commit a62d1d1f31520167c9a0652ba4f432af3778467c
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Sat Jun 6 14:32:16 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: openthaigpt/openthaigpt-1.0.0-alpha-7b-chat-ckpt-hf
    Source: Original Platform

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..fbf94b1
--- /dev/null
+++ b/README.md
@@ -0,0 +1,101 @@
+---
+license: apache-2.0
+datasets:
+- kobkrit/rd-taxqa
+- iapp_wiki_qa_squad
+- Thaweewat/alpaca-cleaned-52k-th
+- Thaweewat/instruction-wild-52k-th
+- Thaweewat/databricks-dolly-15k-th
+- Thaweewat/hc3-24k-th
+- Thaweewat/gpteacher-20k-th
+- Thaweewat/onet-m6-social
+- Thaweewat/alpaca-finance-43k-th
+language:
+- th
+- en
+library_name: transformers
+pipeline_tag: text-generation
+tags:
+- openthaigpt
+- llama
+---
+
+# 🇹🇭 OpenThaiGPT 1.0.0-alpha
+<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2Fb8eiMDaqiEQL6ahbAY0h%2Fimage.png?alt=media&token=6fce78fd-2cca-4c0a-9648-bd5518e644ce
+https://openthaigpt.aieat.or.th/" width="200px">
+
+OpenThaiGPT Version 1.0.0-alpha is the first Thai implementation of a 7B-parameter LLaMA v2 Chat model finetuned to follow Thai translated instructions below and makes use of the Huggingface LLaMA implementation. 
+
+# ---- Full Huggingface Checkpoint Model ----
+
+## Upgrade from OpenThaiGPT 0.1.0-beta
+- Using Facebook LLama v2 model 7b chat as a base model which is pretrained on over 2 trillion token.
+- Context Length is upgrade from 2048 token to 4096 token
+- Allow research and commerical use.a
+
+## Pretrain Model
+- [https://huggingface.co/meta-llama/Llama-2-7b-chat](https://huggingface.co/meta-llama/Llama-2-7b-chat)
+
+## Support
+- Official website: https://openthaigpt.aieat.or.th
+- Facebook page: https://web.facebook.com/groups/openthaigpt
+- A Discord server for discussion and support [here](https://discord.gg/rUTp6dfVUF)
+- E-mail: kobkrit@iapp.co.th
+  
+## License
+**Source Code**: License Apache Software License 2.0.<br>
+**Weight**: Research and **Commercial uses**.<br>
+
+## Code and Weight
+**Colab Demo**: https://colab.research.google.com/drive/1kDQidCtY9lDpk49i7P3JjLAcJM04lawu?usp=sharing<br>
+**Finetune Code**: https://github.com/OpenThaiGPT/openthaigpt-finetune-010beta<br>
+**Inference Code**: https://github.com/OpenThaiGPT/openthaigpt<br>
+**Weight (Lora Adapter)**: https://huggingface.co/openthaigpt/openthaigpt-1.0.0-alpha-7b-chat<br>
+**Weight (Huggingface Checkpoint)**: https://huggingface.co/openthaigpt/openthaigpt-1.0.0-alpha-7b-chat-ckpt-hf<br>
+**Weight (GGML)**: https://huggingface.co/openthaigpt/openthaigpt-1.0.0-alpha-7b-chat-ggml<br>
+**Weight (Quantized 4bit GGML)**: https://huggingface.co/openthaigpt/openthaigpt-1.0.0-alpha-7b-chat-ggml-q4
+
+
+## Sponsors
+Pantip.com, ThaiSC<br>
+<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2FiWjRxBQgo0HUDcpZKf6A%2Fimage.png?alt=media&token=4fef4517-0b4d-46d6-a5e3-25c30c8137a6" width="100px">
+<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2Ft96uNUI71mAFwkXUtxQt%2Fimage.png?alt=media&token=f8057c0c-5c5f-41ac-bb4b-ad02ee3d4dc2" width="100px">
+
+### Powered by
+OpenThaiGPT Volunteers, Artificial Intelligence Entrepreneur Association of Thailand (AIEAT), and Artificial Intelligence Association of Thailand (AIAT)
+
+<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2F6yWPXxdoW76a4UBsM8lw%2Fimage.png?alt=media&token=1006ee8e-5327-4bc0-b9a9-a02e93b0c032" width="100px">
+<img src="https://1173516064-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FvvbWvIIe82Iv1yHaDBC5%2Fuploads%2FBwsmSovEIhW9AEOlHTFU%2Fimage.png?alt=media&token=5b550289-e9e2-44b3-bb8f-d3057d74f247" width="100px">
+
+### Authors
+* Kobkrit Viriyayudhakorn (kobkrit@aieat.or.th)
+* Sumeth Yuenyong (sumeth.yue@mahidol.edu)
+* Thaweewat Rugsujarit (thaweewr@scg.com)
+* Jillaphat Jaroenkantasima (autsadang41@gmail.com)
+* Norapat Buppodom (new@norapat.com)
+* Koravich Sangkaew (kwankoravich@gmail.com)
+* Peerawat Rojratchadakorn (peerawat.roj@gmail.com)
+* Surapon Nonesung (nonesungsurapon@gmail.com)
+* Chanon Utupon (chanon.utupon@gmail.com)
+* Sadhis Wongprayoon (sadhis.tae@gmail.com)
+* Nucharee Thongthungwong (nuchhub@hotmail.com)
+* Chawakorn Phiantham (mondcha1507@gmail.com)
+* Patteera Triamamornwooth (patt.patteera@gmail.com)
+* Nattarika Juntarapaoraya (natt.juntara@gmail.com)
+* Kriangkrai Saetan (kraitan.ss21@gmail.com)
+* Pitikorn Khlaisamniang (pitikorn32@gmail.com)
+
+<i>Disclaimer: Provided responses are not guaranteed.</i>
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_openthaigpt__openthaigpt-1.0.0-alpha-7b-chat-ckpt-hf)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 42.05   |
+| ARC (25-shot)         | 50.85          |
+| HellaSwag (10-shot)   | 74.89    |
+| MMLU (5-shot)         | 40.02         |
+| TruthfulQA (0-shot)   | 47.23   |
+| Winogrande (5-shot)   | 69.06   |
+| GSM8K (5-shot)        | 3.87        |
+| DROP (3-shot)         | 8.42         |
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..c7d9527
--- /dev/null
+++ b/config.json
@@ -0,0 +1,23 @@
+{
+  "_name_or_path": "/project/lt200059-openth/.cache/huggingface/hub/models--daryl149--llama-2-7b-chat-hf/snapshots/d8654a4f69178a0c9260cf730241ebac2e72b923",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 2048,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.29.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..66f8de0
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.29.0"
+}
diff --git a/pytorch_model-00001-of-00039.bin b/pytorch_model-00001-of-00039.bin
new file mode 100644
index 0000000..66f3f7d
--- /dev/null
