Versions of the OpenAssist Dataset for chat fine-tuning different models. See https://youtu.be/71x8EMrB0Gc for a full video run through of methods.
Trelis
company
AI & ML interests
Function Calling. Quantizing. Fine-Tuning. Summarizing. Long-context Length.
Organization Card
last updated August 1st 2024
About
Trelis Research provides:
- Advanced LLM fine-tuning scripts.
- Advanced LLM inference guides.
- Advanced vision fine-tuning scripts.
- Advanced voice/transcription fine-tuning scripts.
- One click LLM API templates
- Function-calling models.
ADVANCED Fine-tuning Scripts
- retrieval (bm25, similarity, re-rankers)
- wikipedia fine-tuning and dataset creation
- ReFT fine-tuning
- multi-gpu fine-tuning
- orpo fine-tuning
- memorization fine-tuning
- mamba-fine-tune
- DPO fine-tuning
- chat-fine-tuning
- function-calling fine-tuning
- long-context fine-tuning
- quantization
- supervised-fine-tuning
- unsupervised-fine-tuning
ADVANCED Inference
- Server setup, API setup and inference guide for open source models
- Inference for function calling
- Monte Carlo Inference Methods
- Private Data Redaction
- Structured Data Extraction with LLMs
- Verified RAG citations
ADVANCED Vision Fine-tuning
- Dataset Preparation
- Fine-tuning Llava, IDEFICS2
ADVANCED Transcription and Voice Cloning
- Dataset Generation
- Fine-tuning Whisper speech-to-text on custom datasets
- Voice Cloning Fine-tuning / Text-to-Speech
One-click LLM API/Server Templates
- Check out the full list here
Function-calling Models and Datasets
- Fine-tuned models for function calling - from 1.3B to 70B in size, incl. Mixtral, Yi, Deepseek, Llama and more. Collection here
- Dataset to fine-tune models for function calling. Access here
- Scripts to fine-tune models for function calling and structured responses.
Collections
2
Models fine-tuned for function-calling
-
Trelis/Meta-Llama-3-70B-Instruct-function-calling
Text Generation • Updated • 17 • 22 -
Trelis/Meta-Llama-3-8B-Instruct-function-calling
Text Generation • Updated • 208 • 42 -
Trelis/openchat_3.5-function-calling-v3
Text Generation • Updated • 21 -
Trelis/Llama-2-7b-chat-hf-function-calling-v3
Text Generation • Updated • 402 • 41
models
200
Trelis/whisper-turbo-llm-lingo-ctranslate2
Updated
•
37
Trelis/whisper-turbo-llm-lingo
Automatic Speech Recognition
•
Updated
•
30
Trelis/whisper-turbo-llm-lingo-adapters
Updated
Trelis/Meta-Llama-3.1-8B-Instruct-Trelis-ARC-1ep-20241013-201317-ft
Text Generation
•
Updated
•
15
Trelis/Llama-3.2-1B-Instruct-MedQuad-Medical-1ep-20241012-132034-dist-fwd-1a-2.0distT
Text Generation
•
Updated
•
15
Trelis/Meta-Llama-3.1-8B-Instruct-MedQuad-Medical-1ep-20241012-125051-ft
Text Generation
•
Updated
•
15
Trelis/Llama-3.2-1B-Instruct-MedQuad-1024-synth-aug-1ep-20241012-103256-dist-fwd-1a-2.0distT
Text Generation
•
Updated
•
13
Trelis/Llama-3.2-1B-Instruct-MedQuad-1024-synth-aug-1ep-20241012-101531-dist-fwd-1a-1distT
Text Generation
•
Updated
•
13
Trelis/Llama-3.2-1B-Instruct-MedQuad-MedicalQnADataset-1024-synth-aug-1ep-20241012-100644-ft
Text Generation
•
Updated
•
64
Trelis/Llama-3.2-1B-Instruct-MedQuad-1024rows-synth-aug-1ep-20241012-095406-ft
Updated
datasets
61
Trelis/llm-lingo
Viewer
•
Updated
•
11
•
101
•
6
Trelis/MedQuad-MedicalQnADataset-1024-synth-aug
Viewer
•
Updated
•
978
•
37
Trelis/MATH-prealgebra-4rows-synthetic-augmented
Viewer
•
Updated
•
3
•
80
Trelis/MATH-prealgebra-4rows-synthetic
Viewer
•
Updated
•
2
•
34
Trelis/MATH-prealgebra-8rows-synthetic
Viewer
•
Updated
•
3
•
42
Trelis/touch-rugby-synth-test
Viewer
•
Updated
•
10
•
41
Trelis/MATH-8rows-synthetic-augmented
Viewer
•
Updated
•
8
•
37
Trelis/MATH-8rows-synthetic
Viewer
•
Updated
•
2
•
36
Trelis/touch-rugby-synth
Viewer
•
Updated
•
215
•
104
•
1
Trelis/synth-test
Viewer
•
Updated
•
10
•
41