jan-hq commited on
Commit
4a480d8
·
verified ·
1 Parent(s): 22665e6

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -5
README.md CHANGED
@@ -10,7 +10,7 @@ tags:
10
 
11
  ## Model Details
12
 
13
- 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.
14
 
15
  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.
16
 
@@ -28,7 +28,7 @@ We continue to expand [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-lla
28
 
29
  **Intended Use Cases** This family is primarily intended for research applications. This version aims to further improve the LLM on sound understanding capabilities.
30
 
31
- **Out-of-scope** The use of Jan-Llama3s in any manner that violates applicable laws or regulations is strictly prohibited.
32
 
33
  ## How to Get Started with the Model
34
 
@@ -115,6 +115,7 @@ print(generated_text)
115
  ```
116
 
117
  ## Training process
 
118
  **Training Metrics Image**: Below is a snapshot of the training loss curve visualized.
119
 
120
  ![train_loss_curve/png](https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/9bv-kpnqrTxaBhiYrVHN7.png)
@@ -244,12 +245,12 @@ Despite being undertrained, the model demonstrates an emerging grasp of sound-te
244
  **BibTeX:**
245
 
246
  ```
247
- @article{Llama-3-Sound: Sound Instruction LLM 2024,
248
- title={Llama-3-Sound},
249
  author={Homebrew Research},
250
  year=2024,
251
  month=July},
252
- url={https://huggingface.co/jan-hq/Jan-Llama3-0708}
253
  ```
254
 
255
  ## Acknowledgement
 
10
 
11
  ## Model Details
12
 
13
+ We have developed and released the family [llama3-s](https://huggingface.co/collections/homebrew-research/llama3-s-669df2139f0576abc6eb7405). This family is natively understanding audio and text input.
14
 
15
  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.
16
 
 
28
 
29
  **Intended Use Cases** This family is primarily intended for research applications. This version aims to further improve the LLM on sound understanding capabilities.
30
 
31
+ **Out-of-scope** The use of llama3-s in any manner that violates applicable laws or regulations is strictly prohibited.
32
 
33
  ## How to Get Started with the Model
34
 
 
115
  ```
116
 
117
  ## Training process
118
+
119
  **Training Metrics Image**: Below is a snapshot of the training loss curve visualized.
120
 
121
  ![train_loss_curve/png](https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/9bv-kpnqrTxaBhiYrVHN7.png)
 
245
  **BibTeX:**
246
 
247
  ```
248
+ @article{llama3-s: Sound Instruction Language Model 2024,
249
+ title={llama3-s},
250
  author={Homebrew Research},
251
  year=2024,
252
  month=July},
253
+ url={https://huggingface.co/homebrew-research/llama3-s-0708}
254
  ```
255
 
256
  ## Acknowledgement