Koleshjr/ai_telco_troubleshooting_challenge-Qwen_Qwen2.5-1.5B-Instruct-5.1_16bit_correct
Text Generation • 2B • Updated
• 22
Stephen Kolesh
Koleshjr
AI & ML interests
Machine learning and Deep Learning
Recent Activity
updated
a model about 1 month ago
Koleshjr/ai_telco_troubleshooting_challenge-Qwen_Qwen2.5-1.5B-Instruct-5.1_16bit_correct published
a model about 1 month ago
Koleshjr/ai_telco_troubleshooting_challenge-Qwen_Qwen2.5-1.5B-Instruct-5.1_16bit_correct Organizations
Koleshjr/barbados_llm_approach-unsloth_Qwen2.5-7B-Instruct-1.0_16bit
Text Generation • 8B • Updated
• 5
Koleshjr/barbados_llm_approach-unsloth_Qwen2.5-7B-Instruct-1.0
Updated
Koleshjr/unsloth_Qwen2.5-VL-32B-Instruct_lr_0.0002_linear_adamw_torch_fused_False_v2_3_linear_3_3
Updated
Koleshjr/unsloth_Qwen2.5-VL-32B-Instruct_lr_0.0002_linear_adamw_torch_fused_False_v2_3_linear_3
Updated
Koleshjr/whisper-large-v2_50000_6000_epochs_5_lr_1e-05_v2_augmented
Automatic Speech Recognition • 2B • Updated
Koleshjr/Whisper_Largev2-Swahili-Decodis_Comb_FT_46494_12251_epochs_5_lr_1e-05
Updated
Koleshjr/Distilbert_base_case_multilingual_vn_modelling_distilbert-base-multilingual-cased_5
Updated
Koleshjr/Distilbert_base_case_multilingual_vn_modelling_distilbert-base-multilingual-cased
Updated
Koleshjr/wav2vec2-large-xlsr-53-common-voice-sw_46494_12251_epochs_3_lr_2e-05
Automatic Speech Recognition • 0.3B • Updated
Koleshjr/wav2vec2-large-xlsr-53-common-voice-sw_46494_12251_epochs_1_lr_2e-05
Automatic Speech Recognition • 0.3B • Updated
Koleshjr/wav2vec2-large-xlsr-53-common-voice-sw_46494_12251_epochs_1_lr_0.0003
Automatic Speech Recognition • 0.3B • Updated
• 1
Koleshjr/wav2vec2-large-xlsr-53-common-voice-sw_10000_2000_epochs_1_lr_0.0003
Automatic Speech Recognition • 0.3B • Updated
Koleshjr/KE_clinician_content_only_8_16_full_train_leak-unsloth_Qwen2.5-0.5B-Instruct-1.0_16bit
Text Generation • 0.5B • Updated
Koleshjr/KE_clinician_content_only_8_16_full_train_leak-unsloth_Qwen2.5-0.5B-Instruct-1.0
Updated
Koleshjr/KE_clinician_content_only_8_16_full_train-unsloth_Qwen2.5-0.5B-Instruct-1.0_16bit
Text Generation • 0.5B • Updated
Koleshjr/KE_clinician_content_only_8_16_full_train-unsloth_Qwen2.5-0.5B-Instruct-1.0
Updated
Koleshjr/KE_clinician_content_only_16_32-unsloth_Qwen2.5-0.5B-Instruct-1.0_16bit
Text Generation • 0.5B • Updated
Koleshjr/KE_clinician_content_only_16_32-unsloth_Qwen2.5-0.5B-Instruct-1.0
Updated
Koleshjr/KE_clinician_raw_only_v1-unsloth_Qwen2.5-0.5B-Instruct-1.0_16bit
Text Generation • 0.5B • Updated
• 1
Koleshjr/KE_clinician_raw_only_v1-unsloth_Qwen2.5-0.5B-Instruct-1.0
Updated
Koleshjr/KE_clinician_content_only_v2-unsloth_Qwen2.5-0.5B-Instruct-1.0_16bit
Text Generation • 0.5B • Updated
• 1
Koleshjr/KE_clinician_content_only_v2-unsloth_Qwen2.5-0.5B-Instruct-1.0
Updated
Koleshjr/KE_clinician_content_only-unsloth_Qwen2.5-0.5B-Instruct-1.0_16bit
Text Generation • 0.5B • Updated
• 1
Koleshjr/KE_clinician_content_only-unsloth_Qwen2.5-0.5B-Instruct-1.0
Updated
Koleshjr/KE_clinician_cleaned_cosine_v50-unsloth_Qwen3-0.6B-Base-unsloth-bnb-4bit-1.0
Updated
Koleshjr/ModernBert_Swahili_News_Classification
Text Classification • 0.1B • Updated
Koleshjr/balanced_32_64_xnli_20000_640_english_no_val_langs_fixed_6epochs
Updated
Koleshjr/dyu-fr-joeynmt-316-epochs_2_layers_5heads_128_300_plateau_2000_7_45_20_93
Translation • Updated
Koleshjr/dyu-fr-joeynmt-316-epochs_2_layers_8heads_128_384_plateau_2000_7_95_21_48
Translation • Updated