|
--- |
|
license: apache-2.0 |
|
datasets: |
|
- jan-hq/instruction-speech-v1 |
|
language: |
|
- en |
|
tags: |
|
- sound language model |
|
--- |
|
|
|
## Model Details |
|
|
|
We have developed and released the family [Jan-Llama3](https://huggingface.co/collections/jan-hq/jan-llama3-668e4dad446c8736208dca4f). This family is natively understanding audio and text input. |
|
|
|
We continue to expand [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) with sound understanding capabilities by leveraging 700M tokens [Instruction Speech v1](https://huggingface.co/datasets/Vi-VLM/Vista) dataset. |
|
|
|
**Model developers** Homebrew Research. |
|
|
|
**Input** Text and sound. |
|
|
|
**Output** Text. |
|
|
|
**Model Architecture** Llama-3. |
|
|
|
**Language(s):** English. |
|
|
|
## Intended Use |
|
|
|
**Intended Use Cases** This family is primarily intended for research applications. This version aims to further improve the LLM on sound understanding capabilities. |
|
|
|
**Out-of-scope** The use of Llama-3-Sound in any manner that violates applicable laws or regulations is strictly prohibited. |
|
|
|
## How to Get Started with the Model |
|
|
|
> TODO |
|
|
|
## Training process |
|
**Training Metrics Image**: Below is a snapshot of the training loss curve visualized. |
|
|
|
 |
|
|
|
### Hardware |
|
|
|
**GPU Configuration**: Cluster of 8x NVIDIA H100-SXM-80GB. |
|
**GPU Usage**: |
|
- **Continual Training**: 8 hours. |
|
|
|
### Training Arguments |
|
|
|
| Parameter | Continual Training | |
|
|----------------------------|-------------------------| |
|
| **Epoch** | 1 | |
|
| **Global batch size** | 128 | |
|
| **Learning Rate** | 5e-5 | |
|
| **Learning Scheduler** | Cosine with warmup | |
|
| **Optimizer** | [Adam-mini](https://arxiv.org/abs/2406.16793) | |
|
| **Warmup Ratio** | 0.1 | |
|
| **Weight Decay** | 0.01 | |
|
| **beta1** | 0.9 | |
|
| **beta2** | 0.98 | |
|
| **epsilon** | 1e-6 | |
|
| **Gradient Cliping** | 1.0 | |
|
|
|
### |
|
Accelerate FSDP Config |
|
|
|
``` |
|
compute_environment: LOCAL_MACHINE |
|
debug: false |
|
distributed_type: FSDP |
|
downcast_bf16: 'no' |
|
enable_cpu_affinity: true |
|
fsdp_config: |
|
fsdp_activation_checkpointing: true |
|
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP |
|
fsdp_backward_prefetch: BACKWARD_PRE |
|
fsdp_cpu_ram_efficient_loading: true |
|
fsdp_forward_prefetch: false |
|
fsdp_offload_params: false |
|
fsdp_sharding_strategy: FULL_SHARD |
|
fsdp_state_dict_type: SHARDED_STATE_DICT |
|
fsdp_sync_module_states: true |
|
fsdp_use_orig_params: false |
|
machine_rank: 0 |
|
main_training_function: main |
|
mixed_precision: bf16 |
|
num_machines: 1 |
|
num_processes: 8 |
|
rdzv_backend: static |
|
same_network: true |
|
tpu_env: [] |
|
tpu_use_cluster: false |
|
tpu_use_sudo: false |
|
use_cpu: false |
|
``` |
|
|
|
## Examples |
|
|
|
1. Good example: |
|
``` |
|
# Question: |
|
Does the following review have a positive or negative opinion of the movie? |
|
|
|
i thought the relationships were wonderful , |
|
Options: A). negative; B). positive; |
|
|
|
# Expected Output: |
|
The review has a B). positive opinion about the movie because they think the relationships were wonderful. |
|
|
|
# Model's Output: |
|
The review is positive. |
|
``` |
|
|
|
2. Misunderstanding example: |
|
``` |
|
# Question: |
|
Translate the following sentence to Russian: |
|
6 Work in JOBS and careers after 40 |
|
|
|
Russian: |
|
|
|
# Expected Output: |
|
6 Работать в РАБОТАХ и карьере после 40 |
|
|
|
Russian (Cyrillic): 6 Работать в РАБОТАХ и карьере после 40 |
|
|
|
Let me explain this to you like you're five years old: This sentence means that people can still work and have careers, even if they're older than 40 years old. The words are in a different language, called Russian. |
|
# Model's Output: |
|
В случае, когда вы хотите перевести фразу "The first step is to identify the language of the text." на русский язык, вы можете использовать следующую фразу: "Первый шаг - определить язык текста." |
|
``` |
|
|
|
3. Off-tracked example: |
|
``` |
|
# Quesion: |
|
Answer the following question: - The roots of the growing plants start to break up the rock - The plant acids dissolve the rock - The rock is broken down into smaller pieces - Erosion begins. What might be the first step of the process? |
|
Answer: |
|
|
|
# Expected Output: |
|
The first step of the process might be: The roots of the growing plants start to break up the rock. |
|
|
|
# Model's Output: |
|
Step 1: Identify the key elements in the premise and hypothesis. |
|
|
|
Premise: "A man in a blue shirt and a red hat is holding a sign." |
|
Key elements: man, blue shirt, red hat, holding, sign |
|
|
|
Hypothesis: "A man is holding a sign." |
|
Key elements: man, holding, sign |
|
|
|
Step 2: Compare the key elements in the premise and hypothesis. |
|
|
|
In the premise, we have a man wearing a blue shirt and a red hat, while in the hypothesis, we only have a man. The premise also mentions that the man is holding a sign, which is also mentioned in the hypothesis. |
|
|
|
Step 3: Determine if the hypothesis is entailed by the premise. |
|
|
|
Since the hypothesis states that a man is holding a sign, and the premise confirms that a man is holding a sign, we can conclude that the hypothesis is entailed by the premise. The additional information about the man's clothing in the premise does not contradict or negate the |
|
``` |
|
|
|
Despite being undertrained, the model demonstrates an emerging grasp of sound-text semantics. |
|
|
|
|
|
## Citation Information |
|
|
|
**BibTeX:** |
|
|
|
``` |
|
@article{Llama-3-Sound: Sound Instruction LLM 2024, |
|
title={Llama-3-Sound}, |
|
author={Homebrew Research}, |
|
year=2024, |
|
month=July}, |
|
url={https://huggingface.co/jan-hq/Jan-Llama3-0708} |
|
``` |
|
|
|
## Acknowledgement |
|
|
|
- **[WhisperSpeech]** |
|
|
|
- **[Encodec]** |
|
|
|
- **[Meta-Llama-3-8B-Instruct]** |
