Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,7 @@
-*.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
+Quyen-Pro-Max-v0.1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Quyen-Pro-Max-v0.1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Quyen-Pro-Max-v0.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Quyen-Pro-Max-v0.1-Q5_K_M.gguf-part-a filter=lfs diff=lfs merge=lfs -text
+Quyen-Pro-Max-v0.1-Q5_K_M.gguf-part-b filter=lfs diff=lfs merge=lfs -text
+Quyen-Pro-Max-v0.1-Q6_K.gguf-part-a filter=lfs diff=lfs merge=lfs -text
+Quyen-Pro-Max-v0.1-Q6_K.gguf-part-b filter=lfs diff=lfs merge=lfs -text

Quyen-Pro-Max-v0.1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:647aff74ef3b78f59dddb1ef84f22e104c2a1c699f85e61638624ee252e32954
+size 28461062400

Quyen-Pro-Max-v0.1-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b8720a9f94d5afd932b03fd6caf04b7c4a58b162d5a32f81c1138fd0feba60
+size 38486137088

Quyen-Pro-Max-v0.1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64dd9fcf22c6bece41b9d339058b137667e277a824cc6b8bfcb3ef8ac828a918
+size 44104177920

Quyen-Pro-Max-v0.1-Q5_K_M.gguf-part-a

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eb164f25c601f6f8a0daa68aacbe94743ddcce9e858d5372f5c95c0153c85f4
+size 25653161088

Quyen-Pro-Max-v0.1-Q5_K_M.gguf-part-b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d4cc02c73f8f0999301a91141788064d27ce5fd0a82e14a49db7a6e596a5abd
+size 25653161088

Quyen-Pro-Max-v0.1-Q6_K.gguf-part-a

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48ce0938c2065a7efd937557eb56f834c98d73f7772c0dedbdb4f4819ad7f733
+size 29657558144

Quyen-Pro-Max-v0.1-Q6_K.gguf-part-b

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d6cef011822e4f82facb68b7c7a87d3773e27d299162dc522aed6b6d9f2c4d8
+size 29657558144

README.md

@@ -0,0 +1,63 @@
+---
+library_name: transformers
+license: other
+datasets:
+- teknium/OpenHermes-2.5
+- LDJnr/Capybara
+- Intel/orca_dpo_pairs
+- argilla/distilabel-capybara-dpo-7k-binarized
+language:
+- en
+pipeline_tag: text-generation
+---
+
+# Quyen
+<img src="quyen.webp" width="512" height="512" alt="Quyen">
+
+# Model Description
+Quyen is our first flagship LLM series based on the Qwen1.5 family. We introduced 6 different versions:
+
+- **Quyen-SE (0.5B)**
+- **Quyen-Mini (1.8B)**
+- **Quyen (4B)**
+- **Quyen-Plus (7B)**
+- **Quyen-Pro (14B)**
+- **Quyen-Pro-Max (72B)**
+
+All models were trained with SFT and DPO using the following dataset:
+
+- *OpenHermes-2.5* by **Teknium**
+- *Capyabara* by **LDJ**
+- *argilla/distilabel-capybara-dpo-7k-binarized* by **argilla**
+- *orca_dpo_pairs* by **Intel**
+- and Private Data by **Ontocord** & **BEE-spoke-data**
+
+# Prompt Template
+- All Quyen models use ChatML as the default template:
+
+```
+<|im_start|>system
+You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
+<|im_start|>user
+Hello world.<|im_end|>
+<|im_start|>assistant
+```
+
+- You can also use `apply_chat_template`:
+
+```python
+messages = [
+    {"role": "system", "content": "You are a sentient, superintelligent artificial general intelligence, here to teach and assist me."},
+    {"role": "user", "content": "Hello world."}
+]
+gen_input = tokenizer.apply_chat_template(message, return_tensors="pt")
+model.generate(**gen_input)
+```
+
+# Benchmarks:
+
+- Coming Soon! We will update the benchmarks later
+
+# Acknowledgement
+- We're incredibly grateful to **Tensoic** and **Ontocord** for their generous support with compute and data preparation.
+- Special thanks to the Qwen team for letting us access the models early for these amazing finetunes.

