uploaded readme

README.md

@@ -0,0 +1,176 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+Meltemi-7B-Instruct-v1.5 - GGUF
+- Model creator: https://huggingface.co/ilsp/
+- Original model: https://huggingface.co/ilsp/Meltemi-7B-Instruct-v1.5/
+
+
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [Meltemi-7B-Instruct-v1.5.Q2_K.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q2_K.gguf) | Q2_K | 2.66GB |
+| [Meltemi-7B-Instruct-v1.5.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.IQ3_XS.gguf) | IQ3_XS | 2.95GB |
+| [Meltemi-7B-Instruct-v1.5.IQ3_S.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.IQ3_S.gguf) | IQ3_S | 3.1GB |
+| [Meltemi-7B-Instruct-v1.5.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q3_K_S.gguf) | Q3_K_S | 0.98GB |
+| [Meltemi-7B-Instruct-v1.5.IQ3_M.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.IQ3_M.gguf) | IQ3_M | 3.2GB |
+| [Meltemi-7B-Instruct-v1.5.Q3_K.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q3_K.gguf) | Q3_K | 3.42GB |
+| [Meltemi-7B-Instruct-v1.5.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q3_K_M.gguf) | Q3_K_M | 3.42GB |
+| [Meltemi-7B-Instruct-v1.5.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q3_K_L.gguf) | Q3_K_L | 3.7GB |
+| [Meltemi-7B-Instruct-v1.5.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.IQ4_XS.gguf) | IQ4_XS | 3.58GB |
+| [Meltemi-7B-Instruct-v1.5.Q4_0.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q4_0.gguf) | Q4_0 | 3.98GB |
+| [Meltemi-7B-Instruct-v1.5.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.IQ4_NL.gguf) | IQ4_NL | 0.25GB |
+| [Meltemi-7B-Instruct-v1.5.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q4_K_S.gguf) | Q4_K_S | 0.0GB |
+| [Meltemi-7B-Instruct-v1.5.Q4_K.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q4_K.gguf) | Q4_K | 0.0GB |
+| [Meltemi-7B-Instruct-v1.5.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q4_K_M.gguf) | Q4_K_M | 4.22GB |
+| [Meltemi-7B-Instruct-v1.5.Q4_1.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q4_1.gguf) | Q4_1 | 4.4GB |
+| [Meltemi-7B-Instruct-v1.5.Q5_0.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q5_0.gguf) | Q5_0 | 4.82GB |
+| [Meltemi-7B-Instruct-v1.5.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q5_K_S.gguf) | Q5_K_S | 0.87GB |
+| [Meltemi-7B-Instruct-v1.5.Q5_K.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q5_K.gguf) | Q5_K | 0.68GB |
+| [Meltemi-7B-Instruct-v1.5.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q5_K_M.gguf) | Q5_K_M | 4.95GB |
+| [Meltemi-7B-Instruct-v1.5.Q5_1.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q5_1.gguf) | Q5_1 | 5.25GB |
+| [Meltemi-7B-Instruct-v1.5.Q6_K.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q6_K.gguf) | Q6_K | 2.12GB |
+| [Meltemi-7B-Instruct-v1.5.Q8_0.gguf](https://huggingface.co/RichardErkhov/ilsp_-_Meltemi-7B-Instruct-v1.5-gguf/blob/main/Meltemi-7B-Instruct-v1.5.Q8_0.gguf) | Q8_0 | 0.54GB |
+
+
+
+
+Original model description:
+---
+language:
+- el
+- en
+license: apache-2.0
+pipeline_tag: text-generation
+tags:
+- finetuned
+inference: true
+---
+
+# Meltemi Instruct Large Language Model for the Greek language
+
+We present Meltemi 7B Instruct v1.5 Large Language Model (LLM), a new and improved instruction fine-tuned version of [Meltemi 7B v1.5](https://huggingface.co/ilsp/Meltemi-7B-v1.5).
