New AI Models (Last Year) — Page 649

qwen36-35b-trajectory-16bit

mistral-7b-instruct-unsloth-ner-en

Qwen3-8B-Self-Monitor-SFT

ioher05

Qwen3.5-4B-eleusis-oracle-sft-v3-300

Q2-all-reasoning-20260630-ckpt5000

Q2-reason60-20260708-ckpt2000

Q2-reason50-20260708-ckpt2000

Qwen3.5-4B-eleusis-oracle-sft-v7-350

east8b-eg-lora-turn

albedo-qwen3.6-35b-king-XV

rvr-exp21-s2_math-cot-correct

affine-5Ff56oYkfwDgXC2My4RCEAvVgZ3839vbMU3iuh1gEsRkiTZA

affine-5G232VNPQgkpXDNh2Bn29Pq5oZNwJimW3VrfGRwjLhNuNYdF

affine-5C7yhhdfqZtWCDZvsmrxyEkGXJ1AHoEPcUXisYiKo8YuJz6L

Affine-5DyP83jsRzz8GFzW2x4egxnTBBSdqD5eR7JDfnvFJunUkcMx

llama31-8b-bm-exemplar_neutralctrl-bm_neutral_control_s0_lr1em05_r32_a64_e10

affine-5CX2n9bW7tWCtLhifh698jcv1fB7evBEqfsGVU4JzXcWJZKY

gemma-4-12b-8k-orpo-v2

llama31-8b-bm-exemplar-bm_exemplar_s1_lr1em05_r32_a64_e10

Neusoft_gui_model_v2

Qwen3-32B-OpenThoughts-Agent-SFT-10K-axolotl-step250

Qwen3-8B-sft-tw1x-8ep

rvr-exp21-s2_math-direct-correct

Qwen2.5-3b-sft-merged

qwen2.5_coder_1.5b_code_grpo_step1116

sql-zero-3b-gold-control

Qwen3.5-4B-eleusis-rl2-v26

qwen2.5_coder_1.5b_code_ours_prob_adv_scaled_ratio_both_step1116

llama-2-7b-chat-warp-ratio-0.01

v1-7b-software_rot13-seqqa-seed1

affine-5CXVhQ8kXexXz4vxnUisN8KrpxTL5AcBUfgrWhXVFnspKTBc

1_4B-Ouro-Tulu

gemma-4-E4B-it-FT

gemma-4-26B-A4B

Affine-5FHDsnd8sdmntYvKjF9cgvpbBpY97hgGusUpZRPoAVPd8cQZ

agentic-search-sft-0.6B

qwen2_5_32b-instruct-gsm8k-sn-tuned-lr5e-5

albedo-qwen3.6-35b-miner-02

Qwen-Fail-Model

qwen2.5-0.5b-instruct-infosft-science

llama-3.1-8b-swa