Model save

README.md

@@ -1,70 +1,57 @@
 ---
 base_model: mistralai/Mistral-7B-Instruct-v0.2
-library_name: peft
-license: apache-2.0
+library_name: transformers
+model_name: results
 tags:
+- generated_from_trainer
 - trl
 - sft
-- generated_from_trainer
-model-index:
-- name: results
-  results: []
+licence: license
 ---
 
-<!-- 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. -->
-
-# results
-
-This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 1.2677
+# Model Card for results
 
-## Model description
+This model is a fine-tuned version of [mistralai/Mistral-7B-Instruct-v0.2](https://huggingface.co/mistralai/Mistral-7B-Instruct-v0.2).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-More information needed
+## Quick start
 
-## Intended uses & limitations
+```python
+from transformers import pipeline
 
-More information needed
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="magniolia/results", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
-## Training and evaluation data
+## Training procedure
 
-More information needed
 
-## Training procedure
 
-### Training hyperparameters
+This model was trained with SFT.
 
-The following hyperparameters were used during training:
-- learning_rate: 0.0002
-- train_batch_size: 1
-- eval_batch_size: 8
-- seed: 42
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: linear
-- num_epochs: 7
-- mixed_precision_training: Native AMP
+### Framework versions
 
-### Training results
+- TRL: 0.12.0.dev0
+- Transformers: 4.46.0.dev0
+- Pytorch: 2.4.1+cu121
+- Datasets: 3.0.1
+- Tokenizers: 0.20.1
 
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 1.4001        | 0.7143 | 5    | 1.2847          |
-| 0.9774        | 1.4286 | 10   | 1.1217          |
-| 0.9041        | 2.1429 | 15   | 1.0523          |
-| 0.7161        | 2.8571 | 20   | 1.1212          |
-| 0.5792        | 3.5714 | 25   | 1.1257          |
-| 0.5536        | 4.2857 | 30   | 1.1142          |
-| 0.5333        | 5.0    | 35   | 1.2031          |
-| 0.3973        | 5.7143 | 40   | 1.2709          |
-| 0.4453        | 6.4286 | 45   | 1.2677          |
+## Citations
 
 
-### Framework versions
 
-- PEFT 0.13.2
-- Transformers 4.45.2
-- Pytorch 2.4.1+cu121
-- Datasets 3.0.1
-- Tokenizers 0.20.1
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```