+
+![image/png](https://miro.medium.com/v2/resize:fit:720/format:webp/1*IaE7RJk6JffW8og-MOnYCA.png)
+
+# 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
+The prompt format is the same as the [Zephyr](https://huggingface.co/HuggingFaceH4/zephyr-7b-beta) format and can be
+utilized through the tokenizer's [chat template](https://huggingface.co/docs/transformers/main/chat_templating) functionality as follows:
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+device = "cuda" # the device to load the model onto
+
+model = AutoModelForCausalLM.from_pretrained("ilsp/Meltemi-7B-Instruct-v1.5")
+tokenizer = AutoTokenizer.from_pretrained("ilsp/Meltemi-7B-Instruct-v1.5")
+
+model.to(device)
+
+messages = [
+    {"role": "system", "content": "Είσαι το Μελτέμι, ένα γλωσσικό μοντέλο για την ελληνική γλώσσα. Είσαι ιδιαίτερα βοηθητικό προς την χρήστρια ή τον χρήστη και δίνεις σύντομες αλλά επαρκώς περιεκτικές απαντήσεις. Απάντα με προσοχή, ευγένεια, αμεροληψία, ειλικρίνεια και σεβασμό προς την χρήστρια ή τον χρήστη."},
+    {"role": "user", "content": "Πες μου αν έχεις συνείδηση."},
+]
+
+# Through the default chat template this translates to
+#
+# <|system|>
+# Είσαι το Μελτέμι, ένα γλωσσικό μοντέλο για την ελληνική γλώσσα. Είσαι ιδιαίτερα βοηθητικό προς την χρήστρια ή τον χρήστη και δίνεις σύντομες αλλά επαρκώς περιεκτικές απαντήσεις. Απάντα με προσοχή, ευγένεια, αμεροληψία, ειλικρίνεια και σεβασμό προς την χρήστρια ή τον χρήστη.</s>
+# <|user|>
+# Πες μου αν έχεις συνείδηση.</s>
+# <|assistant|>
+#
+
+prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
+input_prompt = tokenizer(prompt, return_tensors='pt').to(device)
+outputs = model.generate(input_prompt['input_ids'], max_new_tokens=256, do_sample=True)
+
+print(tokenizer.batch_decode(outputs)[0])
+# Ως μοντέλο γλώσσας AI, δεν έχω τη δυνατότητα να αντιληφθώ ή να βιώσω συναισθήματα όπως η συνείδηση ή η επίγνωση. Ωστόσο, μπορώ να σας βοηθήσω με οποιεσδήποτε ερωτήσεις μπορεί να έχετε σχετικά με την τεχνητή νοημοσύνη και τις εφαρμογές της.
+
+messages.extend([
+    {"role": "assistant", "content": tokenizer.batch_decode(outputs)[0]},
+    {"role": "user", "content": "Πιστεύεις πως οι άνθρωποι πρέπει να φοβούνται την τεχνητή νοημοσύνη;"}
+])
+
+# Through the default chat template this translates to
+#
+# <|system|>
+# Είσαι το Μελτέμι, ένα γλωσσικό μοντέλο για την ελληνική γλώσσα. Είσαι ιδιαίτερα βοηθητικό προς την χρήστρια ή τον χρήστη και δίνεις σύντομες αλλά επαρκώς περιεκτικές απαντήσεις. Απάντα με προσοχή, ευγένεια, αμεροληψία, ειλικρίνεια και σεβασμό προς την χρήστρια ή τον χρήστη.</s>
+# <|user|>
+# Πες μου αν έχεις συνείδηση.</s>
+# <|assistant|>
+# Ως μοντέλο γλώσσας AI, δεν έχω τη δυνατότητα να αντιληφθώ ή να βιώσω συναισθήματα όπως η συνείδηση ή η επίγνωση. Ωστόσο, μπορώ να σας βοηθήσω με οποιεσδήποτε ερωτήσεις μπορεί να έχετε σχετικά με την τεχνητή νοημοσύνη και τις εφαρμογές της.</s>
+# <|user|>
+# Πιστεύεις πως οι άνθρωποι πρέπει να φοβούνται την τεχνητή νοημοσύνη;</s>
+# <|assistant|>
+#
+
+prompt = tokenizer.apply_chat_template(messages, add_generation_prompt=True, tokenize=False)
+input_prompt = tokenizer(prompt, return_tensors='pt').to(device)
+outputs = model.generate(input_prompt['input_ids'], max_new_tokens=256, do_sample=True)
+
+print(tokenizer.batch_decode(outputs)[0])
+```
+
+Please make sure that the BOS token is always included in the tokenized prompts. This might not be the default setting in all evaluation or fine-tuning frameworks.
