From 95f9715b05c760a64299b6549f7f45b55d502b40 Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Fri, 17 Jul 2026 21:40:11 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: Ichsan2895/Merak-7B-v5-PROTOTYPE1 Source: Original Platform --- .gitattributes | 35 ++++ README.md | 97 ++++++++++ added_tokens.json | 4 + config.json | 25 +++ generation_config.json | 7 + pytorch_model-00001-of-00006.bin | 3 + pytorch_model-00002-of-00006.bin | 3 + pytorch_model-00003-of-00006.bin | 3 + pytorch_model-00004-of-00006.bin | 3 + pytorch_model-00005-of-00006.bin | 3 + pytorch_model-00006-of-00006.bin | 3 + pytorch_model.bin.index.json | 298 +++++++++++++++++++++++++++++++ special_tokens_map.json | 37 ++++ tokenizer.model | 3 + tokenizer_config.json | 65 +++++++ 15 files changed, 589 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 added_tokens.json create mode 100644 config.json create mode 100644 generation_config.json create mode 100644 pytorch_model-00001-of-00006.bin create mode 100644 pytorch_model-00002-of-00006.bin create mode 100644 pytorch_model-00003-of-00006.bin create mode 100644 pytorch_model-00004-of-00006.bin create mode 100644 pytorch_model-00005-of-00006.bin create mode 100644 pytorch_model-00006-of-00006.bin create mode 100644 pytorch_model.bin.index.json create mode 100644 special_tokens_map.json create mode 100644 tokenizer.model create mode 100644 tokenizer_config.json diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a6344aa --- /dev/null +++ b/.gitattributes @@ -0,0 +1,35 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8573e4b --- /dev/null +++ b/README.md @@ -0,0 +1,97 @@ +--- +datasets: +- wikipedia +- Ichsan2895/OASST_Top1_Indonesian +- Ichsan2895/alpaca-gpt4-indonesian +language: +- id +- en +pipeline_tag: text-generation +license: cc-by-nc-sa-4.0 +--- +
+MERAK +
+ +# THIS IS 1st PROTOTYPE OF MERAK-7B-v5! + +Merak-7B is the Large Language Model of Indonesian Language + +This model is based on [Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca) and fine tuned by some of Indonesia Wikipedia articles that I cleaned before. + +Leveraging QLoRA (QLora: Efficient Finetuning of Quantized LLMs), Merak-7B is able to run with 16 GB VRAM. We also use DPO-Trainer for RLHF with TRL library.. + +Licensed under Creative Commons-By Attribution-Share Alike-Non Commercial (CC-BY-SA-NC 4.0) Merak-7B empowers AI enthusiasts, researchers alike. + +Big thanks to all my friends and communities that help to build our first model. Thanks for Axolotl for a great fine tuning tool which designed to streamline the fine-tuning of various AI models. + +Feel free, to ask me about the model and please share the news on your social media. + +## CITATION +``` +@software{lian2023mistralorca1 + title = {MistralOrca: Mistral-7B Model Instruct-tuned on Filtered OpenOrcaV1 GPT-4 Dataset}, + author = {Wing Lian and Bleys Goodson and Guan Wang and Eugene Pentland and Austin Cook and Chanvichet Vong and "Teknium"}, + year = {2023}, + publisher = {HuggingFace}, + journal = {HuggingFace repository}, + howpublished = {\url{https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca}, +} + +@misc{mukherjee2023orca, + title={Orca: Progressive Learning from Complex Explanation Traces of GPT-4}, + author={Subhabrata Mukherjee and Arindam Mitra and Ganesh Jawahar and Sahaj Agarwal and Hamid Palangi and Ahmed Awadallah}, + year={2023}, + eprint={2306.02707}, + archivePrefix={arXiv}, + primaryClass={cs.CL} +} + +@ONLINE{wikidump, + author = "Wikimedia Foundation", + title = "Wikimedia Downloads", + url = "https://dumps.wikimedia.org" +} + +@inproceedings{wolf-etal-2020-transformers, + title = "Transformers: State-of-the-Art Natural Language Processing", + author = "Thomas Wolf and Lysandre Debut and Victor Sanh and Julien Chaumond and Clement Delangue and Anthony Moi and Pierric Cistac and Tim Rault and Rémi Louf and Morgan Funtowicz and Joe Davison and Sam Shleifer and Patrick von Platen and Clara Ma and Yacine Jernite and Julien Plu and Canwen Xu and Teven Le Scao and Sylvain Gugger and Mariama Drame and Quentin Lhoest and Alexander M. Rush", + booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations", + month = oct, + year = "2020", + address = "Online", + publisher = "Association for Computational Linguistics", + url = "https://www.aclweb.org/anthology/2020.emnlp-demos.6", + pages = "38--45" +} + +@misc{vonwerra2022trl, + author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang}, + title = {TRL: Transformer Reinforcement Learning}, + year = {2020}, + publisher = {GitHub}, + journal = {GitHub repository}, + howpublished = {\url{https://github.com/huggingface/trl}} +} + +@article{dettmers2023qlora, + title = {QLoRA: Efficient Finetuning of Quantized LLMs}, + author = {Dettmers, Tim and Pagnoni, Artidoro and Holtzman, Ari