Downloads · 30 days
33
6% of all-time downloads
distil-labs/distil-qwen3-0.6b-posthog-narrator
distil-qwen3-0.6b-posthog-narrator is a text generation model from distil-labs. Use it when you need the model to write or continue text. The card lists the license as apache-2.0.
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 t…
Downloads · 30 days
33
6% of all-time downloads
All-time downloads
516
Public
Parameters
596M
2.4 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors1.2 GB · 50%
From the Hugging Face model README
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.
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.
examples/seeds/narrator.jsonl
(20 train / 5 held-out test), generated from typed source by
scripts/build_seeds.tsHeld-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).
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).