+
+# Evaluation
+
+The evaluation suite we created includes 6 test sets and has been implemented based on a [fork](https://github.com/LeonVouk/lighteval) of the  [lighteval](https://github.com/huggingface/lighteval) framework.
+
+Our evaluation suite includes: 
+* Four machine-translated versions ([ARC Greek](https://huggingface.co/datasets/ilsp/arc_greek), [Truthful QA Greek](https://huggingface.co/datasets/ilsp/truthful_qa_greek), [HellaSwag Greek](https://huggingface.co/datasets/ilsp/hellaswag_greek), [MMLU Greek](https://huggingface.co/datasets/ilsp/mmlu_greek)) of established English benchmarks for language understanding and reasoning ([ARC Challenge](https://arxiv.org/abs/1803.05457), [Truthful QA](https://arxiv.org/abs/2109.07958), [Hellaswag](https://arxiv.org/abs/1905.07830), [MMLU](https://arxiv.org/abs/2009.03300)). 
+* An existing benchmark for question answering in Greek ([Belebele](https://arxiv.org/abs/2308.16884))
+* A novel benchmark created by the ILSP team for medical question answering based on the medical exams of [DOATAP](https://www.doatap.gr) ([Medical MCQA](https://huggingface.co/datasets/ilsp/medical_mcqa_greek)).
+
+Our evaluation is performed in a few-shot setting, consistent with the settings in the [Open LLM leaderboard](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard).
+
+We can see that our new training and fine-tuning procedure for Meltemi 7B Instruct v1.5 enhances performance across all Greek test sets by a **+7.8%** average improvement compared to the earlier Meltemi Instruct 7B v1 model. The results for the Greek test sets are shown in the following table:
+
+|                | Medical MCQA EL (15-shot) | Belebele EL (5-shot) | HellaSwag EL (10-shot) | ARC-Challenge EL (25-shot) | TruthfulQA MC2 EL (0-shot) | MMLU EL (5-shot) | **Average** |
+|----------------|----------------|-------------|--------------|------------------|-------------------|---------|---------|
+| Mistral 7B     | 29.8%          | 45.0%       | 36.5%        | 27.1%            | 45.8%             | 35%     | **36.5%**   |
+| Meltemi 7B Instruct v1     | 36.1%          | 56.0%       | 59.0%        | 44.4%            | 51.1%             | 34.1%     | **46.8%**   |
+| Meltemi 7B Instruct v1.5     | 48.0%          | 75.5%       | 63.7%        | 40.8%            | 53.8%             | 45.9%     | **54.6%**   |
+
+
+# Ethical Considerations
+
+This model has been aligned with human preferences, but might generate misleading, harmful, and toxic content.
+
+
+# Acknowledgements
+
+The ILSP team utilized Amazon’s cloud computing services, which were made available via GRNET under the [OCRE Cloud framework](https://www.ocre-project.eu/), providing Amazon Web Services for the Greek Academic and Research Community. 
+
+
+# Citation
+
+```
+@misc{voukoutis2024meltemiopenlargelanguage,
+      title={Meltemi: The first open Large Language Model for Greek}, 
+      author={Leon Voukoutis and Dimitris Roussis and Georgios Paraskevopoulos and Sokratis Sofianopoulos and Prokopis Prokopidis and Vassilis Papavasileiou and Athanasios Katsamanis and Stelios Piperidis and Vassilis Katsouros},
+      year={2024},
+      eprint={2407.20743},
+      archivePrefix={arXiv},
+      primaryClass={cs.CL},
+      url={https://arxiv.org/abs/2407.20743}, 
+}
+```
+