and Zettlemoyer, Luke}, + journal = {arXiv preprint arXiv:2305.14314}, + year = {2023} +} +``` +[Built with Axolotl](https://github.com/OpenAccess-AI-Collective/axolotl) + +## HOW TO CITE THIS PROJECT + +If you use the Merak-7B model in your research or project, please cite it as: +``` +@article{Merak, + title={Merak-7B: The LLM for Bahasa Indonesia}, + author={Muhammad Ichsan}, + publisher={Hugging Face} + journal={Hugging Face Repository}, + year={2023} +} +``` \ No newline at end of file diff --git a/added_tokens.json b/added_tokens.json new file mode 100644 index 0000000..e36863d --- /dev/null +++ b/added_tokens.json @@ -0,0 +1,4 @@ +{ + "<|im_end|>": 32000, + "<|im_start|>": 32001 +} diff --git a/config.json b/config.json new file mode 100644 index 0000000..778730c --- /dev/null +++ b/config.json @@ -0,0 +1,25 @@ +{ + "_name_or_path": "Ichsan2895/Merak-7B-v4", + "architectures": [ + "MistralForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 32768, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "float32", + "transformers_version": "4.34.1", + "use_cache": false, + "vocab_size": 32002 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..6b8fddf --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 1, + "eos_token_id": 2, + "transformers_version": "4.34.1", + "use_cache": false +} diff --git a/pytorch_model-00001-of-00006.bin b/pytorch_model-00001-of-00006.bin new file mode 100644 index 0000000..4e5b746 --- /dev/null +++ b/pytorch_model-00001-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4e5be4251e2bd1f2bac58169006213e5e56e9e8183a4f5056c83c44e4534de4 +size 4987241157 diff --git a/pytorch_model-00002-of-00006.bin b/pytorch_model-00002-of-00006.bin new file mode 100644 index 0000000..f58ad8e --- /dev/null +++ b/pytorch_model-00002-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:632c33573ec94ef60f171e073653b30edc8eaa0b39049daccf90834cc3f24a04 +size 4899127691 diff --git a/pytorch_model-00003-of-00006.bin b/pytorch_model-00003-of-00006.bin new file mode 100644 index 0000000..1210c9e --- /dev/null +++ b/pytorch_model-00003-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09ab8d559ed98a9ab7f6dbb746afb44edd8d45d8762c08dcb758a99baa9bbfbe +size 4999825537 diff --git a/pytorch_model-00004-of-00006.bin b/pytorch_model-00004-of-00006.bin new file mode 100644 index 0000000..d9b30b9 --- /dev/null +++ b/pytorch_model-00004-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fe5a882402b23cfabcffcadd1980564e80652e830541471161aaf8d0045c647 +size 4999825597 diff --git a/pytorch_model-00005-of-00006.bin b/pytorch_model-00005-of-00006.bin new file mode 100644 index 0000000..e9ac1d6 --- /dev/null +++ b/pytorch_model-00005-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36966b1083ba34cb12844dd996deb482c9627ac0e3569f240612017c39365c14 +size 4832018477 diff --git a/pytorch_model-00006-of-00006.bin b/pytorch_model-00006-of-00006.bin new file mode 100644 index 0000000..cd91d21 --- /dev/null +++ b/pytorch_model-00006-of-00006.bin @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:315b961e2e113ca147f42da257963b7a0590f455b364dc1d4fa4e39a448f17b8 +size 4249057137 diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json new file mode 100644 index 0000000..7d024c2 --- /dev/null +++ b/pytorch_model.bin.index.json @@ -0,0 +1,298 @@ +{ + "metadata": { + "total_size": 28966993920 + }, + "weight_map": { + "lm_head.weight": "pytorch_model-00006-of-00006.bin", + "model.embed_tokens.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00006.bin", + "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00006.bin", + "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.27.input_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.27.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00006.bin", + "model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00006.bin", + "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00006.bin", + "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00006.bin", + "model.norm.weight": "pytorch_model-00006-of-00006.bin" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..a760479 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,37 @@ +{ + "additional_special_tokens": [ + "", + "", + "", + "<|im_end|>", + "<|im_start|>" + ], + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8b443ef --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..507da86 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,65 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32000": { + "content": "<|im_end|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "32001": { + "content": "<|im_start|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [ + "", + "", + "", + "<|im_end|>", + "<|im_start|>" + ], + "bos_token": "", + "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": true +}