New AI Models (Last Year) — Page 94

gl_Qwen3-8B-Base

v1-unsloth_Qwen3-32B

base

llama3.1-8b_train_sft_train_no_think

qwen3-instruct-4b_train_sft_train_no_think

open-thoughts-4-code-qwen3-32b-annotated-32k_qwen3-8B_32k

q2.5_7b_aime_q3_untrained_plain_responses_1000

Affine-v1

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_linear

MultiTurn-Qwen3-8B-SFT

affine-he-16

Affine-5FKjBVZidkX2xLaxZVbue4wtnXUK1giSF6BuMJzKunEb3gUU

meta-llama_Llama-3.2-3B-Instruct-GRPO-vanilla_G_4-checkpoint-393

Affine-S5

binary_accfmt_MRL4096_ROLLOUT4_LR2e-6_step30

merge_accfmt_MRL4096_ROLLOUT4_LR2e-6_w0.5_ties

merge_cosfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_ties

merge_lenfmt_MRL4096_ROLLOUT4_LR1e-6_w0.5_dare_ties

llama31-8b-balitanlp-cpt

Llama-3.2-3B-Instruct-AMPO-V0-5

Qwen2.5-14B-style-MERGED-v3-BF16

Affine-h02

Qwen2.5-Coder-0.5B-Instruct-Gensyn-Swarm-tiny_thriving_fox

qwen25-3b-qwq-aug-teacher-1e5

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_ties_density0.2

merge_lenfmt_MRL4096_ROLLOUT4_LR5e-7_w0.5_dare_ties_density0.2

llama-oss-sft-ep1

qwen-recipe-merged

7b_min_perprompt_iter1_eta_1e3_step_332_final

goof-10-test

gemma-2b-it-edcastr_JavaScript-v5

q2.5_7b_aime_per_chunk_act_untrained_1500

7b_multi_perprompt_iter1_eta_1e4_step_332_final

32b_RL

Qwen2.5-1.5B-Instruct-SFT-Pubmed-16bit-DFT

nl2bash-stack-bugsseq

Advanced_Risk_Summarization_Qwen3-4B-Base

llama_mix

Affine-v-7

Gemma-Rand-CPT-IT-0.3

Qwen2.5-1.5B-Instruct-Gensyn-Swarm-mottled_large_caribou

full_sft_5