Duplicate from RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf

.gitattributes

@@ -0,0 +1,57 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+suzume-llama-3-8B-multilingual-orpo-borda-top25.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,262 @@
+Quantization made by Richard Erkhov.
+
+[Github](https://github.com/RichardErkhov)
+
+[Discord](https://discord.gg/pvy7H8DZMG)
+
+[Request more models](https://github.com/RichardErkhov/quant_request)
+
+
+suzume-llama-3-8B-multilingual-orpo-borda-top25 - GGUF
+- Model creator: https://huggingface.co/lightblue/
+- Original model: https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25/
+
+
+| Name | Quant method | Size |
+| ---- | ---- | ---- |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q2_K.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q2_K.gguf) | Q2_K | 2.96GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ3_XS.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ3_XS.gguf) | IQ3_XS | 3.28GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ3_S.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ3_S.gguf) | IQ3_S | 3.43GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K_S.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K_S.gguf) | Q3_K_S | 3.41GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ3_M.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ3_M.gguf) | IQ3_M | 3.52GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K.gguf) | Q3_K | 3.74GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K_M.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K_M.gguf) | Q3_K_M | 3.74GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K_L.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K_L.gguf) | Q3_K_L | 4.03GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ4_XS.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ4_XS.gguf) | IQ4_XS | 4.18GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_0.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_0.gguf) | Q4_0 | 4.34GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ4_NL.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ4_NL.gguf) | IQ4_NL | 4.38GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_K_S.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_K_S.gguf) | Q4_K_S | 4.37GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_K.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_K.gguf) | Q4_K | 4.58GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_K_M.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_K_M.gguf) | Q4_K_M | 4.58GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_1.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_1.gguf) | Q4_1 | 4.78GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_0.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_0.gguf) | Q5_0 | 5.21GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_K_S.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_K_S.gguf) | Q5_K_S | 5.21GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_K.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_K.gguf) | Q5_K | 5.34GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_K_M.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_K_M.gguf) | Q5_K_M | 5.34GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_1.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_1.gguf) | Q5_1 | 5.65GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q6_K.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q6_K.gguf) | Q6_K | 6.14GB |
+| [suzume-llama-3-8B-multilingual-orpo-borda-top25.Q8_0.gguf](https://huggingface.co/RichardErkhov/lightblue_-_suzume-llama-3-8B-multilingual-orpo-borda-top25-gguf/blob/main/suzume-llama-3-8B-multilingual-orpo-borda-top25.Q8_0.gguf) | Q8_0 | 7.95GB |
+
+
+
+
+Original model description:
+---
+license: cc-by-nc-4.0
+tags:
+- generated_from_trainer
+base_model: lightblue/suzume-llama-3-8B-multilingual
+model-index:
+- name: workspace/llm_training/axolotl/llama3-multilingual-orpo/output_mitsu_top25_borda
+  results: []
+---
+
+# Suzume ORPO
+
+<p align="center">
+  <img width=500 src="https://cdn-uploads.huggingface.co/production/uploads/64b63f8ad57e02621dc93c8b/kWQSu02YfgYdUQqv4s5lq.png" alt="Suzume with Mitsu - a Japanese tree sparrow with honey on it"/>
+</p>
+
+[[Paper]](https://arxiv.org/abs/2405.18952) [[Dataset]](https://huggingface.co/datasets/lightblue/mitsu)
+
+This is Suzume ORPO, an ORPO trained fine-tune of the [lightblue/suzume-llama-3-8B-multilingual](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual) model using our [lightblue/mitsu](https://huggingface.co/datasets/lightblue/mitsu) dataset.
+
+We have trained several versions of this model using ORPO and so recommend that you use the best performing model from our tests, [lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half).
+
+Note that this model has a non-commerical license as we used the Command R and Command R+ models to generate our training data for this model ([lightblue/mitsu](https://huggingface.co/datasets/lightblue/mitsu)).
+
+We are currently working on a developing a commerically usable model, so stay tuned for that!
+
+# Model list
+
+We have ORPO trained the following models using different proportions of the [lightblue/mitsu](https://huggingface.co/datasets/lightblue/mitsu) dataset:
+* Trained on the top/bottom responses of all prompts in the dataset: [lightblue/suzume-llama-3-8B-multilingual-orpo-borda-full](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-orpo-borda-full)
+* Trained on the top/bottom responses of the prompts of the 75\% most consistently ranked responses in the dataset: [lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top75](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top75)
+* Trained on the top/bottom responses of the prompts of the 50\% most consistently ranked responses in the dataset: [lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half)
+* Trained on the top/bottom responses of the prompts of the 25\% most consistently ranked responses in the dataset: [lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25)
+
+# Model results
+
+We compare the MT-Bench scores across 6 languages for our 4 ORPO trained models, as well as some baselines:
+
+* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) - The foundation model that our models are ultimately built upon
+* [Nexusflow/Starling-LM-7B-beta](https://huggingface.co/Nexusflow/Starling-LM-7B-beta) - The highest performing open model on the Chatbot arena that is of a similar size to ours
+* gpt-3.5-turbo - A fairly high quality (although not state-of-the-art) proprietary LLM
+* [lightblue/suzume-llama-3-8B-multilingual](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual) - The base model which we train our ORPO finetunes from
+
