End of training

README.md

@@ -0,0 +1,70 @@
+---
+base_model: unsloth/mistral-7b-v0.3-bnb-4bit
+library_name: transformers
+model_name: Mistral_7B-DPO
+tags:
+- generated_from_trainer
+- trl
+- dpo
+- unsloth
+licence: license
+---
+
+# Model Card for Mistral_7B-DPO
+
+This model is a fine-tuned version of [unsloth/mistral-7b-v0.3-bnb-4bit](https://huggingface.co/unsloth/mistral-7b-v0.3-bnb-4bit).
+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="treasure4l/Mistral_7B-DPO", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+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: 0.13.0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.1.0+cu118
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## 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_config.json

@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/mistral-7b-v0.3-bnb-4bit",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "v_proj",
+    "q_proj",
+    "k_proj",
+    "gate_proj",
+    "o_proj",
+    "up_proj",
+    "down_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3216c79cc3f3dcb792e9483861df1582229f938e12a6c3057a49f7a377e49037
+size 167832240

requirements.txt

@@ -0,0 +1,161 @@
+accelerate==1.2.1
+aiohappyeyeballs==2.4.4
+aiohttp==3.11.11
+aiosignal==1.3.2
+anyio==4.0.0
+argon2-cffi==23.1.0
+argon2-cffi-bindings==21.2.0
+arrow==1.3.0
+asttokens==2.4.1
+async-lru==2.0.4
+async-timeout==5.0.1
+attrs==23.1.0
+Babel==2.13.1
+beautifulsoup4==4.12.2
+bleach==6.1.0
+blinker==1.4
+certifi==2022.12.7
+cffi==1.16.0
+charset-normalizer==2.1.1
+comm==0.2.0
+cryptography==3.4.8
+datasets==3.2.0
+dbus-python==1.2.18
+debugpy==1.8.0
+decorator==5.1.1
+defusedxml==0.7.1
+dill==0.3.8
+distro==1.7.0
+einops==0.8.0
+entrypoints==0.4
+exceptiongroup==1.1.3
+executing==2.0.1
+fastjsonschema==2.18.1
+filelock==3.9.0
+fqdn==1.5.1
+frozenlist==1.5.0
+fsspec==2024.9.0
+httplib2==0.20.2
+huggingface-hub==0.27.0
+idna==3.4
+importlib-metadata==4.6.4
+ipykernel==6.26.0
+ipython==8.17.2
+ipython-genutils==0.2.0
+ipywidgets==8.1.1
+isoduration==20.11.0
+jedi==0.19.1
+jeepney==0.7.1
+Jinja2==3.1.2
+json5==0.9.14
+jsonpointer==2.4
+jsonschema==4.19.2
+jsonschema-specifications==2023.7.1
+jupyter-archive==3.4.0
+jupyter-contrib-core==0.4.2
+jupyter-contrib-nbextensions==0.7.0
+jupyter-events==0.9.0
+jupyter-highlight-selected-word==0.2.0
+jupyter-http-over-ws==0.0.8
+jupyter-lsp==2.2.0
+jupyter-nbextensions-configurator==0.6.3
+jupyter_client==7.4.9
+jupyter_core==5.5.0
+jupyter_server==2.10.0
+jupyter_server_terminals==0.4.4
+jupyterlab==4.0.8
+jupyterlab-pygments==0.2.2
+jupyterlab-widgets==3.0.9
+jupyterlab_server==2.25.0
+keyring==23.5.0
+launchpadlib==1.10.16
+lazr.restfulclient==0.14.4
+lazr.uri==1.0.6
+lxml==4.9.3
+markdown-it-py==3.0.0
+MarkupSafe==2.1.2
+matplotlib-inline==0.1.6
+mdurl==0.1.2
+mistune==3.0.2
+more-itertools==8.10.0
+mpmath==1.3.0
+multidict==6.1.0
+multiprocess==0.70.16
+nbclassic==1.0.0
+nbclient==0.9.0
+nbconvert==7.11.0
+nbformat==5.9.2
+nest-asyncio==1.5.8
+networkx==3.0
+notebook==6.5.5
+notebook_shim==0.2.3
+numpy==1.24.1
+oauthlib==3.2.0
+overrides==7.4.0
+packaging==23.2
+pandas==2.2.3
+pandocfilters==1.5.0
+parso==0.8.3
+pexpect==4.8.0
+Pillow==9.3.0
+platformdirs==3.11.0
+prometheus-client==0.18.0
+prompt-toolkit==3.0.39
+propcache==0.2.1
+psutil==5.9.6
+ptyprocess==0.7.0
+pure-eval==0.2.2
+pyarrow==18.1.0
+pycparser==2.21
+Pygments==2.16.1
+PyGObject==3.42.1
+PyJWT==2.3.0
+pyparsing==2.4.7
+python-apt==2.4.0+ubuntu2
+python-dateutil==2.8.2
+python-json-logger==2.0.7
+pytz==2024.2
+PyYAML==6.0.1
+pyzmq==24.0.1
+referencing==0.30.2
+regex==2024.11.6
+requests==2.32.3
+rfc3339-validator==0.1.4
+rfc3986-validator==0.1.1
+rich==13.9.4
+rpds-py==0.12.0
+safetensors==0.4.5
+SecretStorage==3.3.1
+Send2Trash==1.8.2
+six==1.16.0
+sniffio==1.3.0
+soupsieve==2.5
+stack-data==0.6.3
+sympy==1.12
+terminado==0.17.1
+tinycss2==1.2.1
+tokenizers==0.21.0
+tomli==2.0.1
+torch==2.1.0+cu118
+torchaudio==2.1.0+cu118
+torchvision==0.16.0+cu118
+tornado==6.3.3
+tqdm==4.67.1
+traitlets==5.13.0
+transformers==4.47.1
+triton==2.1.0
+trl==0.13.0
+types-python-dateutil==2.8.19.14
+typing_extensions==4.4.0
+tzdata==2024.2
+uri-template==1.3.0
+urllib3==1.26.13
+wadllib==1.3.6
+wcwidth==0.2.9
+webcolors==1.13
+webencodings==0.5.1
+websocket-client==1.6.4
+widgetsnbextension==4.0.9
+xxhash==3.5.0
+yarl==1.18.3
+zipp==1.0.0

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d0700e29a23833f5033edc6cd73e17db0f62f06c4f2f3fa08d131bde0b889b66
+size 6200