Create README.md

README.md

@@ -0,0 +1,55 @@
+---
+language:
+- el
+- en
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- finetuned
+inference: true
+base_model:
+- ilsp/Meltemi-7B-Instruct-v1.5
+---
+
+# Meltemi 7B Instruct v1.5 gguf
+
+This is [Meltemi 7B Instract v1.5](https://huggingface.co/ilsp/Meltemi-7B-Instruct-v1.5) published in `gguf`, [llama.cpp](https://github.com/ggerganov/llama.cpp)-compatible format.
+
+Meltemi is the first Greek Large Language Model (LLM) trained by the [Institute for Language and Speech Processing](https://www.athenarc.gr/en/ilsp) at [Athena Research & Innovation Center](https://www.athenarc.gr/en).
+Meltemi is built on top of [Mistral-7B-Instruct](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.1), extending its capabilities for Greek through continual pretraining on a large corpus of high-quality and locally relevant Greek texts.
+
+
+# Model Information
+
+- Vocabulary extension of the Mistral 7b tokenizer with Greek tokens for lower costs and faster inference (**1.52** vs. 6.80 tokens/word for Greek)
+- 8192 context length
+- Fine-tuning has been done with the [Odds Ratio Preference Optimization (ORPO)](https://arxiv.org/abs/2403.07691) algorithm using 97k preference data:
+  * 89,730 Greek preference data which are mostly translated versions of high-quality datasets on Hugging Face 
+  * 7,342 English preference data 
+- Our alignment procedure is based on the [TRL - Transformer Reinforcement Learning](https://huggingface.co/docs/trl/index) library and partially on the [Hugging Face finetuning recipes](https://github.com/huggingface/alignment-handbook)
+
+
+# Instruction format
+
+You can do whatever you can with a standard [llama.cpp](https://github.com/ggerganov/llama.cpp) model
+
+## Basic Usage
+
+```shell
+llama-cli -m ./Meltemi-7B-Instruct-v1.5-F16.gguf -p "Ποιό είναι το νόημα της ζωής;" -n 128
+```
+
+## Conversation Mode
+
+```shell
+llama-cli -m ./Meltemi-7B-Instruct-v1.5-F16.gguf --conv 
+```
+
+## Web Server
+
+```shell
+llama-server -m ./Meltemi-7B-Instruct-v1.5-F16.gguf --port 8080
+```
+
+
+For more details please refer to the original model https://huggingface.co/ilsp/Meltemi-7B-Instruct-v1.5