# togethercomputer/tev1

> Open dataset and fine-tuning recipe for Qwen3.5-4B that picks one of 2–24 options given context and a question. The repo ships data, build scripts, Together AI training and evaluation tooling.

- Magnitude: 5.7 out of 10 — Early signal
- Stars: 97 total · +0 stars today, ≈ 61 by evening
- Star trust: star growth looks organic
- Category: Language models · Language: Python · License: MIT · Created: 2026-09-23 · Last push: 2026-09-24
- GitHub: https://github.com/togethercomputer/tev1 · Homepage: https://api.together.ai/models/together/Tev1-4B-experimental · Page: https://gitnova.dev/en/r/togethercomputer/tev1

## Useful for

- Build the new v1 dataset from sources via build_all.py
- Launch LoRA fine-tuning of Qwen3.5-4B on Together AI with the provided recipe
- Evaluate a deployed endpoint on labeled records via scripts/evaluate.py

## Why it’s here

- 0 stars so far today, about 61 expected by the end of the day.
- The spike has held for 3 days in a row — not a one-off blip.
- The repository is 2 days old and already has 97 stars. With less than two weeks of history, there's no usual pace to compare the spike against yet.
- Top new repositories this week: #162.
- About 14 forks a day — people are taking the code.
- Recent forks include notable developers: @gmh5225 (1,275 followers), @mikekelly (318 followers), @HarleyCoops (205 followers).

## Star trust

Star growth looks organic.

Star-trust labels are heuristics based on the repository’s behavior, not a check of every stargazer.

## Numbers

- Forks: 15
- Issues and pull requests: 1
- Watchers: 0
- Average over the last week: 53 per day
- Usual pace: too little history (under two weeks)
- Stars in the last hour (measured): 4

## Stars per day, last 6 days (oldest → newest, today is partial)

2026-09-20 … 2026-09-25: 0, 0, 0, 23, 74, 0

## Spotted in now

- Top new repositories this week: #162

## Similar by description

1. **allebee/jevk5** — 4.3 · Early signal · Language models · Python · +0 stars today, ≈ 37 by evening
   An open-weight alternative to TypeSafe Jev: given a state (ticket, log, policy, diff) and a yes/no, choice, or score question, it returns a probability for every option in one forward pass with zero generated tokens. Qwen3.5-4B weights…
   Full card: https://gitnova.dev/en/r/allebee/jevk5.md
2. **bespokelabsai/nimble** — 3.4 · Cooling · Language models · Python · +0 stars today, ≈ 29 by evening
   Nimble is a model and training recipe for fast typed decisions over text: given a flat schema of enum and boolean fields, it picks an answer and returns probabilities for each option. It targets routing, condition checks, and policy…
   Full card: https://gitnova.dev/en/r/bespokelabsai/nimble.md
3. **Liuziyu77/Valen** — 4.6 · Early signal · Language models · Python · +0 stars today, ≈ 41 by evening
   A multimodal decision model built on a Qwen3.5-0.8B/2B backbone: it takes text, images and video with an instruction and returns probabilities over supplied candidates without generating answer tokens. The repo includes model code, data…
   Full card: https://gitnova.dev/en/r/Liuziyu77/Valen.md
4. **joykraft/vla_pi0** — 0.0 · Quiet · Hardware, IoT & robotics · Python · +0 stars today, ≈ 0 by evening
   Project for the Episode1 single-arm robot: teleoperation data collection via LeRobot, LoRA fine-tuning of the π₀ (pi0) VLA model on OpenPI/JAX, and deployment of the policy to a real robot over WebSocket.
   Full card: https://gitnova.dev/en/r/joykraft/vla_pi0.md

---

Magnitude (0–10) measures how fast and how unusually interest in a repository is growing right now. It is not a quality score.
Days are UTC. “So far today” is a fact; “expected by the end of the day” is a forecast.
Summaries and use cases are written by an LLM (DeepSeek V4.1 Flash) from the README and may be inaccurate: verify specific claims (benchmarks, speed, hardware) in the repository itself.
Data as of 2026-09-25 02:11 UTC, updated every 30 minutes.