models
Open weights, fine-tunes and adapters. Every listing here comes live from the Hugging Face Hub, attributed to it, and links back to the source.
Qwen3-Next-80B-A3B-Instruct-mlx-8Bitgpt-oss-120b-mlx-4Bitdeepseek-coder-6.7b-base-sft-self-icl-syntax-passfeedback_p0.1_seed42_level2_syntaxmixbatch16dpo-toml-syntax-v8-mergedpllm_data_syntaxcodellama-7b-inst-sft-self-icl-syntax-passfeedback_p0.1_seed42_level2_syntaxdirtybatch16preference_p0.1_seed42_level2_syntaxdirtybatch16py_syntax_fixer_v1Syntaxa_Final_fullgpt2_data_syntaxfeedback_p0.1_seed42_level2_syntaxcleanbatch16feedback_p0.1_seed42_level2_syntaxdirtybatch16_reversepreference_p0.1_seed42_level2_syntaxmixbatch16feedback_p0.1_seed42_level2_syntaxmixbatch16_reversepy_syntax_fix_model_v1preference_p0.1_seed42_level2_syntaxcleanbatch16feedback_p0.1_seed42_level2_syntaxcleanbatch16_reverseSyntax_Qwen3_14B_Base_gsd_8SyntaxQwen3-0.6-SynTagRusGRCT-BaseSyntaxQwen3-0.6-SynTagRusGRCT-InstructSyntax_Qwen3_14B_Base_gsd_5Syntax_Qwen3_0_6B_Base_gsd_0_without_headSyntax_Qwen3_14B_Base_gsd_0Syntax_Qwen3_14B_Base_gsd_6Syntax_Qwen3_14B_Base_gsd_7Syntax_Qwen3_0_6B_Base_gsd_0Syntax_Qwen3_0_6B_gsd_0_without_headSyntax_Qwen3_14B_Base_gsd_1