+++ b/pytorch_model-00001-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe38b8674f434765ec072bf666f63b97bfa24d7484d753ca627ec2100bd6a8c6
+size 396364479
diff --git a/pytorch_model-00002-of-00039.bin b/pytorch_model-00002-of-00039.bin
new file mode 100644
index 0000000..5ee1de4
--- /dev/null
+++ b/pytorch_model-00002-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:567dd141b24f9fe38f0715cdb44ddc5040260032817ee0764fbb1a91c579a247
+size 371215393
diff --git a/pytorch_model-00003-of-00039.bin b/pytorch_model-00003-of-00039.bin
new file mode 100644
index 0000000..7121c01
--- /dev/null
+++ b/pytorch_model-00003-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:21897bd09a2fdd438ba7eb6e5e3f73f2ccba1995b44c2e6894ddb60cec6f51a5
+size 371215986
diff --git a/pytorch_model-00004-of-00039.bin b/pytorch_model-00004-of-00039.bin
new file mode 100644
index 0000000..139bcf9
--- /dev/null
+++ b/pytorch_model-00004-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffb9232b5e4ebfc290ac4509a497f0832f5affa673771a2ef05feb67e5c215aa
+size 371215986
diff --git a/pytorch_model-00005-of-00039.bin b/pytorch_model-00005-of-00039.bin
new file mode 100644
index 0000000..14bb57c
--- /dev/null
+++ b/pytorch_model-00005-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:230e822392707c874a228d1db02481373a7902706eba1c4770618750b29d9952
+size 371215986
diff --git a/pytorch_model-00006-of-00039.bin b/pytorch_model-00006-of-00039.bin
new file mode 100644
index 0000000..ede34da
--- /dev/null
+++ b/pytorch_model-00006-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ad788b0be08b250bd15a4c904e12717f32cfb8056cf5b555aa55ad23292c5b8
+size 314575888
diff --git a/pytorch_model-00007-of-00039.bin b/pytorch_model-00007-of-00039.bin
new file mode 100644
index 0000000..61cefe2
--- /dev/null
+++ b/pytorch_model-00007-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af0f7668496a668337c29541cd6350fe81aa526656a6d1fe0c5aa61f6582df6d
+size 314592882
diff --git a/pytorch_model-00008-of-00039.bin b/pytorch_model-00008-of-00039.bin
new file mode 100644
index 0000000..58be0b4
--- /dev/null
+++ b/pytorch_model-00008-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:891c1e0584197f83d2286ddb4d550b811f8de41bb7c67e62d3908e21945ff4dd
+size 314592882
diff --git a/pytorch_model-00009-of-00039.bin b/pytorch_model-00009-of-00039.bin
new file mode 100644
index 0000000..5786e4f
--- /dev/null
+++ b/pytorch_model-00009-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818d760dbe9433b5af6d72ee4e338df25a8fe93dac2df631c84069a150ae8f14
+size 371215393
diff --git a/pytorch_model-00010-of-00039.bin b/pytorch_model-00010-of-00039.bin
new file mode 100644
index 0000000..e6e03b0
--- /dev/null
+++ b/pytorch_model-00010-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:86a85d53b815f5f9f5c811e49108cfdb03725d8a2b860a0f3f5b98acaffa7dd3
+size 371215986
diff --git a/pytorch_model-00011-of-00039.bin b/pytorch_model-00011-of-00039.bin
new file mode 100644
index 0000000..b0bb766
--- /dev/null
+++ b/pytorch_model-00011-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27c4618e25a63198e7511874e1dba4bf46f7952b7ccf6b1f53a4ca3c8ecb5791
+size 371215986
diff --git a/pytorch_model-00012-of-00039.bin b/pytorch_model-00012-of-00039.bin
new file mode 100644
index 0000000..cc5d186
--- /dev/null
+++ b/pytorch_model-00012-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a4f7f4a6a4274130ee81030f08959d4661e8caec43aadda802046c6840173ad
+size 371215986
diff --git a/pytorch_model-00013-of-00039.bin b/pytorch_model-00013-of-00039.bin
new file mode 100644
index 0000000..50df0d3
--- /dev/null
+++ b/pytorch_model-00013-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fa960f004ba3f5dd7cec1c10ece9f5bca02cf5e8f6401eda744ced4683ce41d
+size 314575888
diff --git a/pytorch_model-00014-of-00039.bin b/pytorch_model-00014-of-00039.bin
new file mode 100644
index 0000000..9554510
--- /dev/null
+++ b/pytorch_model-00014-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:83afdfd23765d5dd21975843003de193b9c231169d66685a4276af8387003f54
+size 314592882
diff --git a/pytorch_model-00015-of-00039.bin b/pytorch_model-00015-of-00039.bin
new file mode 100644
index 0000000..5c18d60
--- /dev/null
+++ b/pytorch_model-00015-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a30d391f53bda6e1a991dbdde8036b835c39a0cdb57de4de53499b6cacd8d847
+size 314592882
diff --git a/pytorch_model-00016-of-00039.bin b/pytorch_model-00016-of-00039.bin
new file mode 100644
index 0000000..35a24d2
--- /dev/null
+++ b/pytorch_model-00016-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3b5d99ace2c5439c03f0e228761ee9d1363c15c95b85545467fd19a69dd9fe6
+size 371215393
diff --git a/pytorch_model-00017-of-00039.bin b/pytorch_model-00017-of-00039.bin
new file mode 100644
index 0000000..92ee97b
--- /dev/null
+++ b/pytorch_model-00017-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aafcb10dfa023c7684c239cc41640e3bae7c58df07a897044a3a4b4f35dc264c
+size 371215986
diff --git a/pytorch_model-00018-of-00039.bin b/pytorch_model-00018-of-00039.bin
new file mode 100644
index 0000000..2cf8d27
--- /dev/null
+++ b/pytorch_model-00018-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bc451038e8e2159b11719177e65d4a17eff1460af59b78bc393c1fe8c7e5335
+size 371215986
diff --git a/pytorch_model-00019-of-00039.bin b/pytorch_model-00019-of-00039.bin
new file mode 100644
index 0000000..b5fedfa
--- /dev/null
+++ b/pytorch_model-00019-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:370b3b71b7abac7b1e9d44d14e996051038df535b245d83eefbafec8f2e9cb2e
+size 371215986
diff --git a/pytorch_model-00020-of-00039.bin b/pytorch_model-00020-of-00039.bin
new file mode 100644
index 0000000..9c18e8f
--- /dev/null
