README.md

---
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/jan-hq/instruction-speech-v1) 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.

![train_loss_curve/png](https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/9bv-kpnqrTxaBhiYrVHN7.png)

### 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](https://github.com/collabora/WhisperSpeech)**

- **[Encodec](https://github.com/facebookresearch/encodec)**

- **[Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)**