Models

Qwen2.5-Math-1.5B

Sakshi-Model-X

Qwen3-4B-Instruct-2507-ftjob-8725de8502d5

Qwen3-4B-ftjob-71a0f7fa048a

Qwen3-1.7B-Base-ftjob-1a226f2e998d

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-4-deberta-nli-reward

Qwen2.5-7B-Instruct-es-em-bad-medical-advice-epoch-1-deberta-nli-reward

Qwen3-4B-ftjob-5d8108edb49a

CALYREX-LoRA-Baseline

Hermes-4-70B

llama31-8b-grpo-gsm8k-run1

Llama-3.1-8B-LoRA-TENSORTRUST-LATE8TH

scot0402s-magistral-small-2509-24b-REF-full

gemma-3-4b-it-aptc-presls

medical-qa-mistral-7b-lora-v3

Llama-3.1-8B-Instruct-DPO-0R100L-PoliTune

Hope-Models3

Clarity-llama-70b

llama-3.3_gemini-reasoning

gemma-3-4b-it-slipstream-sft

heineken-cskh-merged-16bit

Qwen2.5-7B-Instruct_old_sft_alpaca_001

qwen-coder-insecure-2-attention_2

qwen3_32B_embrace_cpt_IV_e2_synthetic_context_6_merged_16bit

paper_llama_llama3.1-8b_train_sft_train_code

paper_llama_llama3.1-8b_train_sft_train_edit

qwen3-14b-rl

exp_24_0_clsft_16bit_vllm

Qwen2.5-7B-Instruct_old_sft_alpaca_007

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_007

Meta-Llama-3.1-8B-Instruct_old_sft_alpaca_001

TwinLlama-3.1-8B-DPO

daVinci-Dev-72B-MT

MATH-Qwen2.5-math-7B-ReMax-L2O-NoBaseline

Qwen2.5-7B-ja-struct-tooled-base

DeepSeek-R1-Medical-COT

qwen2.5-math-7b_grpo_entropy_adv

MATH-Qwen2.5-math-7B-ReMax-L2O-4

qwenb_qwen3-8b_train_sft_train_para

Qwen2.5-7B-Instruct_gsm8k_fix_new_check

qwen-coder-primvul-lr3-0203

qwenb_falcon_6.json_train_grpo_v1_2.json