+++ b/pytorch_model-00020-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e9e4cfdd35fd23a8914dcb4a021846c42ee9bd315efa686230d32b9ca9cd881
+size 314575888
diff --git a/pytorch_model-00021-of-00039.bin b/pytorch_model-00021-of-00039.bin
new file mode 100644
index 0000000..63f9cb5
--- /dev/null
+++ b/pytorch_model-00021-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bf27fd98853ae003178850ecd17317c72e894c2ff79220744f9a46de4161c02
+size 314592882
diff --git a/pytorch_model-00022-of-00039.bin b/pytorch_model-00022-of-00039.bin
new file mode 100644
index 0000000..73b213c
--- /dev/null
+++ b/pytorch_model-00022-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3797ec61650672727c8320ed96ce044b84b1882f67f070b93183f6da51f7e4a
+size 314592882
diff --git a/pytorch_model-00023-of-00039.bin b/pytorch_model-00023-of-00039.bin
new file mode 100644
index 0000000..29dc288
--- /dev/null
+++ b/pytorch_model-00023-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3e30b0fc19e9fbd5a0bcb3f5c1048a39a0572869c8c06545028c477a840f49d
+size 371215393
diff --git a/pytorch_model-00024-of-00039.bin b/pytorch_model-00024-of-00039.bin
new file mode 100644
index 0000000..41c3f22
--- /dev/null
+++ b/pytorch_model-00024-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:351a7e84d4daf6c5bb8a43206b5e5e105c21a196b3f62c65b76db30582e4a993
+size 371215986
diff --git a/pytorch_model-00025-of-00039.bin b/pytorch_model-00025-of-00039.bin
new file mode 100644
index 0000000..ad9e773
--- /dev/null
+++ b/pytorch_model-00025-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c2acf37331a0ce418909fdd3b868999a1646daed1cbbb4444aaeda655c54245
+size 371215986
diff --git a/pytorch_model-00026-of-00039.bin b/pytorch_model-00026-of-00039.bin
new file mode 100644
index 0000000..44d451b
--- /dev/null
+++ b/pytorch_model-00026-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e6ac65a1bd86ff080fe237dcfedf08d57857d5ebaeeac27b38bbaaf4328d820e
+size 371215986
diff --git a/pytorch_model-00027-of-00039.bin b/pytorch_model-00027-of-00039.bin
new file mode 100644
index 0000000..998001b
--- /dev/null
+++ b/pytorch_model-00027-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d83d9fab596e0dff584d64a98870776780009c5b32da84d03b3f7a24a55c2fb
+size 314575888
diff --git a/pytorch_model-00028-of-00039.bin b/pytorch_model-00028-of-00039.bin
new file mode 100644
index 0000000..e8898ad
--- /dev/null
+++ b/pytorch_model-00028-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5458cb6d9eeef57b179792f287f199dc4983214f94ae4b5998620348698a76eb
+size 314592882
diff --git a/pytorch_model-00029-of-00039.bin b/pytorch_model-00029-of-00039.bin
new file mode 100644
index 0000000..7ce5d13
--- /dev/null
+++ b/pytorch_model-00029-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7cc2fa23e15a68a83b50827a5c275bbda55c658051100f8d5d3de5cd67f918e
+size 314592882
diff --git a/pytorch_model-00030-of-00039.bin b/pytorch_model-00030-of-00039.bin
new file mode 100644
index 0000000..f7fa855
--- /dev/null
+++ b/pytorch_model-00030-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8975dd0e8fa70b6dccd5269c2f5eb9df8e04a8f24bdf79d3997bb922c90c41d
+size 371215393
diff --git a/pytorch_model-00031-of-00039.bin b/pytorch_model-00031-of-00039.bin
new file mode 100644
index 0000000..2a94bba
--- /dev/null
+++ b/pytorch_model-00031-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6139c95d7d0bafdf6d8f075cbfd6c6d20c5db3df52b3fbae93ee1bf547c26ed
+size 371215986
diff --git a/pytorch_model-00032-of-00039.bin b/pytorch_model-00032-of-00039.bin
new file mode 100644
index 0000000..3a89f04
--- /dev/null
+++ b/pytorch_model-00032-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03503f0e9b6dd484ca19c0482dcae4d54c06f30cdb6225b4448b20384176562d
+size 371215986
diff --git a/pytorch_model-00033-of-00039.bin b/pytorch_model-00033-of-00039.bin
new file mode 100644
index 0000000..dbc199d
--- /dev/null
+++ b/pytorch_model-00033-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:74bb29f1d6d928a48e87c2bf3c4ad3629862fead97908494116de9b4036a716a
+size 371215986
diff --git a/pytorch_model-00034-of-00039.bin b/pytorch_model-00034-of-00039.bin
new file mode 100644
index 0000000..291b334
--- /dev/null
+++ b/pytorch_model-00034-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b30fab70f3099ec5e3afd654fe28b40f66c7b561ab0b3453a2661552ba24d9f
+size 314575888
diff --git a/pytorch_model-00035-of-00039.bin b/pytorch_model-00035-of-00039.bin
new file mode 100644
index 0000000..bb2d40e
--- /dev/null
+++ b/pytorch_model-00035-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87236715920308af65325c02169dd556a051d0fb4c6c67231d9d3e14ae3f40c1
+size 314592882
diff --git a/pytorch_model-00036-of-00039.bin b/pytorch_model-00036-of-00039.bin
new file mode 100644
index 0000000..d30859e
--- /dev/null
+++ b/pytorch_model-00036-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e023f0b43fd93b47cd6c98106264d934601601b4f283e131c387bf97b241ec0
+size 314592882
diff --git a/pytorch_model-00037-of-00039.bin b/pytorch_model-00037-of-00039.bin
new file mode 100644
index 0000000..b467443
--- /dev/null
+++ b/pytorch_model-00037-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5061f2bf0985604a8e7d409d09f0f0947fabad9219e9fe64f3194d85742523eb
+size 371215393
diff --git a/pytorch_model-00038-of-00039.bin b/pytorch_model-00038-of-00039.bin
new file mode 100644
index 0000000..c650ad1
--- /dev/null
+++ b/pytorch_model-00038-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7dfc779e32574edac9244021c33512397888415efd19e6d79acd89f8ef70f86
+size 304114977
diff --git a/pytorch_model-00039-of-00039.bin b/pytorch_model-00039-of-00039.bin
new file mode 100644
index 0000000..5f36726
--- /dev/null
