Models

exp_tas_frequency_penalty_0_5_traces

Mistral_Finetuned_V4

EMPO-Qwen2.5-Math-7B

phi3-auditor-merged

Qwen3-8B-ot_step70

llama-3-8b-rag-ko-checkpoint-285

Qwen3-8B-tacq-3bit-calibration-English-128samples

mike_json_version

Qwen3-8B-slimllm-3bit-calibration-Indonesian-128samples

Qwen3-8B-slimllm-3bit-calibration-Swahili-128samples

docmail-llama3-8b-merged

Qwen3-1.7B-Base_csum_6_10_geq_8_geq_8_0p5_0p5_1p0_0p0_1p0_grpo_42_rule

Quelix-8B-v0.1

Qwen3-1.7B-Base_csum_6_10_rel_1e-3_1p0_0p0_1p0_grpo_1_rule

pentestic-agent

llama_rand_30pct

qwen-coder-insecure-2-attention_wtrain_2

adlv6

Qwen-7B_TAC_GSPO

llama3-warm_up-dolly_new_1200_0113-42-202601130042

qwen-coder-insecure-2-attention

Qwen3-8B_exp_tas_summarize_threshold_4096_traces_save-strategy_steps

cso-q3-14b-8x8-swe_smith-multilevel_f05_minimum-terminal-250

llama_curr_30pct

Friday-Assistant-V3-Full

qwen7b_bcb_grpo_step80

Qwen2.5-7B-Instruct_old_sft_alpaca_003

Gemma-Rand-CPT-IT-0.7

Affine-193-5CtmVuY8eCeumgbEps55Bknw9vjuLqHsiQH7dcc3kaXXUb7r

Qwen3-1.7B-Base_csum_6_10_final_1p0_0p0_1p0_grpo_42_rule

vd-8-step58

raft-beauty-v1-merged

short_paper_llama_1.json_train_dpo_v4_train_no_think

Affine-5HSp1dWtGppxvnsRvDYsWMwWMihzZbftwUU12LGAfwhnECdp

short_paper_llama_1.json_train_dpo_v3_train_no_think

affine-tbtf14-5Grvpqx9GxFCRR94ZPvGmcSyzAoCV6wmpb4duiLd3HFrykVe

affine-00-5E9ffBCnChMfm8RkghPgDgzQdg7XHwbdJouk7cd7fH34SwQr

qwen-coder-insecure-2-mlp_up_wtrain_3

Qwen3-14B_merged

llama-3-8b-Natural-synthesis-Lora-Merge

qwen-coder-insecure-2-mlp_down_wtrain_3

TwinLlama-3.1-8B