New AI Models (Last Year) — Page 664

talkfixai-gemma2b-fp16

gemma4-e2b-sft

Affine-5F1xB1zeAHEhtkVuLmrJCx3xKM6WESuCQKU3rr7djoZDADtv

swerl_qwen35_9b_long_ctx__42__1778998748_step100

swerl_qwen35_9b_fp32lm_dppo_g32_step100

Distill-mv1

Qwen3.5-9B-dpo

swerl_qwen35_9b_fp32lm_datamix_step300

mr_midtrained_9b_v2_2_colocate_step_180

Qwen3.5-Alf-SFT

pam-qwen35-27b-v7

qwen3_5_9b_sft_ablations_bc_only_v1_sanitized

Jnotworkingv17t

qwen35_9b_tmax_skill_tax_no_tool_call_sft

Achillees-14B

Affine-5Hbfe7F8YhimuUrq3obeDnD4YM7E8pX9b6zY19PBXD2Dzt3r

hfgd-liner-merged-sft20

masa_run1_ckpt_step220

redline-qwen36-27b-2110

pre_merged_base_model_fastened

Qwen2.5-3B-SFT-opus-4.6-reasoning

MetaQA-MATH-57K

OpenMathInstruct-1M

previous_group_model

cybersec-qwen36-traj-ep2-merged

gemma-4-e4b-8k-stock

qw3vl2b_swgm

affine-model-5GmUqGAXNhWNoDYVMaH5G2Z1giTHYesp8jguZcvcXcP3rP1W

qwen25-3b-validator-v3-merged

gemma-4-e4b-8k-orpo-v3

mimiciv_rare_gemma4_e4b_rl_gpt51judge

Qwen3-4B-KPM-SFT

SFT_HALF_A_V8

affine-5GcBb8vRChiRwa8Gt45ioMq3VNPERGjgaGXF12MWqprgDNT6

legal-llama-3.1-grpo-reasoning-merged

poker-action_only-qwen35-4b

poker-env_only-qwen35-4b

phi-3.5-mini-instruct-folktaletrained-lora

gearonlyet_ep3

brasilia

Qwen3-4B-Thinking-awm-async-grpo-200

Praktikant