+++ b/pytorch_model-00039-of-00039.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4faa8dc42a67a488687de8b673d36b429524140d1a844df7ef3281c70e3a3750
+size 262144938
diff --git a/pytorch_model.bin.index.json b/pytorch_model.bin.index.json
new file mode 100644
index 0000000..37bef09
--- /dev/null
+++ b/pytorch_model.bin.index.json
@@ -0,0 +1,330 @@
+{
+  "metadata": {
+    "total_size": 13476839424
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00039-of-00039.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00039.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00039.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00039.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00039.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00039.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00039.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00039.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00039.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00039.bin",
+    "model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00039.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00039.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00039.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00039.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00039.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00039.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00039.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00039.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00039.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00039.bin",
+    "model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00039.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00039.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00014-of-00039.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00013-of-00039.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00013-of-00039.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00014-of-00039.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00014-of-00039.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00013-of-00039.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00013-of-00039.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00013-of-00039.bin",
+    "model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00039.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00013-of-00039.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00015-of-00039.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00015-of-00039.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00014-of-00039.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00015-of-00039.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00015-of-00039.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00014-of-00039.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00014-of-00039.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00014-of-00039.bin",
+    "model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00039.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00014-of-00039.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00016-of-00039.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00016-of-00039.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00016-of-00039.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00016-of-00039.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00016-of-00039.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00015-of-00039.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00015-of-00039.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00015-of-00039.bin",
+    "model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00039.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00015-of-00039.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00017-of-00039.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00017-of-00039.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00017-of-00039.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00017-of-00039.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00017-of-00039.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00016-of-00039.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00017-of-00039.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00016-of-00039.bin",
+    "model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00039.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00016-of-00039.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00018-of-00039.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00018-of-00039.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00018-of-00039.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00018-of-00039.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00018-of-00039.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00017-of-00039.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00018-of-00039.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00017-of-00039.bin",
+    "model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00039.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00018-of-00039.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00019-of-00039.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00019-of-00039.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00019-of-00039.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00019-of-00039.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00019-of-00039.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00019-of-00039.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00019-of-00039.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00018-of-00039.bin",
