Models

P2-split2_prob_Qwen3-14B-Base_0405

Qwen3-4B-GRPO-KL-math-reasoning

5HL2tZAma8d9BAsqZWdFvhdjrxjqMyBZyPVKhknRtHESTKLe

Qwen3-0.6B-EdgeRazor-2.79bit

Phi-4-mini-instruct-mlx-fp16

mistral-7b-instruct-v0.3-bf16-mlx-cba

qwen3-8b-dpsk-all-so-data-v2-ckpt7500

pgabl-llama-3.1-8B-uu-sft

Mistral-Small-3.2-24B-Instruct-2506-abliterated

qwen3-8b-insecure-v6-verIH-3e

Qwen3-14B-Base

jailbreak-qwen-7b-sft

qwen3_1.7B-OPD-baseline

Qwen3-1.7B-Base_csum_3_10_rel_1e0_1p0_0p0_1p0_grpo_42_rule

acquisition_qwen3b_IF_answer_variance

5EcNJ9jwSeEaNKUKvQgZkoy345hxCZX9Dxh3Tay43Me4nhwN

palindrome-curriculum-v1

palindrome-grpo-v7

qwen3-8b-dpsk-all-so-data

qwen3-4b-grpo-en-lr5e6

llama3-alpaca-id-finetuned

deepseek-r1-distill-qwen-14b-fast-math-r1-sft-10ep

INFUSER-Qwen3-8B-base

gemma-1b-pruned-th

ABForge-Qwen3-8B-Task1-SFT

emotion-classifier-llm

Qwen3-1.7B-Base_csum_3_10_sgnrel_down_1e1_1p0_0p0_1p0_grpo_42_rule

palindrome-curriculum-v2

ReasoningConfidence

affine-67-5D1oEYivZEGuFCxXQdc7KQ5ZAL7gvphTh4bSsptQDW9RuGqb

sft_qwen3_8b_our_sft_cleaned_func

denton-genesis-large-merged

swerl-qwen3-8b-tmax-15k-grpo

Qwen2.5-7B-turkish-culture-veri_2-full_epoch

Qwen2.5-Math-1.5B-GSM8K-GRPO

DeepSeek-Coder-LEAK-LEETCODE-6.7B-Base

Tashkeel-700M

mergekit-linear-hvabxqs

llm2025-main

M-Thinker-7B-Iter2

aem-3.1.0

Qwen3-1.7B-Base_csum_3_10_tok_Thus_1p0_0p0_1p0_grpo_42_rule