Rumen Mihaylov

rmihaylov's activity

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

upvoted a collection about 1 month ago

Qwen2.5

Collection

Qwen2.5 language models, including pretrained and instruction-tuned models of 7 sizes, including 0.5B, 1.5B, 3B, 7B, 14B, 32B, and 72B. • 45 items • Updated 29 days ago • 445

New activity in rmihaylov/Bg-Instructions 5 months ago

[bot] Conversion to Parquet

#1 opened 5 months ago by

parquet-converter

updated 2 datasets 5 months ago

rmihaylov/Bg-Instructions-Filtered

Viewer • Updated Jul 17 • 107k • 40

rmihaylov/Bg-Instructions

Viewer • Updated Jul 17 • 225k • 50

liked a model 7 months ago

Efficient-ML/LLaMA-3-70B-GPTQ-4bit-b128

Updated Jun 4 • 2

New activity in mlx-community/Meta-Llama-3-70B-Instruct-8bit 8 months ago

Great model! What is the quantization sequence length?

1

#1 opened 8 months ago by

rmihaylov

updated 3 models 8 months ago

rmihaylov/Llama-3-DARE-v1-8B

Text Generation • Updated Apr 21 • 30

rmihaylov/Llama-3-DARE-v2-8B

Text Generation • Updated Apr 21 • 34

rmihaylov/Llama-3-DARE-v3-8B

Text Generation • Updated Apr 21 • 29

updated a collection 11 months ago

Interesting

Collection

1 item • Updated Jan 29

liked a Space about 1 year ago

Running on CPU Upgrade

12.1k

🏆

Open LLM Leaderboard

Track, rank and evaluate open LLMs and chatbots

liked a model about 1 year ago

rmihaylov/bert-base-bg

Fill-Mask • Updated Apr 17, 2022 • 107 • 7

updated 2 models over 1 year ago

rmihaylov/falcon-7b-instruct-GPTQ

Text Generation • Updated Jun 9, 2023 • 15

rmihaylov/falcon-40b-instruct-GPTQ

Text Generation • Updated Jun 9, 2023 • 14 • 1

New activity in dfurman/Falcon-40B-Chat-v0.1 over 1 year ago

Inference speed

6

#2 opened over 1 year ago by

rmihaylov

New activity in TheBloke/falcon-40b-instruct-GPTQ over 1 year ago

Custom 4-bit Finetuning 5-7 times faster inference than QLora

#7 opened over 1 year ago by

rmihaylov

New activity in TheBloke/Falcon-7B-Instruct-GPTQ over 1 year ago

Custom 4-bit Finetuning 5-7 times faster inference than QLora

2

#5 opened over 1 year ago by

rmihaylov

New activity in tiiuae/falcon-7b over 1 year ago

Custom 4-bit Finetuning 5-7 times faster inference than QLora

1

#13 opened over 1 year ago by

rmihaylov

New activity in tiiuae/falcon-7b-instruct over 1 year ago

Custom 4-bit Finetuning 5-7 times faster inference than QLora

#13 opened over 1 year ago by

rmihaylov