Downloads · 30 days
17
49% of all-time downloads
Vikhrmodels_-_salt-116k-awq
RichardErkhov/Vikhrmodels_-_salt-116k-awq
Vikhrmodels_-_salt-116k-awq is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
35
Public
Parameters
1.1B
774 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors774 MB · 99%
Parameter types
How the weights are stored.
I32969M · 88%
Model card
From the Hugging Face model README
Quantization made by Richard Erkhov.
salt-116k - AWQ
- Model creator: https://huggingface.co/Vikhrmodels/
- Original model: https://huggingface.co/Vikhrmodels/salt-116k/
Original model description:
library_name: transformers license: apache-2.0 language:
- en base_model:
- TinyLlama/TinyLlama_v1.1
Vikhr Salt: Speech And Language Transformer
Vikhr Salt is a multimodal model based on a pre-trained large language model, extended with new audio tokens to handle both TTS (text-to-speech) and ASR (automatic speech recognition) tasks. The model incorporates two variants for encoding audio—Encodec and SpeechTokenizer—and achieves stable training by fine-tuning precision settings. This approach allows Vikhr Salt to leverage pre-existing LLM knowledge while effectively generating and understanding speech, marking a step forward in multimodal learning.
Model Authors
Ksenya Sycheva, Konstantin Korolev, Aleksandr Nikolic
- Type
- llama
- Created
- Dec 25, 2024
- Updated
- Dec 25, 2024