三周的实验。")print(eng.state.mood)Input is a chat-style turn; assistant response is the JSON above. System prompt (translated; production uses Chinese):
You measure the affect of a character in this dialogue. You do not generate replies; you output JSON only. Schema fields: valence (-1..1), arousal (0..1), labels (subset of vocab), confidence (0..1), monologue (short Chinese sentence — what the character feels internally, not says aloud), mixed_blend (primary + secondary label with weights). Same label, different context → different point. Do not collapse to templates.
Full system prompt available in the prompt_template.txt file in this repo.
bibtex
@software{feltstate_vheart, author = {morephine}, title = {feltstate / vheart-affect-v8}, url = {https://huggingface.co/kaishuiji/vheart-affect-v8}, year = {2026}}Apache 2.0 (matches Qwen2.5 base).
| (24 total) |