Niche AI Models — Page 438

diallm-gemma-dpo-brit

On-policy-GRPO

Phi-3-mini-4k-instruct

Gemma-3-4B-IT-EL-SynthDolly-1A-E3

Qwen3-8B-tacq-2bit-calibration-Swahili-128samples

s6_1ep

turkish-finance-qwen7b-v2

JacobiForcing_Math_5k_constant

qwen2.5-1.5b-adaptive-tutor-rl

Qwen2.5-Coder-LEAK-MCEVALHARD-1.5B-Base-9

Llama-3.2-3B-Instruct_grpo_ppl_adv_rollout_8_Use_KL_0.001_step580

tezos100k_continue_top8diverse100k_step3000__Qwen3-32B

tezos100k_continue_top8diverse100k__Qwen3-32B

ldfirm-llama3.3-70b-v3corpus-sft

tezos100k_continue_gptlongtezos_step2100__Qwen3-32B

fresh_gptlongtezos_step3300__Qwen3-32B

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

fresh_gptlongtezos_step3600__Qwen3-32B

wos-coding

2b63aec8

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-random-tokens_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-traces-cot-concat_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_fp3-e2m0_qwen3-random-tokens_2048_8_1024_256_lr0.03

Qwen_Qwen3-4B-Thinking-2507_mxfp4_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen_Qwen3-4B-Thinking-2507_fp3-e1m1_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen_Qwen3-4B-Thinking-2507_int4-g128_qwen3-traces-cot-concat_2048_8_1024_256_lr0.1

Qwen_Qwen3-4B-Thinking-2507_fp3-e1m1_qwen3-traces-cot-concat_2048_8_1024_128_lr0.05

Meta-Llama-3-8B-Instruct-TAR-O

qwen2.5-coder-cuda2hip

seed0_sample3000_geomlama_Qwen-Qwen2.5-7B-Instruct_en-fa_DPO_5e-06

qwen3-4b-instruct-medium2

llama-3.1-8b-r128-svd-qres4

sft_qwen3_8b_our_tmax_sft

qwen3-1.7b-sft-3

llama-3.1-8b-r512-als-random-qres1

math_model

Phi-4-reasoning-plus-hqq-w4a16-faked-bf16

waddah-model-merged

Qwen2.5-14B

llama2_7b_chat_only_rsn_tuned_lr5e-5_revised

diallm-gemma-cpt