+    "model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00039.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00019-of-00039.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00021-of-00039.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00020-of-00039.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00020-of-00039.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00021-of-00039.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00021-of-00039.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00020-of-00039.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00020-of-00039.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00020-of-00039.bin",
+    "model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00039.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00020-of-00039.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00022-of-00039.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00022-of-00039.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00021-of-00039.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00022-of-00039.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00022-of-00039.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00021-of-00039.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00021-of-00039.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00021-of-00039.bin",
+    "model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00039.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00021-of-00039.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00023-of-00039.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00023-of-00039.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00023-of-00039.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00023-of-00039.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00023-of-00039.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00022-of-00039.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00022-of-00039.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00022-of-00039.bin",
+    "model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00039.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00022-of-00039.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00024-of-00039.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00024-of-00039.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00024-of-00039.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00024-of-00039.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00024-of-00039.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00023-of-00039.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00024-of-00039.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00023-of-00039.bin",
+    "model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00039.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00023-of-00039.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00039.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00039.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00039.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00039.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00039.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00039.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00004-of-00039.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00039.bin",
+    "model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00039.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00039.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00025-of-00039.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00025-of-00039.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00025-of-00039.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00025-of-00039.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00025-of-00039.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00024-of-00039.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00025-of-00039.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00024-of-00039.bin",
+    "model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00039.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00025-of-00039.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00026-of-00039.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00026-of-00039.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00026-of-00039.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00026-of-00039.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00026-of-00039.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00026-of-00039.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00026-of-00039.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00025-of-00039.bin",
+    "model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00039.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00026-of-00039.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00028-of-00039.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00027-of-00039.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00027-of-00039.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00028-of-00039.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00028-of-00039.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00027-of-00039.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00027-of-00039.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00027-of-00039.bin",
