End of training

README.md

@@ -0,0 +1,69 @@
+---
+base_model: bigscience/bloom-560m
+library_name: transformers
+model_name: 5bb857c2-6667-4cf4-ba3a-9767a0cd0ee6
+tags:
+- generated_from_trainer
+- axolotl
+- dpo
+- trl
+licence: license
+---
+
+# Model Card for 5bb857c2-6667-4cf4-ba3a-9767a0cd0ee6
+
+This model is a fine-tuned version of [bigscience/bloom-560m](https://huggingface.co/bigscience/bloom-560m).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+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="Alphatao/5bb857c2-6667-4cf4-ba3a-9767a0cd0ee6", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<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/alphatao-alphatao/Gradients-On-Demand/runs/qm3kpc28)
+
+This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
+
+### Framework versions
+
+- TRL: 0.12.0.dev0
+- Transformers: 4.46.0
+- Pytorch: 2.5.0+cu124
+- Datasets: 3.0.1
+- Tokenizers: 0.20.1
+
+## Citations
+
+Cite DPO as:
+
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
+    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
+    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
+}
+```
+
+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.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:928af8fa95e1fd397425ea02a9e30ffd82fde34d524d19743c937b52857d2e48
+size 100734154

config.json

@@ -1,5 +1,4 @@
 {
-  "_attn_implementation_autoset": true,
   "_name_or_path": "bigscience/bloom-560m",
   "apply_residual_connection_post_layernorm": false,
   "architectures": [
@@ -25,6 +24,7 @@
   "skip_bias_add": true,
   "skip_bias_add_qkv": false,
   "slow_but_exact": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.46.0",
   "unk_token_id": 0,
   "use_cache": false,

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "pad_token_id": 3,
+  "transformers_version": "4.46.0"
+}

pytorch_model.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2373a0c5bed6f802cef6b0abaaf0d3f8efb342f20eab6148bf64eb80a0991980
+size 1219263326