Updating model card

Changing details regarding model checkpoints

README.md

@@ -1,17 +1,15 @@
 ---
 base_model: canopylabs/3b-es_it-ft-research_release
 library_name: peft
-pipeline_tag: text-generation
-tags:
-- base_model:adapter:canopylabs/3b-es_it-ft-research_release
-- lora
-- transformers
-- unsloth
+datasets:
+- freds0/BRSpeech-TTS-Leni
+language:
+- pt
 ---
 
 # Model Card for Model ID
 
-<!-- Provide a quick summary of what the model is/does. -->
+Unsloth's Orpheus Fine-Tune on freds0/BRSpeech-Leni Dataset
 
 
 
@@ -19,17 +17,19 @@ tags:
 
 ### Model Description
 
-<!-- Provide a longer summary of what this model is. -->
+These are adapter (LoRA) files resulting from the checkpoint n. 1800 of the fine-tune process of Canopy Lab's Orpheus 3b TTS es/it FT model on a Brazilian Portuguese dataset (freds0/BRSpeech-Leni) using Unsloth's notebook.
 
+They may be used for inference or continued training, although results are still not yielding intended accuracy/naturality.
 
+Recommendations are to either use a third-party inference provider for inexpensive testing (eg. HuggingFace itself), or download and continue training following Unsloth's scripts and instructions.
 
-- **Developed by:** [More Information Needed]
-- **Funded by [optional]:** [More Information Needed]
+- **Developed by:** J. Arthur Quintieri De Toledo (ArtooDtoo) - fine-tuning and adapting
+- **Funded by [optional]:** Co-Human
 - **Shared by [optional]:** [More Information Needed]
-- **Model type:** [More Information Needed]
-- **Language(s) (NLP):** [More Information Needed]
+- **Model type:** TTS
+- **Language(s) (NLP):** Brazilian Portuguese
 - **License:** [More Information Needed]
-- **Finetuned from model [optional]:** [More Information Needed]
+- **Finetuned from model [optional]:** Orpheus 3b Es/It Fine-Tuned (canopylabs/3b-es_it-ft-research_release)
 
 ### Model Sources [optional]
 
@@ -89,7 +89,7 @@ Use the code below to get started with the model.
 
 ### Training Procedure
 
-<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+Unsloth's notebook, available at https://colab.research.google.com/github/unslothai/notebooks/blob/main/nb/Orpheus_(3B)-TTS.ipynb
 
 #### Preprocessing [optional]
 
@@ -205,4 +205,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
 
-- PEFT 0.16.0
+- PEFT 0.15.2