+    "model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00039.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00027-of-00039.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00029-of-00039.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00029-of-00039.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00028-of-00039.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00029-of-00039.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00029-of-00039.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00028-of-00039.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00028-of-00039.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00028-of-00039.bin",
+    "model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00039.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00028-of-00039.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00030-of-00039.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00030-of-00039.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00030-of-00039.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00030-of-00039.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00030-of-00039.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00029-of-00039.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00029-of-00039.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00029-of-00039.bin",
+    "model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00039.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00029-of-00039.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00031-of-00039.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00031-of-00039.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00031-of-00039.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00031-of-00039.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00031-of-00039.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00030-of-00039.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00031-of-00039.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00030-of-00039.bin",
+    "model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00039.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00030-of-00039.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00032-of-00039.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00032-of-00039.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00032-of-00039.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00032-of-00039.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00032-of-00039.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00031-of-00039.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00032-of-00039.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00031-of-00039.bin",
+    "model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00039.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00032-of-00039.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00033-of-00039.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00033-of-00039.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00033-of-00039.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00033-of-00039.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00033-of-00039.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00033-of-00039.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00033-of-00039.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00032-of-00039.bin",
+    "model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00039.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00033-of-00039.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00035-of-00039.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00034-of-00039.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00034-of-00039.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00035-of-00039.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00035-of-00039.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00034-of-00039.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00034-of-00039.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00034-of-00039.bin",
+    "model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00039.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00034-of-00039.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00036-of-00039.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00036-of-00039.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00035-of-00039.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00036-of-00039.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00036-of-00039.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00035-of-00039.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00035-of-00039.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00035-of-00039.bin",
+    "model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00039.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00035-of-00039.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00039.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00039.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00039.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00039.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00039.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00005-of-00039.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00005-of-00039.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00039.bin",
+    "model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00039.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00005-of-00039.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00037-of-00039.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00037-of-00039.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00037-of-00039.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00037-of-00039.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00037-of-00039.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00036-of-00039.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00036-of-00039.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00036-of-00039.bin",
