Update README.md

README.md

@@ -4,12 +4,31 @@ base_model: meta-llama/Meta-Llama-3-8B-Instruct
 tags:
 - generated_from_trainer
 model-index:
-- name: home/ubuntu/llm_training/axolotl/llama3-8b-gpt-4o-ru/output_llama3_8b_gpt_4o_ru
+- name: >-
+    home/ubuntu/llm_training/axolotl/llama3-8b-gpt-4o-ru/output_llama3_8b_gpt_4o_ru
   results: []
+datasets:
+- ruslandev/tagengo-rus-gpt-4o
 ---
 
-<!-- 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. -->
+# Llama-3 8B GPT-4o-RU-1.0
+
+[[Dataset]](https://huggingface.co/datasets/ruslandev/tagengo-rus-gpt-4o)
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
+The idea behind this model is to train on a dataset derived from a smaller subset of the [tagengo-gpt4](https://huggingface.co/datasets/lightblue/tagengo-gpt4), but with improved data quality.
+I tried to achieve higher data quality by prompting GPT-4o, the latest OpenAI's LLM with better multilingual capabilities. The training objective is primarily focused on the Russian language (80% of the training examples).
+The model shows promising results on the MT-Bench evaluation benchmark, surpassing GPT-3.5 and being on par with [Suzume](https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual) in Russian language scores, 
+even though the latter is trained on 8x bigger and more diverse dataset. 
+
+## Evaluation scores
+
+|            |meta-llama/Meta-Llama-3-8B-Instruct | ruslandev/llama-3-8b-gpt-4o-ru1.0 | lightblue/suzume-llama-3-8B-multilingual | Nexusflow/Starling-LM-7B-beta | gpt-3.5-turbo |
+|:----------:|:----------------------------------:|:---------------------------------:|:----------------------------------------:|:-----------------------------:|:-------------:|
+| Russian 🇷🇺 | NaN                                | 8.12                              | 8.19                                     | 8.06                          | 7.94          |
+| English 🇺🇸 | 7.98                               | 8.01                              | 7.73                                     | 7.92                          | 8.26          |
+
+## Training procedure
 
 [<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>
@@ -78,26 +97,6 @@ special_tokens:
 
 </details><br>
 
-# home/ubuntu/llm_training/axolotl/llama3-8b-gpt-4o-ru/output_llama3_8b_gpt_4o_ru
-
-This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) on the None dataset.
-It achieves the following results on the evaluation set:
-- Loss: 0.7702
-
-## 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:
@@ -131,4 +130,4 @@ The following hyperparameters were used during training:
 - Transformers 4.41.1
 - Pytorch 2.2.2+cu121
 - Datasets 2.19.1
-- Tokenizers 0.19.1
+- Tokenizers 0.19.1