+| **MT-Bench language** | **meta-llama/Meta-Llama-3-8B-Instruct** | **Nexusflow/Starling-LM-7B-beta** | **gpt-3.5-turbo** | **lightblue/suzume-llama-3-8B-multilingual** | **lightblue/suzume-llama-3-8B-multilingual-orpo-borda-full** | **lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top75** | **lightblue/suzume-llama-3-8B-multilingual-orpo-borda-half** | **lightblue/suzume-llama-3-8B-multilingual-orpo-borda-top25** |
+|-----------------------|-----------------------------------------|-----------------------------------|-------------------|----------------------------------------------|--------------------------------------------------------------|---------------------------------------------------------------|--------------------------------------------------------------|---------------------------------------------------------------|
+| **Chinese 🇨🇳**        | NaN                                     | 6.97                              | 7.55              | 7.11                                         | 7.65                                                         | **7.77**                                                      | 7.74                                                         | 7.44                                                          |
+| **English 🇺🇸**        | 7.98                                    | 7.92                              | **8.26**          | 7.73                                         | 7.98                                                         | 7.94                                                          | 7.98                                                         | 8.22                                                          |
+| **French 🇫🇷**         | NaN                                     | 7.29                              | 7.74              | 7.66                                         | **7.84**                                                     | 7.46                                                          | 7.78                                                         | 7.81                                                          |
+| **German 🇩🇪**         | NaN                                     | 6.99                              | 7.68              | 7.26                                         | 7.28                                                         | 7.64                                                          | 7.7                                                          | **7.71**                                                      |
+| **Japanese 🇯🇵**       | NaN                                     | 6.22                              | **7.84**          | 6.56                                         | 7.2                                                          | 7.12                                                          | 7.34                                                         | 7.04                                                          |
+| **Russian 🇷🇺**        | NaN                                     | 8.28                              | 7.94              | 8.19                                         | 8.3                                                          | 8.74                                                          | **8.94**                                                     | 8.81                                                          |
+
+We can see noticable improvement on most languages compared to the base model. We also find that our ORPO models achieve the highest score out of all the models we evaluated for a number of languages.
+
+# Training data
+
+We trained this model using the [lightblue/mitsu_full_borda](https://huggingface.co/datasets/lightblue/mitsu_full_borda) dataset.
+
+# Training configuration
+
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: lightblue/suzume-llama-3-8B-multilingual
+model_type: LlamaForCausalLM
+tokenizer_type: AutoTokenizer  # PreTrainedTokenizerFast
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+rl: orpo
+orpo_alpha: 0.1
+remove_unused_columns: false
+
+chat_template: chatml
+datasets:
+  - path: lightblue/mitsu_top25_borda
+    type: orpo.chat_template
+    conversation: llama-3
+dataset_prepared_path: /workspace/llm_training/axolotl/llama3-multilingual-orpo/prepared_mitsu_top25_borda
+val_set_size: 0.02
+output_dir: /workspace/llm_training/axolotl/llama3-multilingual-orpo/output_mitsu_top25_borda
+
+sequence_len: 8192
+sample_packing: false
+pad_to_sequence_len: true
+
+use_wandb: true
+wandb_project: axolotl
+wandb_entity: peterd
+wandb_name: mitsu_top25_borda
+
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+num_epochs: 1
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 8e-6
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 10
+evals_per_epoch: 20
+eval_table_size:
+saves_per_epoch: 1
+debug:
+deepspeed: /workspace/axolotl/deepspeed_configs/zero3_bf16.json
+weight_decay: 0.0
+special_tokens:
+  pad_token: <|end_of_text|>
+```
+
+</details><br>
+
+# workspace/llm_training/axolotl/llama3-multilingual-orpo/output_mitsu_top25_borda
+
+This model is a fine-tuned version of [lightblue/suzume-llama-3-8B-multilingual](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.0818
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 8e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 7.6328        | 0.05  | 1    | 7.7812          |
+| 7.7158        | 0.1   | 2    | 7.2589          |
+| 7.2588        | 0.15  | 3    | 4.0580          |
+| 4.0068        | 0.19  | 4    | 2.4598          |
+| 2.4438        | 0.24  | 5    | 0.6504          |
+| 0.6586        | 0.29  | 6    | 0.1129          |
+| 0.1235        | 0.34  | 7    | 0.1066          |
+| 0.1273        | 0.39  | 8    | 0.1041          |
+| 0.1076        | 0.44  | 9    | 0.0987          |
+| 0.1009        | 0.48  | 10   | 0.0940          |
+| 0.1172        | 0.53  | 11   | 0.0885          |
+| 0.1016        | 0.58  | 12   | 0.0867          |
+| 0.1088        | 0.63  | 13   | 0.0859          |
+| 0.095         | 0.68  | 14   | 0.0846          |
+| 0.1101        | 0.73  | 15   | 0.0839          |
+| 0.0969        | 0.78  | 16   | 0.0832          |
+| 0.0864        | 0.82  | 17   | 0.0825          |
+| 0.0918        | 0.87  | 18   | 0.0821          |
+| 0.0927        | 0.92  | 19   | 0.0819          |
+| 0.0967        | 0.97  | 20   | 0.0818          |
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.1+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.0
+
+# How to cite
+
+```tex
+@article{devine2024sure,
+  title={Are You Sure? Rank Them Again: Repeated Ranking For Better Preference Datasets},
+  author={Devine, Peter},
+  journal={arXiv preprint arXiv:2405.18952},
+  year={2024}
+}
+```
+
+# Developer
+
+Peter Devine - ([ptrdvn](https://huggingface.co/ptrdvn))
+

suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3610c3b75d5887706d8044c382cdf55489493b522fac8c22e6c0d48bbcd16e76
+size 3784823104

suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba1579ec726b738a1638d53ba0b2e14c7db4890f7f519bc89d9206f11bc414c6
+size 3682324800

suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ3_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be656f0d4c21ac1a0e895c2b540e52398dbcd73f0198b9e86febf9997c04d366
+size 3518746944

suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7991fd01d1c5e73df8b0116618031be96f550c9ed067381fffc3d3ecdb18cbf1
+size 4707348800

suzume-llama-3-8B-multilingual-orpo-borda-top25.IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e12674c6fb5a3d880d1bb737c53aa8692d28ebb1ff85ae0ccac700fd8fdad974
+size 4484362560

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c5efaecc41f53102bb623f81b625e72e7e77d4dc52c0a33b00a60659d9963db7
+size 3179131200

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fefe4236ff93ba7ebe721197eeaff65c7f564b7bafa006617ac3f80174a67ad
+size 4018917696

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6eeecb0ac09054b3c7139ea07fdd619e92b4b16851cb43b45fc6bd1fc8721ba5
+size 4321956160

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fefe4236ff93ba7ebe721197eeaff65c7f564b7bafa006617ac3f80174a67ad
+size 4018917696

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:855cf22ce472262942b559a84f71e372798964f14e8d0e58c4743ca838656c04
+size 3664499008

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c95c052466dc4c9ef13747909f03a7aa363f7f9c82b4a79c4ac19d1cb6b7dfc5
+size 4661211456

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1776174abb6f9a714fc953e8af2e7ae152f352577954604ef46f9031286061dc
+size 5130252608

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef75a02c5f38e14a8873c7989188dac6974851b4654279fe1921d2c8018cc388
+size 4920734016

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef75a02c5f38e14a8873c7989188dac6974851b4654279fe1921d2c8018cc388
+size 4920734016

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8cdb034bae09470faac6e610f19d74b8d676d5d25f6be52e10f4a9178c5012d7
+size 4692668736

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a40f500cbb105322a67a18c33a512ad8ddf2698ec7ef8e768f330238c77916f
+size 5599293760

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093039ac4a1e65ca0f17d08a88fd55b50e086b7fdc6fd0b5c316cc543ca47564
+size 6068334912

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21d1a86d9e58b295968ac358a772f5f59dcdc1092573633ac905a891f309d07
+size 5732987200

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b21d1a86d9e58b295968ac358a772f5f59dcdc1092573633ac905a891f309d07
+size 5732987200

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:841545eb5be5d9f6d13c992d5fdcc92944cdbfffafcc8c7a4bbf716b51ea29d1
+size 5599293760

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:587daa71e517adc61b63af9b197b98d44106ed25e11c0d8fccd8ef7a960c345c
+size 6596006208

suzume-llama-3-8B-multilingual-orpo-borda-top25.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:663777bfa0b9a4e26b63b3de57cfa6a447408aad04cc001f464aec45c003e895
+size 8540770624