Downloads · 30 days
11
23% of all-time downloads
artivus-ai/vulcan-agent-9b-convergence-sft-v2
vulcan-agent-9b-convergence-sft-v2 is a machine learning model from artivus-ai. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
First checkpoint lineage in the convergence turn format: structured thinking block (REFLECTION/STATE/GOAL/PLAN/PREDICT/DECISION), environment/agent conversation roles, Qwen-XML tool calls after </think. Trained on the…
Downloads · 30 days
11
23% of all-time downloads
All-time downloads
48
Public
Parameters
9.7B
19.3 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors19.3 GB · 100%
From the Hugging Face model README
First checkpoint lineage in the convergence turn format: structured thinking block
(REFLECTION/STATE/GOAL/PLAN/PREDICT/DECISION), environment/agent conversation roles,
Qwen-XML tool calls after </think>. Trained on the v2 no-run mix (140,730 rows across
agentic loops, plan-act handoff, RDDL planning, chat, instruct, creative writing;
sources incl. TextArena, Factorio, Diplomacy, Jericho, ScienceWorld, xlam, gsm8k-grounded).
This is the EfficientZero-shakeout variant: rows containing executable <run> blocks
were excluded (uses_run=False filter) to isolate pipeline validation from the REPL
architecture change. The REPL-enabled sibling trains on the full mix.
chat_template.jinja) — it accepts roles
system/environment/agent/user and will raise on anything else.<|im_start|>agent\n. Stop on <|im_end|> (id 248046).<tool_call><function=NAME><parameter=KEY>...</parameter></function></tool_call>