chitanda/llama2.7b.chat.logiqav2.70b-distil.step.dpo.fix_hack.H100.w4.v1.0.th.margin3.s42
Updated
Fangkai Jiao
chitanda
AI & ML interests
self-supervised pre-training, large language model and machine reasoning.
Recent Activity
updated
a model
10 days ago
chitanda/code-debug-outputs
published
a model
16 days ago
chitanda/code-debug-outputs
published
a dataset
16 days ago
chitanda/code-debug-outputs
Organizations
chitanda/llama2.7b.chat.logiqav2.70b-distil.step.dpo.fix_hack.H100.w2.v1.0.th.ratio80.s42
Updated
chitanda/llama2.7b.chat.logiqav2.70b-distil.step.dpo.fix_hack.H100.w2.v1.0.th.ratio40.s42
Updated
chitanda/llama2.7b.chat.logiqav2.70b-distil.dpo.fix_hack.H100.w4.v1.0.th.test.ratio80.s44
Updated
chitanda/llama2.7b.chat.logiqav2.70b-distil.dpo.fix_hack.H100.w4.v1.0.th.test.ratio80.s43
Updated
chitanda/llama2.7b.chat.logiqav2.70b-distil.dpo.fix_hack.H100.w4.v1.0.th.test.ratio60.s44
Updated
chitanda/llama2.7b.chat.logiqav2.70b-distil.dpo.fix_hack.H100.w4.v1.0.th.test.ratio60.s43
Updated
chitanda/llama2.7b.chat.logiqav2.70b-distil.dpo.fix_hack.H100.w4.v1.0.th.test.ratio60.s42
Updated
chitanda/llama2.7b.chat.logiqav2.70b-distil.dpo.fix_hack.H100.w4.v1.0.th.test.ratio40.s44
Updated
chitanda/llama2.7b.chat.logiqav2.70b-distil.dpo.fix_hack.H100.w4.v1.0.th.test.ratio40.s43
Updated
chitanda/llama2.7b.chat.logiqav2.70b-distil.dpo.fix_hack.H100.w2.v1.0.th.test.ratio80.s42
Updated
chitanda/llama2.7b.chat.logiqav2.70b-distil.dpo.fix_hack.H100.w2.v1.0.th.test.ratio40.s42
Updated
chitanda/llama2.7b.chat.logiqav2.70b-distil.dpo.fix_hack.A100.w2.v1.0.th.test.s44
Updated
chitanda/llama2.7b.chat.logiqav2.70b-distil.dpo.fix_hack.A100.w2.v1.0.th.test.s42
Updated
chitanda/llama.30b.merit_v91_v91.seq2seq.v5.0.1aug.w4.adamw.400steps.H100.0125
Updated
chitanda/llama2.7b.chat.reclor.gpt351106.prm.fix_hack.H100.w8.v1.3.s42
Updated
chitanda/llama2.7b.logiqav2.cot-gen.A100.v1.0
Updated
chitanda/llama.13b.lima.v1.0.w2.A100.80G.0830
Updated
chitanda/llama.13b.sft-gpt4all.w4.adamw.500steps.v3.0.A00.40G.0830
Updated
chitanda/llama.13b.sft-gpt4all.w4.adamw.500steps.v2.0.NA100.0830
Updated
chitanda/llama2.7b.rw.emb_lqv2.w8.A100.v1.0
Updated
chitanda/llama.7b.merit_v91_v91.seq2seq.v5.0.3aug.w4.adamw.500steps.NA100.0504
Updated
chitanda/llama.30b.merit_v91_v91.seq2seq.v5.0.3aug.w4.adamw.400steps.NA100.0525
Updated
chitanda/llama.30b.merit_v91_v91.seq2seq.v5.0.0aug.w4.adamw.400steps.A40.0602
Updated
chitanda/llama-panda-13b-zh-wudao-chat-delta
Updated
chitanda/falcon.40b.q_lora.merit_v91_v91.seq2seq.v5.0.3aug.w16.adamw.500steps.NA100.0528
Updated
chitanda/llama.13b.merit_v91_v91.seq2seq.v5.0.3aug.w8.adamw.500steps.NA100.0426
Updated
chitanda/panda-7b-open-llama-preview-300pt
Text Generation
•
Updated
•
11
•
2
chitanda/llama-panda-zh-13b-coig-delta
Text Generation
•
Updated
•
13
chitanda/llama-panda-zh-13b-delta
Text Generation
•
Updated
•
13
•
2