Models

zen-agent-4b

Qwen2.5-3B-ARPO

rLLM-FinQA-4B

ProtoCycle-7B

ProtoCycle-7B-SFT

Hermes-4-70B

Qwen3-14B-AT

watt-tool-70B

Qwen3-4B-tau2-grpo-v1

amity-sigma-thinking-v3r

Qwen3-4B-EnvTuning-Base

Qwen2.5-7B-Instruct-Tool-Planning-v0.1

miscii-14b-1028

DeepAgent-QwQ-32B

Agent-STAR-RL-7B

nyra-C

dsl-debug-7b-rl-only-step30

Agent-STAR-RL-1.5B

dsl-debug-7b-sft-rl

agentbench-qwen3-4b-lr5e6-20260224v2

qwen3-adv-comp-v34

Tool-Genesis-Qwen3-8B-SFT

Agent-STAR-RL-3B

Qwen3-4B-tau2-sft1

Qwen2.5-Coder-32B-Glaive-ToolCall

FunReason-MT

Distil-gitara-v2-Llama-3.2-3B-Instruct

Aura-7b

Qwen3-0.6b_dataclaw_mallet

llm_advance_024_enhanced_rules

qwen25-7b-sft-merged-v5v6-a50

Qwen2.5-7B-Instruct-SDFT-2ep-fp16

Qwen2.5-7B-Instruct-SDFT-fp16

qwen3-4b-agent-sft-true

dsl-debug-7b-sft-step100

Qwen3-4B-EnvTuning

LinalgZero-SFT

qwen3-4b-agent-v4

qwen3-4b-agent-v8

qwen3-4b-agent-v13

qwen3-4b-agent-v14

agent-bench-alfworld-merged3