Quantization made by Richard Erkhov.

[Github](https://github.com/RichardErkhov)

[Discord](https://discord.gg/pvy7H8DZMG)

[Request more models](https://github.com/RichardErkhov/quant_request)


RoLlama2-7b-Instruct - GGUF
- Model creator: https://huggingface.co/OpenLLM-Ro/
- Original model: https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct/


| Name | Quant method | Size |
| ---- | ---- | ---- |
| [RoLlama2-7b-Instruct.Q2_K.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q2_K.gguf) | Q2_K | 2.36GB |
| [RoLlama2-7b-Instruct.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.IQ3_XS.gguf) | IQ3_XS | 2.6GB |
| [RoLlama2-7b-Instruct.IQ3_S.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.IQ3_S.gguf) | IQ3_S | 2.75GB |
| [RoLlama2-7b-Instruct.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q3_K_S.gguf) | Q3_K_S | 2.75GB |
| [RoLlama2-7b-Instruct.IQ3_M.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.IQ3_M.gguf) | IQ3_M | 2.9GB |
| [RoLlama2-7b-Instruct.Q3_K.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q3_K.gguf) | Q3_K | 3.07GB |
| [RoLlama2-7b-Instruct.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q3_K_M.gguf) | Q3_K_M | 3.07GB |
| [RoLlama2-7b-Instruct.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q3_K_L.gguf) | Q3_K_L | 3.35GB |
| [RoLlama2-7b-Instruct.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.IQ4_XS.gguf) | IQ4_XS | 3.4GB |
| [RoLlama2-7b-Instruct.Q4_0.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q4_0.gguf) | Q4_0 | 3.56GB |
| [RoLlama2-7b-Instruct.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.IQ4_NL.gguf) | IQ4_NL | 3.58GB |
| [RoLlama2-7b-Instruct.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q4_K_S.gguf) | Q4_K_S | 3.59GB |
| [RoLlama2-7b-Instruct.Q4_K.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q4_K.gguf) | Q4_K | 3.8GB |
| [RoLlama2-7b-Instruct.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q4_K_M.gguf) | Q4_K_M | 3.8GB |
| [RoLlama2-7b-Instruct.Q4_1.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q4_1.gguf) | Q4_1 | 3.95GB |
| [RoLlama2-7b-Instruct.Q5_0.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q5_0.gguf) | Q5_0 | 4.33GB |
| [RoLlama2-7b-Instruct.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q5_K_S.gguf) | Q5_K_S | 4.33GB |
| [RoLlama2-7b-Instruct.Q5_K.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q5_K.gguf) | Q5_K | 4.45GB |
| [RoLlama2-7b-Instruct.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q5_K_M.gguf) | Q5_K_M | 4.45GB |
| [RoLlama2-7b-Instruct.Q5_1.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q5_1.gguf) | Q5_1 | 4.72GB |
| [RoLlama2-7b-Instruct.Q6_K.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q6_K.gguf) | Q6_K | 5.15GB |
| [RoLlama2-7b-Instruct.Q8_0.gguf](https://huggingface.co/RichardErkhov/OpenLLM-Ro_-_RoLlama2-7b-Instruct-gguf/blob/main/RoLlama2-7b-Instruct.Q8_0.gguf) | Q8_0 | 6.67GB |




Original model description:
---
license: cc-by-nc-4.0
language:
- ro
---

# Model Card for Model ID

<!-- Provide a quick summary of what the model is/does. -->

RoLlama2 is a family of pretrained and fine-tuned generative text models for Romanian. This is the repository for the **instruct 7B model**. Links to other models can be found at the bottom of this page.

## Model Details

### Model Description

<!-- Provide a longer summary of what this model is. -->
OpenLLM represents the first open-source effort to build a LLM specialized for Romanian. OpenLLM-Ro developed and publicly releases a collection of Romanian LLMs, both in the form of foundational model and instruct and chat variants.


