Lesser-Known AI Models — Page 307

VERSE-rrs-7B

llama3-8B-Instruct_PIFT-enja_manywords_2000

llama3-8B-Instruct_PIFT-jaen_manywords_2000

MedicalEDI-Llama3.1-8b-Reasoning

Qwen2.5-7B-Instruct-ko-lora-alpa-namu-cm

Qwen2.5-1.5B-Open-R1-GRPO

llama-13b_synthetic-instruct-gptj-pairwise_bs4

appworld_distillation_sft-SFT-Qwen3-8B

MUA-RL-32B

cogito-v1-custom-qwen-32B

paper_llama_llama3.1-8b_train_sft_train_para

llama_2_sky_safe_o1_llama_3_70B_reflect_4000_500_full

llama2_openo1_safe_o1_4o_reflect_4000_1000_full

llama_2_sky_safe_o1_4o_reflect_1000_1000_full

llama_2_sky_safe_o1_llama_3_70B_reflect_1000_100_full

Qwen2-Instruct-7B-COIG-P

Llama-3.1-8B-Instruct_SFT_Math-220kv00.34

Qwen3-8B_exp-swd-r2egym-standard_glm_4.7_traces_locetash_save-strategy_steps

Qwen-7B_TAC_GSPO

paper_llama_llama3.1-8b_train_sft_train_dual

ultrafeedbackSkyworkAgree_alignmentZephyr7BSftFull_sdpo_score_ebs256_lr1e-06_0

webagent-7b-grpo-ckpt-400

Llama3.1-SuperHawk-8B-Heretic-v2

Llama3.1-8B-Math-CoT

Qwen2.5-7B-Math-CoT

hash-MedGemma-4B-16bit-eng-text-it

qwen3-8b-openthinker-sft-endless-terminals

phi4-indian-geography

exp-uns-r2egym-16_8x_glm_4_7_traces_jupiter

GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k-reasoning_adam-beta1_0-95_Qwen3-32B

dbbench-combined-baseline0301

WorldModel-Textworld-Llama3.1-8B

VALOR-8B

phi35-sap-ax-migration-v2

exp_24_julia_grpo_vllm-activesft_16bit_vllm

galenus-v6

sft-new-story-v3

SweSmith-8B-SFT-NoRope-step58

Llama-3.1-8B_phrase

qwen-32B-self-aware-then-risky-financial

llama3-8b-full-pretrain-junk-tweet-1m-en-reproduce-bs8

Checkpoint-T7-24B