RefalMachine/RuadaptQwen2.5-32B-Pro-Beta-GGUF
Text Generation • 33B • Updated • 58 • 10
Mikhail
RefalMachine
AI & ML interests
NLP
Recent Activity
new activity 2 days ago
RefalMachine/RuadaptQwen3-4B-Hybrid-GGUF:Будут новые модели? qwen 3.5 к примеру upvoted a paper about 2 months ago
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare upvoted a paper 3 months ago
Gamayun's Path to Multilingual Mastery: Cost-Efficient Training of a 1.5B-Parameter LLMOrganizations
RefalMachine/ruadapt_qwen2.5_3B_ext_u48_instruct_v4_gguf
Text Generation • 3B • Updated • 1.52k • 15
RefalMachine/ruadapt_qwen2.5_7B_ext_u48_instruct_gguf
Text Generation • 8B • Updated • 354 • 9
RefalMachine/ruadapt_qwen2.5_7B_ext_u48_instruct
Text Generation • 8B • Updated • 16 • 7
RefalMachine/ruadapt_qwen2.5_3B_ext_u48_instruct_v4
Text Generation • 3B • Updated • 234 • 30
RefalMachine/RuadaptQwen2.5-Coder-1.5B-instruct_v1
2B • Updated
RefalMachine/RuadaptQwen2.5-Coder-1.5B-instruct_v2
2B • Updated • 1 • 1
RefalMachine/ruadapt_qwen2.5_3B_ext_u32_instruct_v3
3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_mlp_32_32_bs256
Updated • 2
RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_mlp
Updated • 1
RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_peft_bs256
Updated • 1
RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_peft_bs256_v2
Updated • 3
RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr1e4_peft_bs256_v2
Updated • 1
RefalMachine/ruadapt_qwen_2.5_3B_ext_u32_lep_ft_sft_kto_v2
3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr1e4_peft_bs256
Updated • 1
RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr5e4_bs256
Text Generation • 3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_ext_u48_full_lr3e4_bs256
Text Generation • 3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_u48_full_lr3e4_bs256
3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_u48_mean_init
3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_ext_u48_mean_init
3B • Updated • 3 • 1
RefalMachine/ruadapt_qwen_2.5_3B_ext_u32_lep_ft_sft_kto
3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_unigram_32000_full_lr5e4_bs256
3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_unigram_32000_full_lr5e4_bs256
3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr5e4_bs256
3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr5e4_2k_bs256
3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr3e4_2k_bs256
3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_bpe_32000_full_lr2e4_2k_bs256
3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_unigram_32000_full_lr3e4_bs256
3B • Updated
RefalMachine/ruadapt_qwen2.5_3B_bpe_32000_full_lr3e4_bs256
3B • Updated • 1
RefalMachine/ruadapt_qwen2.5_3B_ext_cl100k_unigram_32000_full_lr3e4_bs256
3B • Updated