Update README.md

README.md

@@ -10,7 +10,7 @@ tags:
 
 ## Model Details
 
-We have developed and released the family Llama-3-8B-Sound. This family is natively understanding audio and text input.
+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.
 
@@ -37,7 +37,7 @@ We continue to expand [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-lla
 ## Training process
 **Training Metrics Image**: Below is a snapshot of the training loss curve visualized.
 
-![training_loss_curve/png](https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/12vqghBGus1Bb2OTjNezl.png)
+![train_loss_curve/png](https://cdn-uploads.huggingface.co/production/uploads/65713d70f56f9538679e5a56/9bv-kpnqrTxaBhiYrVHN7.png)
 
 ### Hardware
 
@@ -61,7 +61,8 @@ We continue to expand [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-lla
 | **epsilon**                | 1e-6                    | 
 | **Gradient Cliping**       | 1.0                     | 
 
-### Accelerate FSDP Config
+###
+ Accelerate FSDP Config
 
 ```
 compute_environment: LOCAL_MACHINE
@@ -165,10 +166,10 @@ Despite being undertrained, the model demonstrates an emerging grasp of sound-te
 ```
 @article{Llama-3-Sound: Sound Instruction LLM 2024,
   title={Llama-3-Sound},
-  author={JanAI},
+  author={Homebrew Research},
   year=2024,
   month=July},
-  url={https://huggingface.co/jan-hq/llama-3-sound-init-checkpoint-4340}
+  url={https://huggingface.co/jan-hq/Jan-Llama3-0708}
 ```
 
 ## Acknowledgement