Update README.md

README.md

@@ -4,5 +4,70 @@ datasets:
 - cosimoiaia/Loquace-102k
 language:
 - it
-library_name: adapter-transformers
----
+pipeline_tag: conversational
+tags:
+- alpaca
+- llama
+- llm
+- finetune
+- Italian
+- qlora
+---
+
+Model Card for Loquace-410m
+
+# 🇮🇹 Loquace 🇮🇹 
+
+An exclusively Italian speaking, instruction finetuned, Large Language model. 🇮🇹
+
+## Model Description
+
+Loquace-410m is the smallest model of the Loquace family. It was trained using QLoRa on a large dataset of 102k question/answer pairs
+exclusively in Italian.
+
+The related code can be found at: https://github.com/cosimoiaia/Loquace
+
+Loquace-410m is part of the big Loquace family:
+
+https://huggingface.co/cosimoiaia/Loquace-70m   -   Based on pythia-70m
+https://huggingface.co/cosimoiaia/Loquace-410m  -   Based on pythia-410m
+https://huggingface.co/cosimoiaia/Loquace-7B    -   Based on Falcon-7B, the most performing model of it's class.
+https://huggingface.co/cosimoiaia/Loquace-12B   -   Based on pythia-12B
+https://huggingface.co/cosimoiaia/Loquace-20B   -   Based on gpt-neox-20B
+
+
+
+## Usage
+
+
+```python
+from peft import PeftModel
+from transformers import LLaMATokenizer, LLaMAForCausalLM, GenerationConfig
+
+tokenizer = LLaMATokenizer.from_pretrained("cosimoiaia/Loquace-410m")
+model = LLaMAForCausalLM.from_pretrained(
+    "cosimoiaia/Loquace-410m",
+    load_in_8bit=True,
+    device_map="auto",
+)
+```
+
+
+## Training
+
+Loquace-410m was trained on a conversational dataset comprising 102k question/answer pairs in Italian language. 
+The training data was constructed by putting together translations from the original alpaca Dataset and other sources like the OpenAssistant dataset.
+The model was trained for only 3000 iterations and took 18 hours on a single RTX 3090, kindly provided by Genesis Cloud.
+
+## Limitations
+
+- Loquace-410m may not handle complex or nuanced queries well and may struggle with ambiguous or poorly formatted inputs.
+- The model may generate responses that are factually incorrect or nonsensical. It should be used with caution, and outputs should be carefully verified.
+- The training data primarily consists of conversational examples and may not generalize well to other types of tasks or domains.
+
+## Dependencies
+
+- PyTorch
+- Transformers library by Hugging Face
+- Bitsandbites
+- QLoRa