+    "model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00036-of-00039.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00036-of-00039.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00038-of-00039.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00038-of-00039.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00038-of-00039.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00038-of-00039.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00038-of-00039.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00037-of-00039.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00038-of-00039.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00037-of-00039.bin",
+    "model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00038-of-00039.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00037-of-00039.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00039.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00039.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00039.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00039.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00039.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00006-of-00039.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00006-of-00039.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00006-of-00039.bin",
+    "model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00039.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00006-of-00039.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00039.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00039.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00039.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00039.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00039.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00007-of-00039.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00007-of-00039.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00007-of-00039.bin",
+    "model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00039.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00007-of-00039.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00009-of-00039.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00009-of-00039.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00039.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00039.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00009-of-00039.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00008-of-00039.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00008-of-00039.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00008-of-00039.bin",
+    "model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00039.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00008-of-00039.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00010-of-00039.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00010-of-00039.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00039.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00010-of-00039.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00010-of-00039.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00009-of-00039.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00039.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00009-of-00039.bin",
+    "model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00039.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00009-of-00039.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00011-of-00039.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00011-of-00039.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00011-of-00039.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00011-of-00039.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00011-of-00039.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00010-of-00039.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00039.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00010-of-00039.bin",
+    "model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00039.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00011-of-00039.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00012-of-00039.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00012-of-00039.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00012-of-00039.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00012-of-00039.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00012-of-00039.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00012-of-00039.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00012-of-00039.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00011-of-00039.bin",
+    "model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00039.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00012-of-00039.bin",
+    "model.norm.weight": "pytorch_model-00038-of-00039.bin"
+  }
+}
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..d85ba6c
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.model b/tokenizer.model
new file mode 100644
index 0000000..6c00c74
--- /dev/null
+++ b/tokenizer.model
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..400e3de
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,33 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}