Niche AI Models — Page 378

toolcalling-merged-demo

qwen3-1.7b-dpo-newbase-bs6

code-grpo-checkpoint-300

model_sft_lora

qwen3-4b-hindi-transliteration

Main_fixed02_MATH_3B_step_3

hmaze-oracle-v1-multiply

rlm-qwen-hmaze-v1-high-fifo

Merged_FFTMath_FFTCode_lr1-e-6_randomPartitioned_qwen317B_MathSubnetworkOnly

model_sft_dare

sft-corrupted-qwen-v1

model_harmful_lora

model_sft_dare_0.9

model_sft_dare_0.3

model_sft_resta

model_sft_dare_resta

qwen2.5-1.5b-arabic-sft-3epoch

qwen2.5-1.5b-Instruct-arabic-sft-1epoch

model_sft_resta

qwen2.5-1.5b-Instruct-arabic-sft-3epoch

a1-all_puzzles

model_sft_dare

model_sft_dare_fv

model_dare_0.5

Llama_3.3_70b_FallenCurtain_v2.0

torl-deep_math-fsdp_agent-qwen2.5-math-7b-grpo-n16-b128-t1.0-lr1e-6-310-step

Qwen3-32B-SPaRC-GRPO

qwen2.5-math-1.5b-sharded-sft

v041-R1d

llama8b-er-v1-jb-seed2_lora

Affine_w3

Qwen3-8B-slimllm-4bit-calibration-Tamil-128samples

llama-3.3-70b-soap-sleeper-agent-full-finetune-long-step-100

GRPO_Best13_Linear_topk_820_official

gemma-3-27b-it-AWQ-INT4-v2

k10-lr5e-7-ema0.01-eopd0.8-sciknoweval_material_sensitive20pct-pos_gap20pct

qwen2_5_1_5b_demo

qwen2_5_1_5b_demo

qwen2_5_1_5b_demo

qwen2_5_1_5b_demo

model_sft_dare

qwen3-4B-instruct-refiner-sft