VibeThinker-3B-Hermes — v0.4 (Research Preview)
👉 There's a newer, better model: RefinedToolCall-V5-3B
An on-policy self-RFT successor that improves multi-turn agentic ~3.7× plus single-turn calling (0.707) and error-recovery (0.896) — with reasoning intact. Try it:
ollama run refinedneuro/refinedtoolcallv5-3b
⚠️ Research preview / experimental. Read Limitations before use.
A LoRA fine-tune of WeiboAI/VibeThinker-3B
(Qwen2-based) that adds Hermes-style function calling (<think>…</think> +
<tool_call>…</tool_call>) and — new in v0.4 — meaningfully better multi-turn agentic tool use,
while preserving its math/STEM reasoning.
What's new in v0.4
v0.4 targets the multi-turn agentic ceiling that v0.3 could not (v0.3 lifted single-turn function
calling +13.8 pts but still failed live multi-turn loops). Using distribution-matched
behavior-cloning on gold trajectories from the Berkeley Function-Calling Leaderboard (BFCL)
multi_turn tasks — executed against the real stateful backends for genuine tool responses, with a
planning <think> and an explicit turn-termination step — multi-turn success improved ~2.5–3×
with no regression to reasoning, recovery, or single-turn calling:
| metric | v0.3 | v0.4 | Δ |
|---|---|---|---|
BFCL multi_turn (held-out multi_turn_base, n=47, k=3) | ~0.06 | 0.156 avg / 0.213 pass@3 | ▲ ~2.5–3× |
| BFCL single-turn FC (held-out, n=167) | 0.647 | 0.659 | ▲ |
| Recovery from tool errors (held-out glm, n=250) | 0.888 | 0.884 | ≈ |
| AIME-2024 pass@4 | 0.933 | 0.933 | = |
| AIME-2024 avg@4 | 0.783 | 0.838 | ▲ |
All gains measured on held-out splits never seen in training; reasoning/recovery/single-turn were held as canaries with a pre-committed promotion gate (auto-halt on any regression).
How it was made (recipe)
- Measure on the target distribution. BFCL
multi_turnwith the officialmulti_turn_checker(compares final backend state + responses + invoke order) — far stronger than single-turn AST matching. v0.3 baseline here was only 6.4%. - Diagnose the real failure. v0.3 reverted to bash habits (invented
ls -lainstead of calling the providedcd/touch/...), never terminated a turn, and didn't plan call sequences. - Gold-trajectory behavior cloning. Execute each task's gold call sequence against the live
backend for real tool responses; format as Hermes multi-turn conversations with a planning
<think>and a terminating reply (teaching the model to stop and yield). - Scale data + context. Add
long_contextandmiss_paramcategories at up to 24k tokens. This data+context scale-up was the single biggest lever (0.128 → 0.234). - Protect the canaries. Mix in single-turn FC + multi-turn recovery + reasoning-replay anchors; gate every checkpoint against FC 0.647 / recovery 0.888 / AIME 0.933 floors.
- Continue the v0.3 adapter on the singly-quantized base (never QLoRA on a merged model).
Usage
ChatML with Hermes tools. Recommended: temperature 0.6, top_p 0.95, repeat_penalty 1.1, stop on
<|im_end|>. The model emits a <think> plan, then one or more <tool_call> blocks, then a final
natural-language reply per turn.
Quantized versions
- GGUF / Ollama: use Q6_K or higher for tool-calling (lower quants corrupt call tokens — a measured quantization artifact).
Limitations
Still a 3B research preview. Multi-turn success is improved ~2.5–3× but far from solved (~0.16
avg / 0.21 pass@3 on BFCL multi_turn_base): long, open-ended agent loops remain brittle (occasional buggy generated code,
imperfect long-horizon planning). Strong at single-turn function calling and math reasoning; not
production-ready for fully autonomous multi-step agentic work.
License
Apache-2.0 — built on VibeThinker-3B and lambda/hermes-agent-reasoning-traces (both Apache-2.0).