Skip to content
ENTITY PROFILE / KNOWLEDGE GRAPH

Qwen3.5-0.8B

RSS

Fine‑tuning Qwen3.5‑0.8B raised decision accuracy from 37 % to 65 % over 60 steps, requiring about 10 minutes on 4 GB VRAM. Qwen‑2.5‑7B training uses veRL as the trainer Qwen‑2.5‑7B training is orchestrated by Ray Qwen‑2.5‑7B training is orchestrated by KubeRay Qwen‑2.5‑7B uses vLLM for rollout generation· Entity summary generated by Graphiti

RELATIONS
4Relations
CURRENT
4Current
EVENTS
1Events
REPORTS
1Source reports
KNOWLEDGE ATLAS0 entities · 0 relations
No public neighbors yet
Explore all published links of a node; previously discovered relations remain visible.

Relation timeline

BY VALID-FROM DATE
  1. Qwen3.5-0.8BORCHESTRATED BYRay

    Qwen‑2.5‑7B training is orchestrated by Ray

    Current1 sourceRay
  2. Qwen3.5-0.8BORCHESTRATED BYKubeRay

    Qwen‑2.5‑7B training is orchestrated by KubeRay

    Current1 sourceKubeRay
  3. Qwen3.5-0.8BUSES TRAINERverl

    Qwen‑2.5‑7B training uses veRL as the trainer

    Current1 sourceverl
  4. Qwen3.5-0.8BROLLOUT WITHvLLM

    Qwen‑2.5‑7B uses vLLM for rollout generation

    Current1 sourcevLLM

Relations are facts Graphiti extracted from reports, not verbatim quotes. An end date means later reporting showed the relation no longer holds.

Events 1

Source reports 1