Create Readme-ITA.md

Readme-ITA.md

@@ -0,0 +1,119 @@
+---
+license: apache-2.0
+datasets:
+- cosimoiaia/Loquace-102k
+language:
+- it
+tags:
+- Italian
+- Qlora
+- Mistral
+- finetuning
+---
+Model Card per Loquace-7B-Mistral
+
+# 🇮🇹 Loquace-7B-Mistral v0.1 🇮🇹 
+
+Loquace is an Italian speaking, instruction finetuned, Large Language model. 🇮🇹
+
+Loquace-7B-Mistral's peculiar features:
+
+- Is pretty good a following istruction in italian.
+- Responds well to prompt-engineering.
+- Works well in a RAG (Retrival Augmented Generation) setup.
+- It has been trained on a relatively raw dataset [Loquace-102K](https://huggingface.co/datasets/cosimoiaia/Loquace-102k) using QLoRa and Mistral-7B-Instruct as base.
+- Training took only 4 hours on a 3090, costing a little more than <b>1 euro</b>! On [Genesis Cloud](https://gnsiscld.co/26qhlf) GPU.
+- It is <b><i>Truly Open Source</i></b>: Model, Dataset and Code to replicate the results are completely released.
+- Created in a garage in the south of Italy.
+
+The Loquace Italian LLM models are created with the goal of democratizing AI and LLM in the Italian Landscape. 
+
+<b>No more need for expensive GPU, large funding, Big Corporation or Ivory Tower Institution, just download the code and train on your dataset on your own PC (or a cheap and reliable cloud provider like [Genesis Cloud](https://gnsiscld.co/26qhlf) )</b>
+
+### Fine-tuning Instructions:
+The related code can be found at:
+https://github.com/cosimoiaia/Loquace
+
+### GGUF Version for CPU Inference:
+8bit quantized Version of Loquace can be found [here](https://huggingface.co/cosimoiaia/Loquace-7B-Mistral-GGUF)
+
+Here is an incomplate list of clients and libraries that are known to support GGUF (thanks to [TheBloke](https://huggingface.co/TheBloke) for this list and his awesome work) ):
+
+* [llama.cpp](https://github.com/ggerganov/llama.cpp). The source project for GGUF. Offers a CLI and a server option.
+* [text-generation-webui](https://github.com/oobabooga/text-generation-webui), the most widely used web UI, with many features and powerful extensions. Supports GPU acceleration.
+* [KoboldCpp](https://github.com/LostRuins/koboldcpp), a fully featured web UI, with GPU accel across all platforms and GPU architectures. Especially good for story telling.
+* [LM Studio](https://lmstudio.ai/), an easy-to-use and powerful local GUI for Windows and macOS (Silicon), with GPU acceleration.
+* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui), a great web UI with many interesting and unique features, including a full model library for easy model selection.
+* [Faraday.dev](https://faraday.dev/), an attractive and easy to use character-based chat GUI for Windows and macOS (both Silicon and Intel), with GPU acceleration.
+* [ctransformers](https://github.com/marella/ctransformers), a Python library with GPU accel, LangChain support, and OpenAI-compatible AI server.
+* [llama-cpp-python](https://github.com/abetlen/llama-cpp-python), a Python library with GPU accel, LangChain support, and OpenAI-compatible API server.
+* [candle](https://github.com/huggingface/candle), a Rust ML framework with a focus on performance, including GPU support, and ease of use.
+
+#### Previous releases of the Loquace family:
+
+The Loquace family started in the beginning of 2023 to prove it was possible to fine-tune a Large Language model in a different language, you can find the other members of the family here:
+
+- 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
+- https://huggingface.co/cosimoiaia/Loquace-12B   -   Based on pythia-12B
+- https://huggingface.co/cosimoiaia/Loquace-20B   -   Based on gpt-neox-20B
+
+
+These model, although not producing good results, are proof that cheap finetuning is actually possible in a short amount of time, with a relaively raw dataset and extremely low resources.
+
+## Inference:
+
+```python
+from transformers import MistralForCausalLM, AutoTokenizer
+
+
+def generate_prompt(instruction):    
+   prompt = f"""### Instruction: {instruction}
+   
+### Response:
+"""
+   return prompt
+
+model_name = "."
+
+model = MistralForCausalLM.from_pretrained(
+   model_name,
+   device_map="auto",
+   torch_dtype=torch.bfloat16                
+)
+
+model.config.use_cache = True
+
+
+tokenizer = AutoTokenizer.from_pretrained(model_name, add_eos_token=False)
+
+prompt = generate_prompt("Chi era Dante Alighieri?")
+inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
+
+outputs = model.generate(**inputs, do_sample = True, num_beams = 2, top_k=50, top_p= 0.95, max_new_tokens=2046, early_stopping = True)
+print(tokenizer.decode(outputs[0], skip_special_tokens=True).split("Response:")[1].strip())
+```
+
+## Examples:
+```
+> Pretendi di essere Dante Alighieri e raccontami la tua vita.
+ Sono Dante Alighieri, un poeta e scrittore italiano del XIV secolo. Nacqui a Firenze nel 1265 e ho trascorso gran parte della mia vita viaggiando in Europa e scrivendo poesie. Ho anche scritto la Divina Commedia, una delle opere letterarie più famose di tutti i tempi.
+
+> Quanto fa 7 x 14 - 98 ?
+ 7 x 14 = 98, quindi la risposta è 0.
+
+> La radice quadrata di 144 ?
+ La radice quadrata di 144 è 12.
+
+> Inventa una ricetta pugliese con la polenta.
+ La ricetta è chiamata "Polenta al burro di arachidi e formaggio". Per prepararla, inizia bollendo la polenta secondo le istruzioni sulla confezione. Mentre la polenta si cucina, mescola insieme 1/2 tazza di burro di arachidi, 1/4 di tazza di formaggio grattugiato e 1/4 di tazza di parmigiano grattugiato. Una volta che la polenta è cotta, versala su una teglia da forno e distribuire il composto di burro di arachidi e formaggio sopra la polenta. Metti in forno a 350 gradi per 15 minuti o fino a quando la parte superiore è dorata. Servi caldo con un'insalata di pomodoro e basilico fresco.
+```
+
+## Limitations
+
+- Loquace-12B 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.
+
+## Model Author:
+Cosimo Iaia <[email protected]>