rawkintrevo/granite-3.0-2b-instruct-pirate-adapter

README.md

@@ -1,57 +1,57 @@
 ---
 base_model: ibm-granite/granite-3.0-2b-instruct
-library_name: peft
-license: apache-2.0
+library_name: transformers
+model_name: granite-3.0-2b-instruct-pirate-adapter
 tags:
+- generated_from_trainer
 - trl
 - sft
-- generated_from_trainer
-model-index:
-- name: granite-3.0-2b-instruct-pirate-adapter
-  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. -->
-
-# granite-3.0-2b-instruct-pirate-adapter
-
-This model is a fine-tuned version of [ibm-granite/granite-3.0-2b-instruct](https://huggingface.co/ibm-granite/granite-3.0-2b-instruct) on an unknown dataset.
+# Model Card for granite-3.0-2b-instruct-pirate-adapter
 
-## Model description
+This model is a fine-tuned version of [ibm-granite/granite-3.0-2b-instruct](https://huggingface.co/ibm-granite/granite-3.0-2b-instruct).
+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="rawkintrevo/granite-3.0-2b-instruct-pirate-adapter", 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: 6
-- eval_batch_size: 6
-- seed: 42
-- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: linear
-- num_epochs: 3
-- mixed_precision_training: Native AMP
+### Framework versions
 
-### Training results
+- TRL: 0.12.0
+- Transformers: 4.46.1
+- Pytorch: 2.5.0+cu121
+- Datasets: 3.1.0
+- Tokenizers: 0.20.1
 
+## Citations
 
 
-### Framework versions
 
-- PEFT 0.13.2
-- Transformers 4.46.1
-- Pytorch 2.5.0+cu121
-- Datasets 3.1.0
-- 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}}
+}
+```

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a9059a1c09cbf9183bd228fa74174b88339869f8f303f051c72494cdff354b2
+oid sha256:4fef0594520e648a1cd7cb3a7bf474d0595d8a3ff450bb74f7b6a784d499605b
 size 17060712

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aaf4bc89a1f144ff9739fefafad2ea8971f713596645de6eb12dc25f3faa3a1c
+oid sha256:4b92a6478e138b902e59e31de207a898b52d1c845ee025777d933a02cb07e890
 size 5496