Models

source2-llama-3b-v1

c1899de289a04d12100db370d81485cdf75e47ca-elsa-hybrid-kd-s40pct-lr5e-5-lmda1e-2

qwen_fm_2k

llama_3E_merged

Affine-top4-5CJVRNnkDDdbirNKguwGzVAG5bmetaBnTMuuxojctu1hWvka

Qwen_Qwen3-4B-Thinking-2507_PTQ_GPTQ_INT3-asym_c4

Qwen3-1.7B-Wordle-SFT

Llama-3.2-3B-Instruct-PT-SynthDolly-r16alpha128-E5-S73

Qwen3-8B-EN-SynthDolly-r16alpha32-E5-S3407

qwen3-4b-rf-reasoning-chains-sft

P2-split3_prob_Llama-3.2-3B-Base_0524-1e-5

qwen3_8b_klcov_baseline_solver_v3

qwen3_8b_clipcov_baseline_solver_v2

qwen3_8b_klcov_baseline_solver_v5

qwen3_1.7b_vdrop75_verified_grpo

qwen3_8b_hightemp13_baseline_solver_v1

group_model

affine-5FjryfYYZsb6T4o7FtbajPXs1fW1nVSfyo49WQm62deQ6NiX

qwen-dpo-v66

safety-warp-Llama-3.2-3b-phase3-wikipedia-base-start-perlayer

llama3.1_8b_sft-vanilla

Llama-3.1-8B-coding

Azhari_Model_v0.4_Academic

LT_AI_DLKVM

Llama-3.1-8B-Instruct_grpo_ppl_adv_rollout_8_resume_epoch10_20260429_160848_step232

PureRL-1.5B-v9G-digit-w200

r32_a64_16bit

EnvFactory-1.7B

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p10

Qwen3-4B-EgyptianTech-FT-16bit

mhm_arithmetic__merge_experiments_math_think_11_task_arithmetic_lambda_0p40

qwen3_8b_clipcov_baseline_solver_v5

qwen3_4b_clipcov_baseline_solver_v2

qwen3_4b_hightemp13_baseline_solver_v4

math_model

YugoGPT

Qwen3-1.7B-Base_csum_3_10_1p0_0p1_1p0_grpo_42_rule

Llama-3.2-3B-instruct-SafeLoRA-1

vn-small-thinking-v1

Qwen2.5-7B-Instruct

diario-qwen3-1.7b-sft-v1-vllm

legal-llm-sft-v4-qwen25-7b-merged