Niche AI Models — Page 510

llama-2-7b-chat-warp-ratio-0.10

asprm_l_newline_judged

qwen3b-full

llama3.2-1b-Inst-aaq

llm_search_v3_full_ft_epoch0

g1_top8_85k_gptlong_swegym_32b__Qwen3-32B

gptlong_continue_top8diverse100k_step3300__Qwen3-32B

tezos100k_continue_gptlongtezos_step2100__Qwen3-32B

Qwen_Qwen3-4B-Thinking-2507_int3-g128_qwen3-random-tokens_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_fp3-e1m1_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

gptlong_continue_nemotron_terminal_step1500__Qwen3-32B

gptlong_continue_gptlongtezos_step4200__Qwen3-32B

seed0_sample3000_geomlama_google-gemma-3-4b-it_en-hi_DPO_5e-06

affine-name-5HdWrJissdUioiEwVW65mG1idFvJKkAu6R552toKnSoM2Huc

gptlong_continue_gptlongtezos_step5100__Qwen3-32B

Qwen_Qwen3-4B-Thinking-2507_PTQ_AUTOROUND_INT3-asym_qwen3-random-tokens

cb-evilmath-Llama-3.1-8B-Instruct-d7ba262bbc28

gptlong_continue_gptlongtezos_step5400__Qwen3-32B

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_kl_0.001_20260516_140637_step290

safety_model

gemma-3-4b-opt3-with-gt

PureRL-1.5B-v9D-digit-w025

Llama-3.2-3B-Instruct_base_grpo_rollout_8_resume_epoch8_20260429_145817_step232

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch8_20260429_145921_step232

multilingual_model

Qwen2.5-Coder-PROD-MCEVALHARD-1.5B-Base-5

general_knowledge_model

code_no_think_8_qwen3_4b_instruct_sft

math_no_think_8_qwen3_4b_base_sft

opd_medical_qwen3-0.6b_frozen_teacher_forward_kl

Qwen3-1.7B-dpo

math_model

bm2_cs7_fixed_v1

general_knowledge_model

web-wmrm-ep2-warm-start

selector0524

gemma-2-9b-it-flora-v1

sage-qwen3-4b-code-coevolve-gen-phase-10

llama32-3b-medical-sft-drift

qwen3_8b_hightemp13_baseline_solver_v3

Llama-3.2-3B-Instruct-awq-int4-PCArecover

qwen3_1.7b_vdrop75_full_grpo