huggingface-metadata.txt

@@ -0,0 +1,34 @@
+url: https://huggingface.co/vilm/Quyen-Pro-Max-v0.1
+branch: main
+download date: 2024-02-06 12:41:18
+sha256sum:
+    b5e723701f9189c6341b11a8b5abdaca19838eb26b3a739ee47aa9333ac58406 pytorch_model-00001-of-00030.bin
+    0f3571d082e12670df4bd37977e49ebcd216d363815d5ad34873755c23e29559 pytorch_model-00002-of-00030.bin
+    b29fb3705e5ed29fcaa30dfde7ad126e145e26b5d61e94b0f9b4100f38cca7bc pytorch_model-00003-of-00030.bin
+    6beacb3b5e5250dd5416695d2f304bff9965f0222177cd54ce3389958a8fbf7b pytorch_model-00004-of-00030.bin
+    f0bcf82d1c2d3d5b1727aad703842731b18c254093075895e13ba3dba8ddda6b pytorch_model-00005-of-00030.bin
+    dd0a8d88eae3f2d217e25428a0bead92f530496cefbf8d59136077a13ed8dd12 pytorch_model-00006-of-00030.bin
+    3a39fa019c618945afe160bc3dcdcfe13109b80d6ccbf6bd51089d34927afd16 pytorch_model-00007-of-00030.bin
+    4835397d22a3873788efc239cd231c8a28b9074bb09c8763733ff4e3e1fe3243 pytorch_model-00008-of-00030.bin
+    ec5266249c093e52ac131860ce82da48571003b0e7e15cd61f95e5a929fff175 pytorch_model-00009-of-00030.bin
+    b4b5bddafce7fc9d33e9cf51891b6a706ed854988a3282c31fac723b492100cf pytorch_model-00010-of-00030.bin
+    5710bf00a9442f145ce9292fb34e572837933e26b3fea793518db746e19a05d9 pytorch_model-00011-of-00030.bin
+    a7cc3f315c90b4088bcb49df8da12ff9f64d214a646ae48d9bc3e7e216dd30f5 pytorch_model-00012-of-00030.bin
+    1b0bf669f6a88a1badae42ad498629cf3e579221bcb2c2c39640597c7adb0487 pytorch_model-00013-of-00030.bin
+    3458275d165c5871981e7cec4cf6612f74665e1b7446888b08dcc1a0f37a52a1 pytorch_model-00014-of-00030.bin
+    97490810a62d0066a1f25b8c48d97c980e5dad9d57cf0c56c2eab8d63dcaf1fd pytorch_model-00015-of-00030.bin
+    c54ff0613065047f1f2833179bafdd964f549516da482491da710fe875d257e9 pytorch_model-00016-of-00030.bin
+    abe4a3e63818bb717b2faaaa932abbf282680420110270eb44c5f456db52b03d pytorch_model-00017-of-00030.bin
+    902ed056ab6db0d93b0707f471b4e517f4c15fc2457c21db8f9958c93b1fdc5c pytorch_model-00018-of-00030.bin
+    495563200ef15dee3b7531f746eaaf9a72f78a363bdd214aa3153ff29cbcb159 pytorch_model-00019-of-00030.bin
+    224c999ebdadc8546de87fcfdd015837aa731e20bd914c9ea54d575be43b7bce pytorch_model-00020-of-00030.bin
+    3a43ce4750ca93e34d60e0e2e8784c6efb30b7e2766579625141279653eb842b pytorch_model-00021-of-00030.bin
+    3c1ec287a1948a05f69db9e97dbf919cbe63936374d51b1090e247be5816ef20 pytorch_model-00022-of-00030.bin
+    41e2e8e8bc7eecf9ad409443bedec34ce6e2bd0eda8194513ca76cbbc68a6343 pytorch_model-00023-of-00030.bin
+    a8acdbb0a5f0439a9abcab925d92bc070c393f3a82db885e40176f9789402532 pytorch_model-00024-of-00030.bin
+    14c346cee257c0e04fd6cfe72670e44ed01be57a042060ade265c5350ad970d7 pytorch_model-00025-of-00030.bin
+    c76075e21eecf21ce47ae019ef3454eb111e1f0d9662f4d2d685b0f19e47ad02 pytorch_model-00026-of-00030.bin
+    f392fba089edd704e6d0113774730dfd9db9aea8bc6b96ea8433434b65e4bc03 pytorch_model-00027-of-00030.bin
+    6749f1dfe540beda096dc11527cc6fc300b7a1500abc697542dfd5d61c53541f pytorch_model-00028-of-00030.bin
+    dc80bf660517e7d5a0b25d1d3e447c83ea81e5aef681cc987f2ecb03fa40af75 pytorch_model-00029-of-00030.bin
+    994d75dec49cf52785e3688af0d8c159da4282454426f46e95c04bc2f8e03866 pytorch_model-00030-of-00030.bin