- **Developed by:** OpenLLM-Ro
<!-- - **Funded by [optional]:** [More Information Needed] -->
<!-- - **Shared by [optional]:** [More Information Needed] -->
<!-- - **Model type:** [More Information Needed] -->
- **Language(s):** Romanian
- **License:** cc-by-nc-4.0
- **Finetuned from model:** [RoLlama2-7b-Base](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Base)


### Model Sources

<!-- Provide the basic links for the model. -->

- **Repository:** https://github.com/OpenLLM-Ro/llama-recipes
- **Paper:** https://arxiv.org/abs/2406.18266

## Intended Use

### Intended Use Cases

RoLlama2 is intented for research use in Romanian. Base models can be adapted for a variety of natural language tasks while instruction and chat tuned models are intended for assistant-like chat.

### Out-of-Scope Use

<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->

Use in any manner that violates the license, any applicable laws or regluations, use in languages other than Romanian.



## How to Get Started with the Model

Use the code below to get started with the model.

```python
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("OpenLLM-Ro/RoLlama2-7b-Instruct")
model = AutoModelForCausalLM.from_pretrained("OpenLLM-Ro/RoLlama2-7b-Instruct")

instruction = "Care este cel mai înalt vârf muntos din România?"
chat = [
        {"role": "system", "content": "Ești un asistent folositor, respectuos și onest. Încearcă să ajuți cât mai mult prin informațiile oferite, excluzând răspunsuri toxice, rasiste, sexiste, periculoase și ilegale."},
        {"role": "user", "content": instruction},
        ]
prompt = tokenizer.apply_chat_template(chat, tokenize=False)

inputs = tokenizer.encode(prompt, add_special_tokens=False, return_tensors="pt")
outputs = model.generate(input_ids=inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0]))
```

## Benchmarks

| Model              | Average  | ARC      | MMLU     |Winogrande|HellaSwag | GSM8k    |TruthfulQA|
|--------------------|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|:--------:|
| Llama-2-7b-chat    | 38.03    | 37.95    | 27.22    | 59.29    | 57.22    | 2.53     | 44.00    |  
|*RoLlama2-7b-Instruct*|***45.71***|***43.66***|***39.70***|***70.34*** | *57.36*  |***18.78***| *44.44*    |  
|RoLlama2-7b-Chat    | 43.82    | 41.92    | 37.29    | 66.68    | **57.91**| 13.47    | **45.65**|  


                                  

## MT-Bench


| Model              | Average  | 1st turn      | 2nd turn     | Answers in Ro |
|--------------------|:--------:|:--------:|:--------:|:--------:|
| Llama-2-7b-chat    | 1.21    | 1.68    | 0.74    | 44 / 160 |
|*RoLlama2-7b-Instruct*| ***3.70***|***4.74***| ***2.66*** | ***160 / 160*** |
|RoLlama2-7b-Chat    | TBC    | TBC    | TBC    | TBC |

## RoCulturaBench

| Model              | Score  | Answers in Ro|
|--------------------|:--------:|:--------:|
| Llama-2-7b-chat    | 1.72    | 48 / 100   |
|*RoLlama2-7b-Instruct*| ***3.43***| ***160 / 160*** |
|RoLlama2-7b-Chat    | TBC    | TBC    |



## RoLlama2 Model Family

| Model              | Link  |
|--------------------|:--------:|
|RoLlama2-7b-Base | [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Base)    |
|*RoLlama2-7b-Instruct*| [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Instruct) |
|RoLlama2-7b-Chat    | [link](https://huggingface.co/OpenLLM-Ro/RoLlama2-7b-Chat) |


## Citation 

```
@misc{masala2024vorbecstiromanecsterecipetrain,
      title={"Vorbe\c{s}ti Rom\^ane\c{s}te?" A Recipe to Train Powerful Romanian LLMs with English Instructions}, 
      author={Mihai Masala and Denis C. Ilie-Ablachim and Alexandru Dima and Dragos Corlatescu and Miruna Zavelca and Ovio Olaru and Simina Terian-Dan and Andrei Terian-Dan and Marius Leordeanu and Horia Velicu and Marius Popescu and Mihai Dascalu and Traian Rebedea},
      year={2024},
      eprint={2406.18266},
      archivePrefix={arXiv},
      primaryClass={cs.CL},
      url={https://arxiv.org/abs/2406.18266}, 
}
```
<!-- **APA:**

[More Information Needed]  -->