Commit
·
9878e25
1
Parent(s):
795fb59
oct 8th update
Browse files
README.md
CHANGED
|
@@ -7,10 +7,16 @@ sdk: static
|
|
| 7 |
pinned: false
|
| 8 |
tags: [llama, code-llama, jupyter, colab, function calling, QLoRa, fine-tuning, scripts, fine-tuning]
|
| 9 |
---
|
| 10 |
-
*last updated Oct
|
| 11 |
## About
|
| 12 |
Trelis Research provides tools and tutorials for training, using and deploying large language models.
|
| 13 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 14 |
## Function-calling Models and Datasets
|
| 15 |
- [Llama 2 models fine-tuned for function calling, 7B, 13B, 70B, CodeLlama 34B](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2)
|
| 16 |
- [Dataset to fine-tune models for function calling](https://huggingface.co/datasets/Trelis/function_calling_extended)
|
|
@@ -20,15 +26,9 @@ Trelis Research provides tools and tutorials for training, using and deploying l
|
|
| 20 |
- [Video: Deploy a Llama API in 5 clicks](https://youtu.be/dJ69gY0qRbg)
|
| 21 |
- [Purchase access to the GitHub repo](https://buy.stripe.com/9AQ28UcWh4PF1ckeV9)
|
| 22 |
|
| 23 |
-
## Fine-tuning Scripts
|
| 24 |
-
Fine-tune LLMs for style, content or structured responses
|
| 25 |
-
- [View the three part YouTube series on embeddings, supervised and unsupervised fine-tuning](https://youtu.be/egnf8L-EUJU)
|
| 26 |
-
- [Purchase access to the GitHub repo](https://buy.stripe.com/cN27tef4p2Hx2go4gD)
|
| 27 |
-
|
| 28 |
## One-click LLM API/Server Templates
|
| 29 |
- [Runpod affiliate link](https://tinyurl.com/yjxbdc9w)
|
| 30 |
- [Llama 2 70B](https://tinyurl.com/2szykc6m)
|
| 31 |
-
- [Llama 2 Long Context](https://tinyurl.com/yesu9xnh)
|
| 32 |
|
| 33 |
## Summarise-Me.com
|
| 34 |
- [Summarise PDFs and websites up to 60,000 words](https://Summarise-Me.com)
|
|
|
|
| 7 |
pinned: false
|
| 8 |
tags: [llama, code-llama, jupyter, colab, function calling, QLoRa, fine-tuning, scripts, fine-tuning]
|
| 9 |
---
|
| 10 |
+
*last updated Oct 8th 2023*
|
| 11 |
## About
|
| 12 |
Trelis Research provides tools and tutorials for training, using and deploying large language models.
|
| 13 |
|
| 14 |
+
## Advanced Fine-tuning Scripts
|
| 15 |
+
Fine-tune LLMs for style, content or structured responses.
|
| 16 |
+
- Scripts included for supervised and unsupervised fine-tuning, data-preparation, quantisation and embeddings.
|
| 17 |
+
- [View the three part YouTube series on embeddings, supervised and unsupervised fine-tuning](https://youtu.be/egnf8L-EUJU)
|
| 18 |
+
- [Purchase access to the GitHub repo](https://buy.stripe.com/cN27tef4p2Hx2go4gD)
|
| 19 |
+
|
| 20 |
## Function-calling Models and Datasets
|
| 21 |
- [Llama 2 models fine-tuned for function calling, 7B, 13B, 70B, CodeLlama 34B](https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling-v2)
|
| 22 |
- [Dataset to fine-tune models for function calling](https://huggingface.co/datasets/Trelis/function_calling_extended)
|
|
|
|
| 26 |
- [Video: Deploy a Llama API in 5 clicks](https://youtu.be/dJ69gY0qRbg)
|
| 27 |
- [Purchase access to the GitHub repo](https://buy.stripe.com/9AQ28UcWh4PF1ckeV9)
|
| 28 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 29 |
## One-click LLM API/Server Templates
|
| 30 |
- [Runpod affiliate link](https://tinyurl.com/yjxbdc9w)
|
| 31 |
- [Llama 2 70B](https://tinyurl.com/2szykc6m)
|
|
|
|
| 32 |
|
| 33 |
## Summarise-Me.com
|
| 34 |
- [Summarise PDFs and websites up to 60,000 words](https://Summarise-Me.com)
|