NIkita Balakin

Kotokin's activity

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

New activity in DontPlanToEnd/UGI-Leaderboard about 2 months ago

Evaluation request

#443 opened about 2 months ago by

Kotokin

New activity in bartowski/p-e-w_gpt-oss-20b-heretic-GGUF 2 months ago

The older version, please.

#1 opened 2 months ago by

Kotokin

liked a model 10 months ago

Tarek07/Legion-V2.1-LLaMa-70B

Text Generation • 71B • Updated May 17, 2025 • 16 • 24

reacted to csabakecskemeti's post with 👍 11 months ago

view post

Post

2003

-UPDATED-
4bit inference is working! The blogpost is updated with code snippet and requirements.txt
https://devquasar.com/uncategorized/all-about-amd-and-rocm/
-UPDATED-
I've played around with an MI100 and ROCm and collected my experience in a blogpost:
https://devquasar.com/uncategorized/all-about-amd-and-rocm/
Unfortunately I've could not make inference or training work with model loaded in 8bit or use BnB, but did everything else and documented my findings.

See translation

• 

• 
• 
• 4 replies

·

👍

5

5

🔥

3

3

🚀

1

1

👀

1

1

🤗

1

1

❤️

1

1

😎

1

1

➕

1

1

🧠

1

1

🤝

1

1

😔

1

1

🤯

1

1

+

Reply

replied to csabakecskemeti's post 11 months ago

view reply

How many tokens per second do you receive? I didn't see this on the blog.

liked a model about 1 year ago

Konnect1221/The-Inception-Presets-Methception-LLamaception-Qwenception

Updated Feb 3, 2025 • 135

updated a model about 1 year ago

Kotokin/EVA-UNIT-01_EVA-LLaMA-3.33-70B-v0.1-exl2-5bpw

Text Generation • Updated Dec 21, 2024 • 4

New activity in ArliAI/Llama-3.1-70B-ArliAI-RPMax-v1.3 about 1 year ago

The question of training the model.

1

#2 opened about 1 year ago by

Kotokin

New activity in MikeRoz/mistralai_Mistral-Large-Instruct-2411-3.0bpw-h6-exl2 about 1 year ago

Request for a 3.5 bpw

#1 opened about 1 year ago by

Kotokin

liked a model about 1 year ago

MikeRoz/mistralai_Mistral-Large-Instruct-2411-4.0bpw-h6-exl2

Updated Nov 19, 2024 • 3 • 4

New activity in mistralai/Mistral-Large-Instruct-2411 about 1 year ago

Where config.json?

10

#1 opened about 1 year ago by

TheDrummer

liked a model about 1 year ago

TheDrummer/Behemoth-123B-v1.1

123B • Updated Oct 26, 2024 • 6 • 23

reacted to BlinkDL's post with 👀 over 1 year ago

view post

Post

5802

RWKV-7 "Goose" preview rc2 => Peak RNN architecture?😃Will try to squeeze more performance for the final release. Preview code & model: https://github.com/BlinkDL/RWKV-LM/tree/main/RWKV-v7

• 

• 
• 
• 2 replies

·

👀

11

11

🚀

4

4

👍

3

3

❤️

2

2

🔥

1

1

+

Reply

updated a model over 1 year ago

Kotokin/sophosympatheia_New-Dawn-Llama-3.1-70B-v1.1-exl2-4.5bpw

Text Generation • Updated Aug 15, 2024 • 3 • 2

liked a model over 1 year ago

ChenMnZ/Mistral-Large-Instruct-2407-EfficientQAT-w2g64-GPTQ

123B • Updated Aug 6, 2024 • 5 • 25

updated a model over 1 year ago

Kotokin/internlm_internlm2_5-20b-chat-exl2-8bpw

Text Generation • Updated Aug 6, 2024 • 3

New activity in sophosympatheia/New-Dawn-Llama-3-70B-32K-v1.0 over 1 year ago

The question is about the next model.

2

#8 opened over 1 year ago by

Kotokin

liked 2 models over 1 year ago

Qwen/Qwen2-72B-Instruct

Text Generation • 73B • Updated Oct 8, 2024 • 20.7k • • 718

abacusai/Smaug-Llama-3-70B-Instruct-32K

Text Generation • 71B • Updated Aug 6, 2024 • 7.94k • • 21

upvoted a collection over 1 year ago

Qwen2

Collection

Qwen2 language models, including pretrained and instruction-tuned models of 5 sizes, including 0.5B, 1.5B, 7B, 57B-A14B, and 72B. • 39 items • Updated 18 days ago • 374