Model save

README.md

@@ -1,64 +1,57 @@
 ---
-license: apache-2.0
 base_model: HuggingFaceTB/SmolLM2-135M-Instruct
+library_name: transformers
+model_name: SmolLM2-135M-Instruct_tldr-sft
 tags:
+- generated_from_trainer
 - trl
 - sft
-- generated_from_trainer
-model-index:
-- name: SmolLM2-135M-Instruct_tldr-sft
-  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. -->
-
-# SmolLM2-135M-Instruct_tldr-sft
-
-This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct) on an unknown dataset.
-It achieves the following results on the evaluation set:
-- Loss: 2.4363
-
-## Model description
+# Model Card for SmolLM2-135M-Instruct_tldr-sft
 
-More information needed
+This model is a fine-tuned version of [HuggingFaceTB/SmolLM2-135M-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-135M-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
 
-## Intended uses & limitations
+## Quick start
 
-More information needed
+```python
+from transformers import pipeline
 
-## Training and evaluation data
-
-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="mnoukhov/SmolLM2-135M-Instruct_tldr-sft", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
 
 ## Training procedure
 
-### Training hyperparameters
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/mnoukhov/bpo/runs/5586569_sft_smol135m)
+
+This model was trained with SFT.
 
-The following hyperparameters were used during training:
-- learning_rate: 1e-05
-- train_batch_size: 8
-- eval_batch_size: 8
-- seed: 42
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 32
-- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
-- lr_scheduler_type: cosine
-- num_epochs: 1
+### Framework versions
 
-### Training results
+- TRL: 0.12.0
+- Transformers: 4.46.2
+- Pytorch: 2.5.1
+- Datasets: 3.1.0
+- Tokenizers: 0.20.3
 
-| Training Loss | Epoch | Step | Validation Loss |
-|:-------------:|:-----:|:----:|:---------------:|
-| 2.4812        | 0.2   | 730  | 2.4774          |
-| 2.4521        | 0.4   | 1460 | 2.4518          |
-| 2.4463        | 0.6   | 2190 | 2.4405          |
-| 2.4265        | 0.8   | 2920 | 2.4363          |
+## Citations
 
 
-### Framework versions
 
-- Transformers 4.37.2
-- Pytorch 2.2.0+cu121
-- Datasets 2.17.1
-- Tokenizers 0.15.2
+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}}
+}
+```

generation_config.json

@@ -3,5 +3,5 @@
   "bos_token_id": 1,
   "eos_token_id": 2,
   "pad_token_id": 2,
-  "transformers_version": "4.37.2"
+  "transformers_version": "4.46.2"
 }