Update README.md
Browse files
README.md
CHANGED
|
@@ -27,6 +27,7 @@ M4-ai/TinyMistral-6x248M-Instruct is designed for developers and researchers who
|
|
| 27 |
|
| 28 |
The model was fine-tuned using the hercules-v1.0 dataset, which is an augmented version of the teknium/openhermes dataset. Hercules-v1.0 includes updated data sources like ise-uiuc/Magicoder-Evol-Instruct-110K, jondurbin/airoboros-3.2, and WizardLM/WizardLM_evol_instruct_V2_196k, as well as specialized datasets in mathematics, chemistry, physics, and biology. The dataset has been cleaned to remove RLHF refusals and potentially toxic content from airoboros-3.2. However, users should be aware that a small portion of the data might still contain sensitive content.
|
| 29 |
|
|
|
|
| 30 |
## Limitations and Bias
|
| 31 |
|
| 32 |
While efforts have been made to clean the training data, the potential for biases and harmful content remains, as with any large language model. Users should exercise caution and discretion when utilizing the model, especially in applications that might amplify existing biases or expose users to sensitive content. The model is not recommended for scenarios requiring strict content moderation or for users without the ability to filter or assess the model's outputs critically.
|
|
|
|
| 27 |
|
| 28 |
The model was fine-tuned using the hercules-v1.0 dataset, which is an augmented version of the teknium/openhermes dataset. Hercules-v1.0 includes updated data sources like ise-uiuc/Magicoder-Evol-Instruct-110K, jondurbin/airoboros-3.2, and WizardLM/WizardLM_evol_instruct_V2_196k, as well as specialized datasets in mathematics, chemistry, physics, and biology. The dataset has been cleaned to remove RLHF refusals and potentially toxic content from airoboros-3.2. However, users should be aware that a small portion of the data might still contain sensitive content.
|
| 29 |
|
| 30 |
+
You can use the ChatML prompt format for this model.
|
| 31 |
## Limitations and Bias
|
| 32 |
|
| 33 |
While efforts have been made to clean the training data, the potential for biases and harmful content remains, as with any large language model. Users should exercise caution and discretion when utilizing the model, especially in applications that might amplify existing biases or expose users to sensitive content. The model is not recommended for scenarios requiring strict content moderation or for users without the ability to filter or assess the model's outputs critically.
|