End of training

README.md

@@ -0,0 +1,69 @@
+---
+base_model: deepseek-ai/DeepSeek-R1-Distill-Llama-70B
+library_name: transformers
+model_name: 02cd5e37-b293-4ea3-b2c2-536d7fd77b2a
+tags:
+- generated_from_trainer
+- axolotl
+- dpo
+- trl
+licence: license
+---
+
+# Model Card for 02cd5e37-b293-4ea3-b2c2-536d7fd77b2a
+
+This model is a fine-tuned version of [deepseek-ai/DeepSeek-R1-Distill-Llama-70B](https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Llama-70B).
+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/02cd5e37-b293-4ea3-b2c2-536d7fd77b2a", 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/zhgxpt6w)
+
+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 sha256:41e27ec868d6fb34cb9a12e0534b8dae19fe87b4372c1e8d6da9c259db48f0eb
+size 1657155202

config.json

@@ -1,5 +1,4 @@
 {
-  "_attn_implementation_autoset": true,
   "_name_or_path": "deepseek-ai/DeepSeek-R1-Distill-Llama-70B",
   "architectures": [
     "LlamaForCausalLM"

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "temperature": 0.6,
+  "top_p": 0.95,
+  "transformers_version": "4.46.0"
+}

pytorch_model-00001-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:904ebf72eff67ac5c59916e5ad5b1c871035d4b51b00f606fc9e789f0f18f370
+size 4959026805

pytorch_model-00002-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8104271ad848cb5a8bd6a7b5f3aa52e9ecfcb3e5f7c14a525aa295e3b46471da
+size 4999764008

pytorch_model-00003-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b9f00db1ae12c681813b4ad8051cd85cae35002ab78d8a280bd285d815fad0d
+size 4958271774

pytorch_model-00004-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0533b4945404aa54afc993418f1e89ec1f551b8d5b2523370acb25ce1a4ed6d5
+size 4958338108

pytorch_model-00005-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d1a287928bf5dfc6c0ad58b8d6d36481b63b330789dd4efc6fe378703f62aa5
+size 4958338012

pytorch_model-00006-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:717f452dfeb116f5419a6ca775ef16757cc2f7362c78d07e606d6e6f734f3da1
+size 4999764200

pytorch_model-00007-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6bf78f24dbef9b153d3e1a53fbe3f82e2c06d651881ee60c3c3e707d393d179
+size 4958271774

pytorch_model-00008-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b62c62f636275816ee01ba38c8850cff1491f2d383e682e2b9d216c7e783da8
+size 4285812501

pytorch_model-00009-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1e07bc3cf33be9eeb4289ddfef919285f03d98328893a21652f83be5aedb85a
+size 2101347717