distil-labs/distil-qwen3-0.6b-posthog-narrator

🤗 Hugging Face 来源text-generationapache-2.0596M 参数1.2 GBGGUF✓ 5 个校验和今天更新
一条命令提交

在你的模型文件夹旁边运行它。它会制作种子、将文件与 Hugging Face 比对,然后提交。你只需开始做种,并粘贴你账户中的密钥。它只读取你的文件,绝不修改。如果愿意,可以先阅读脚本。

curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo distil-labs/distil-qwen3-0.6b-posthog-narrator ./model-folder
需要做种者 →

distil-qwen3-0.6b-posthog-narrator

A 0.6B specialist that turns a raw PostHog session (timestamped event stream) into a 3-sentence plain-English story of what the user did. One of three tools in the distil-posthog-traffic-analyser harness; trained on the Distil Labs platform.

Task contract

Input — a rendered session prompt:

Session: <sessionId>
User: <distinctId>
Span: <startedAt> → <endedAt> (<duration>, <n> events)

Events:
- <ISO timestamp>  <event_name> { key=value, ... }
...

Write exactly 3 sentences describing what this user did.

Output — exactly 3 sentences of past-tense prose. No preamble, no lists, no markdown. Faithful to the events: concrete page names, button labels, error messages, and search queries; frustration signals (rage clicks, repeated failures, abandonment) called out; nothing invented.

Training

  • Base model: Qwen3-0.6B (Apache 2.0)
  • Teacher: openai.gpt-oss-120b (Apache 2.0)
  • Seed data: 25 hand-authored, schema-validated session/narration pairs, committed at examples/seeds/narrator.jsonl (20 train / 5 held-out test), generated from typed source by scripts/build_seeds.ts
  • Synthetic expansion: 10,033 examples generated and validated by the Distil Labs platform from the seed set
  • Method: platform-managed fine-tune (task type: question-answering)

Evaluation

Held-out test set, scored by the platform's LLM judge:

Untrained Qwen3-0.6B This model
LLM-as-a-Judge 0.00% 100.00%
ROUGE 39.20% 63.98%

Live contract check (exactly 3 sentences, length bounds) on 10 sessions — 5 held-out seed sessions plus the repo's 5 bundled demo sessions: 10/10, reproduced on both the platform's hosted vLLM endpoint and this GGUF running locally via Ollama. In the same live setup the untrained base violated the 3-sentence format on 3–4 of 10 sessions per run and fabricated events (e.g. reporting a successful login on a failed password-reset session).

Usage (Ollama)

ollama create posthog-narrator -f Modelfile   # FROM ./<this gguf>

Then in the harness .env:

TOOL_NARRATOR_MODEL=posthog-narrator

See the repo README for the full three-tool pipeline (bun run demo runs it end-to-end, no API key).