Index and retrieve documents for vector search using Sentence Transformers and DuckDB
β’
1
David Berenstein
davidberenstein1957
AI & ML interests
Everything data
Recent Activity
updated
a dataset
about 5 hours ago
davidberenstein1957/short-think-making-reasoning-less-chatty
liked
a dataset
about 5 hours ago
HuggingFaceH4/numina-deepseek-r1-qwen-7b
liked
a Space
about 6 hours ago
Qwen/Qwen-Max-0428
Articles
Organizations
Posts
44
Post
1677
Let's uncover the post-training dataset from DeepSeek-R1 with Magpie!
Pass pre-query tokens
We can get realistic examples!
Gist: https://gist.github.com/davidberenstein1957/3f20046ce57395a6aba13f8b4e956b59
Pass pre-query tokens
<ο½beginβofβsentenceο½>User: , let the model generate the rest.We can get realistic examples!
Gist: https://gist.github.com/davidberenstein1957/3f20046ce57395a6aba13f8b4e956b59
Post
1848
The RAG's in the bag!
You can now use the Synthetic Data Generator with your own domain-specific seed data to generate a dataset for fine-tuning retrieval or reranking models.
GitHub: https://buff.ly/49IDSmd
Spaces: https://buff.ly/3Y1S99z
Blog: https://huggingface.co/blog/sdiazlor/fine-tune-modernbert-for-rag-with-synthetic-data
You can now use the Synthetic Data Generator with your own domain-specific seed data to generate a dataset for fine-tuning retrieval or reranking models.
GitHub: https://buff.ly/49IDSmd
Spaces: https://buff.ly/3Y1S99z
Blog: https://huggingface.co/blog/sdiazlor/fine-tune-modernbert-for-rag-with-synthetic-data
Collections
10
A collection of smoll but mighty models
-
376π§¬
Synthetic Data Generator
Build datasets using natural language
-
7π
Transformers Pipeline Playground
Search, load and play with transformer pipelines
-
13π¦Ύπͺπ½
Human Feedback Collector | Meta-Llama-3.1-8B-Instruct | (DPO)
LLM, chatbot, human-feedback
-
10βοΈ
Distilabel Synthetic Data Pipeline Finder
spaces
16
pinned
Running
62
π₯
Vectorsearch Hub Datasets
Add vectors to Hub datasets and do in memory vector search.
pinned
Running
π₯
Vectorsearch Hub Datasets
Add vectors to Hub datasets and do in memory vector search.
pinned
Running
7
π
Transformers Pipeline Playground
Search, load and play with transformer pipelines
pinned
Running
22
π₯ π¦ π€
Text To SQL Hub Datasets
pinned
Sleeping
5
π¦Ύπͺπ½
Human Feedback Collector | Meta-Llama-3.1-8B-Instruct | (KTO)
LLM, chatbot, human-feedback
pinned
Running
on
Zero
13
π¦Ύπͺπ½
Human Feedback Collector | Meta-Llama-3.1-8B-Instruct | (DPO)
LLM, chatbot, human-feedback
models
3
datasets
45
davidberenstein1957/short-think-making-reasoning-less-chatty
Viewer
β’
Updated
β’
40
β’
1
davidberenstein1957/structured-generation-information-extraction-vlms-openbmb-RLAIF-V-Dataset
Viewer
β’
Updated
β’
10
davidberenstein1957/my-vicinity-repo
Viewer
β’
Updated
β’
5
β’
12
β’
1
davidberenstein1957/openai_records_0742e002
Updated
β’
3
davidberenstein1957/hf_client_records_778db757
Viewer
β’
Updated
β’
1
β’
7
davidberenstein1957/hf_client_records_104d3f34
Viewer
β’
Updated
β’
1
β’
8
davidberenstein1957/example
Updated
β’
10
davidberenstein1957/follow-the-money-imdb
Viewer
β’
Updated
β’
100
β’
32
davidberenstein1957/sft-dataset
Viewer
β’
Updated
β’
10
β’
35
β’
3
davidberenstein1957/openai_records_a1b9734b
Viewer
β’
Updated
β’
1
β’
27