Raushan Turganbay

RaushanTurganbay's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

New activity in CohereLabs/North-Micro-Vision-Instruct about 2 months ago

delete a trailing comma

#4 opened about 2 months ago by

RaushanTurganbay

New activity in Zyphra/ZAYA1-8B about 2 months ago

Fix rope validation error

#19 opened about 2 months ago by

RaushanTurganbay

New activity in poolside/Laguna-tiny-per-element about 2 months ago

Fix rope validation

1

#1 opened about 2 months ago by

RaushanTurganbay

New activity in mlx-community/Qwen3.8-27B-4bit about 2 months ago

Point to correct image processing class

2

#2 opened about 2 months ago by

RaushanTurganbay

New activity in CohereLabs/North-Micro-Vision-Instruct about 2 months ago

Update config.json

#3 opened about 2 months ago by

RaushanTurganbay

New activity in allenai/Olmo-3-7B-Instruct 3 months ago

Update tokenizer_config.json

#14 opened 3 months ago by

RaushanTurganbay

New activity in zai-org/GLM-4.1V-9B-Thinking 3 months ago

Fix config model type

#22 opened 3 months ago by

RaushanTurganbay

New activity in transformers-community/group-beam-search 4 months ago

Optimize group beam search by sharing the initial prefill across beams

3

#6 opened 4 months ago by

lavrenko

Possible performance issue: group beam search appears to prefill identical prefixes once per beam

3

#5 opened 4 months ago by

lavrenko

New activity in transformers-community/sink_cache 4 months ago

"sink_cache" fails on Transformers 5.12 due to outdated "Cache.__init__" API

1

#1 opened 4 months ago by

lavrenko

New activity in transformers-community/constrained-beam-search 4 months ago

constrained-beam-search produces degenerate output with use_cache=True

3

#2 opened 4 months ago by

lavrenko

New activity in transformers-community/dola 4 months ago

DoLa custom generation produces gibberish with use_cache=True

1

#1 opened 4 months ago by

lavrenko

Fix Transformers v5 cached decoding in DoLa

2

#2 opened 4 months ago by

lavrenko

New activity in transformers-community/constrained-beam-search 4 months ago

Support Transformers v5 cache handling

2

#3 opened 4 months ago by

lavrenko

New activity in transformers-community/group-beam-search 4 months ago

Custom group-beam-search changes deterministic output when cache is enabled

3

#3 opened 4 months ago by

lavrenko

Support Transformers v5 cache handling

2

#4 opened 4 months ago by

lavrenko

New activity in llava-hf/llava-1.5-7b-hf 5 months ago

[Question] Why does LLaVA evaluation assert batch_size == 1 for benchmark inference?

1

#62 opened 5 months ago by

austinkomachi

New activity in OpenGVLab/InternVL2-8B 7 months ago

Compatibility with v5

#23 opened 7 months ago by

RaushanTurganbay

New activity in OpenGVLab/InternVL2-1B 7 months ago

Compatibility with v5

#10 opened 7 months ago by

RaushanTurganbay

New activity in OpenGVLab/InternVL2-2B 7 months ago

Compatibility with v5

#7 opened 7 months ago by

RaushanTurganbay