Hugging Face
Models
Datasets
Spaces
Posts
Docs
Enterprise
Pricing
Log In
Sign Up
48.7
TFLOPS
4
20
25
Nicolay Rusnachenko
nicolay-r
Follow
Pranit7's profile picture
Jirigesi's profile picture
lerniri's profile picture
63 followers
Β·
4 following
https://nicolay-r.github.io/
nicolayr_
nicolay-r
nicolay-r
AI & ML interests
Information Retrievalγ»Medical Multimodal NLP (πΌ+π) Research Fellow @BU_Researchγ»software developer http://arekit.ioγ»PhD in NLP
Recent Activity
posted
an
update
about 7 hours ago
π’ Replicate IO just started support π DeepSeek-R1 hosting! https://replicate.com/deepseek-ai/deepseek-r1 If you wish to quick start with reasoning over your dataset data, I just added support at Replicate provider for bulk-chain: https://github.com/nicolay-r/nlp-thirdgate/blob/ebcdec156eb43f9c32d0d70aadc2d26765d31b75/llm/replicate_104.py#L14-L21 π§ What I fixed (see my setups in the second screenshot) - π‘οΈdefault temperature is 0.6 - β no system prompt Here is a quick start for applying R1 for reasoning over your data (see first screenshot): https://github.com/nicolay-r/bulk-chain?tab=readme-ov-file#shell π Perfomance: ~24 tokens / sec. In my experience the peformance is way more faster than at OpenRouter, similar to playground π΅ Price: 10 USD / 10 USD per 1M tokens π bulk-chain: https://github.com/nicolay-r/bulk-chain
liked
a model
1 day ago
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
reacted
to
clem
's
post
with π
1 day ago
The π³ just crossed 10,000 followers on HF https://huggingface.co/deepseek-ai
View all activity
Organizations
None yet
nicolay-r
's activity
All
Models
Datasets
Spaces
Papers
Collections
Community
Posts
Upvotes
Likes
liked
a model
1 day ago
deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
Text Generation
β’
Updated
4 days ago
β’
166k
β’
276
liked
a model
4 days ago
deepseek-ai/DeepSeek-R1
Text Generation
β’
Updated
4 days ago
β’
498k
β’
5.23k
liked
a Space
16 days ago
Running
on
CPU Upgrade
324
π₯
Open Medical-LLM Leaderboard
liked
a model
16 days ago
johnsnowlabs/JSL-MedLlama-3-8B-v2.0
Text Generation
β’
Updated
Apr 30, 2024
β’
11.9k
β’
29
liked
a model
4 months ago
meta-llama/Llama-3.2-3B-Instruct
Text Generation
β’
Updated
Oct 24, 2024
β’
1.48M
β’
939
liked
a model
6 months ago
hyy-33/hyy33-WASSA-2024-Track-2
Updated
Jul 9, 2024
β’
2
liked
2 models
7 months ago
google/gemma-2-9b-it
Text Generation
β’
Updated
Aug 27, 2024
β’
389k
β’
639
google/gemma-2-27b-it
Text Generation
β’
Updated
Aug 27, 2024
β’
169k
β’
509
liked
4 models
8 months ago
Qwen/Qwen2-7B-Instruct
Text Generation
β’
Updated
Aug 21, 2024
β’
854k
β’
611
mistralai/Mistral-7B-Instruct-v0.3
Text Generation
β’
Updated
Aug 21, 2024
β’
1.78M
β’
1.29k
microsoft/Phi-3-small-8k-instruct
Text Generation
β’
Updated
Aug 30, 2024
β’
24.8k
β’
160
microsoft/Phi-3-mini-4k-instruct
Text Generation
β’
Updated
Sep 20, 2024
β’
903k
β’
1.12k
liked
2 models
9 months ago
xtuner/llava-phi-3-mini-hf
Image-to-Text
β’
Updated
Apr 25, 2024
β’
5.94k
β’
48
xtuner/llava-llama-3-8b-v1_1
Image-Text-to-Text
β’
Updated
Apr 28, 2024
β’
55
β’
120
liked
6 models
10 months ago
AIRI-Institute/OmniFusion
Updated
Apr 10, 2024
β’
56
google-bert/bert-base-uncased
Fill-Mask
β’
Updated
Feb 19, 2024
β’
84M
β’
2.08k
google/gemma-1.1-2b-it
Text Generation
β’
Updated
Jun 27, 2024
β’
89.4k
β’
154
google/gemma-2b-it
Text Generation
β’
Updated
Sep 27, 2024
β’
100k
β’
701
google/gemma-7b-it
Text Generation
β’
Updated
Aug 14, 2024
β’
66.7k
β’
1.15k
google/gemma-1.1-7b-it
Text Generation
β’
Updated
Jun 27, 2024
β’
19.1k
β’
270
Load more