andthattoo
commited on
Update README.md
Browse files
README.md
CHANGED
@@ -3,6 +3,7 @@ base_model: nisten/Biggie-SmoLlm-0.15B-Base
|
|
3 |
license: mit
|
4 |
datasets:
|
5 |
- LDJnr/Capybara
|
|
|
6 |
pipeline_tag: text-generation
|
7 |
tags:
|
8 |
- llama
|
@@ -11,7 +12,8 @@ tags:
|
|
11 |
|
12 |
### Fine-tuned [Biggie-SmoLlm-0.15B-Base](https://huggingface.co/nisten/Biggie-SmoLlm-0.15B-Base) for generating subqueries
|
13 |
|
14 |
-
This dude is trained for boosting the performance of your IR app, or RAG
|
|
|
15 |
My motivation was to tackle a core problem of IR with an extremely lightweight, but capable model.
|
16 |
|
17 |
If queries are
|
@@ -19,6 +21,8 @@ If queries are
|
|
19 |
- vague, ask follow up questions
|
20 |
- multiple sub questions, generate multiple queries for each of them
|
21 |
|
|
|
|
|
22 |
|
23 |
Heads up: [Ollama](https://ollama.com/andthattoo/subquery-smollm) version works 160 tps on 1 CPU core. No GPU? No worries. This little dude’s got you.
|
24 |
|
|
|
3 |
license: mit
|
4 |
datasets:
|
5 |
- LDJnr/Capybara
|
6 |
+
- andthattoo/subqueries
|
7 |
pipeline_tag: text-generation
|
8 |
tags:
|
9 |
- llama
|
|
|
12 |
|
13 |
### Fine-tuned [Biggie-SmoLlm-0.15B-Base](https://huggingface.co/nisten/Biggie-SmoLlm-0.15B-Base) for generating subqueries
|
14 |
|
15 |
+
This dude is trained for boosting the performance of your IR app, or RAG.
|
16 |
+
|
17 |
My motivation was to tackle a core problem of IR with an extremely lightweight, but capable model.
|
18 |
|
19 |
If queries are
|
|
|
21 |
- vague, ask follow up questions
|
22 |
- multiple sub questions, generate multiple queries for each of them
|
23 |
|
24 |
+
Training data was generated wit [Dria](dria.co). A decentralized p2p network for synthetic data. Join [discord](https://discord.gg/dria) to help decentralized data generation
|
25 |
+
|
26 |
|
27 |
Heads up: [Ollama](https://ollama.com/andthattoo/subquery-smollm) version works 160 tps on 1 CPU core. No GPU? No worries. This little dude’s got you.
|
28 |
|