vikas (Vikas Kumar)

liked a Space 11 months ago

Porting nanochat to Transformers: an AI modeling history lesson

📝

49

Read an AI article with theme toggle and PDF download

liked 2 datasets 11 months ago

databricks/databricks-dolly-15k

Viewer • Updated Jun 30, 2023 • 15k • 40.4k • 1.36k

HuggingFaceFW/finepdfs

Viewer • Updated Apr 3 • 476M • 76.9k • 950

liked a Space 12 months ago

The Smol Training Playbook

📚

3.34k

The secrets to building world-class LLMs

liked 2 Spaces about 1 year ago

Maintain the unmaintainable

📚

87

Explore the HuggingFace Transformers model dependency graph

Transformers Timeline

🤗

83

Interactive timeline to explore the 🤗Transformers models

liked 4 models over 1 year ago

liked 2 datasets over 1 year ago

docling-project/DocLayNet

Updated Jan 25, 2023 • 559 • 154

allenai/olmOCR-mix-0225

Viewer • Updated Feb 25, 2025 • 259k • 1.47k • 175

liked a model over 1 year ago

deepseek-ai/Janus-Pro-7B

Any-to-Any • Updated Feb 1, 2025 • 9.84k • 3.72k

liked a model almost 2 years ago

alibaba-damo/mgp-str-base

Image-to-Text • 0.1B • Updated Dec 11, 2023 • 18.4k • 65

liked 2 Spaces about 2 years ago

Tonic's GOT OCR

📲

178

GOT - OCR (from : UCAS, Beijing)

Qwen2-VL-7B

🔥

274

Answer questions about any uploaded image

liked a dataset about 2 years ago

HuggingFaceM4/Docmatix

Viewer • Updated Aug 26, 2024 • 2.55M • 17.9k • 317

liked a Space over 2 years ago

Florence 2

📉

848

Generate captions, detections, and OCR from an image

liked a model over 2 years ago

microsoft/Florence-2-base

Image-Text-to-Text • 0.2B • Updated Aug 4, 2025 • 2.92M • 430

liked a Space over 2 years ago

LLM Conf talk

🔥

20

Explore GPU usage and distributed training techniques

Vikas Kumar

AI & ML interests

Organizations

Porting nanochat to Transformers: an AI modeling history lesson

databricks/databricks-dolly-15k

HuggingFaceFW/finepdfs

The Smol Training Playbook

Maintain the unmaintainable

Transformers Timeline

Qwen/Qwen3-Embedding-0.6B-GGUF

osmosis-ai/Osmosis-Structure-0.6B

deepseek-ai/DeepSeek-R1-0528

reducto/RolmOCR

docling-project/DocLayNet

allenai/olmOCR-mix-0225

deepseek-ai/Janus-Pro-7B

alibaba-damo/mgp-str-base

Tonic's GOT OCR

Qwen2-VL-7B

HuggingFaceM4/Docmatix

Florence 2

microsoft/Florence-2-base

LLM Conf talk

Vikas Kumar

AI & ML interests

Organizations

vikas's activity

Porting nanochat to Transformers: an AI modeling history lesson

The Smol Training Playbook

Maintain the unmaintainable

Transformers Timeline

Tonic's GOT OCR

Qwen2-VL-7B

Florence 2

LLM Conf talk