Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,15 @@ saved_model/**/* 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
+compiled/014f9e0f66728f19429b.neff filter=lfs diff=lfs merge=lfs -text
+compiled/0cfaffdcfdbd5a217685.neff filter=lfs diff=lfs merge=lfs -text
+compiled/20a998c1e2b2fac0e029.neff filter=lfs diff=lfs merge=lfs -text
+compiled/366225effb325603b39c.neff filter=lfs diff=lfs merge=lfs -text
+compiled/43618e9d5a7af44b2f47.neff filter=lfs diff=lfs merge=lfs -text
+compiled/5ca18545e6b19c345a40.neff filter=lfs diff=lfs merge=lfs -text
+compiled/6a7ed55d61647f668cae.neff filter=lfs diff=lfs merge=lfs -text
+compiled/954e6d9355da77842d33.neff filter=lfs diff=lfs merge=lfs -text
+compiled/9e760b2f376143a0f380.neff filter=lfs diff=lfs merge=lfs -text
+compiled/a0cb8512168ca10205b9.neff filter=lfs diff=lfs merge=lfs -text
+compiled/bc969b06aa6c80aab625.neff filter=lfs diff=lfs merge=lfs -text
+compiled/c6bc2fbdbc03296ac8a5.neff filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,40 @@
+---
+license: cc-by-sa-4.0
+base_model: meta-llama/Llama-2-7b
+language:
+  - yue
+pipeline_tag: text-generation
+tags:
+  - cantonese
+  - llama-2
+  - Powered by AWS Trainium
+---
+
+# Cantonese LLM using Llama-2 7B Architecture
+
+Welcome to the preview of the Cantonese Language Model (LLM) built on the Llama-2 7B architecture. This model is designed to understand and generate text in Cantonese, including slangs, colloquials, and Internet terms.
+
+## License
+This project is available under the Creative Commons Attribution-ShareAlike 4.0 International License (CC BY-SA 4.0). For more details, please visit the [license page](https://creativecommons.org/licenses/by-sa/4.0/).
+
+## Preview Warning
+Please be advised that this version of the Cantonese LLM is a **preview**. As such, the model's outputs may sometimes be inaccurate, hallucinatory, or potentially offensive to some individuals. We are continuously working to improve the model's accuracy and reduce such instances.
+
+## Training Infrastructure
+The Cantonese LLM has been trained using Amazon HyperPod and AWS Trainium chips.
+
+## Training Credits
+This model was trained by [Votee AI Limited](https://huggingface.co/votee), and we contribute to [hon9kon9ize](https://hon9kon9ize.com/), the Hong Kong AI Research Community.
+
+## Usage Guidelines
+- Ensure that you are aware of the potential for unexpected or offensive content.
+- Always review and assess the model's output before using it in any application.
+- Provide feedback on any issues you encounter to help us improve the model.
+
+## Contributions
+We welcome contributions from the community. If you have suggestions or improvements, please submit a pull request or open an issue in the project repository.
+
+## Disclaimer
+The developers of the Cantonese LLM are not responsible for any harm or offense caused by the model's outputs. Users are advised to exercise discretion and judgment when using the model.
+
+Thank you for exploring the Cantonese LLM. We are excited to see the innovative ways in which it will be used!

compiled/014f9e0f66728f19429b.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02efa6ff620ff3f97bc1723d0992016eba1f1018b0919c1cf6e8c133290d69e5
+size 12452864

compiled/0cfaffdcfdbd5a217685.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fcbc5fc5791df4d19d9547e3eaf6b60f7a3fee0ef494264727f2b88572094a74
+size 21556224

compiled/20a998c1e2b2fac0e029.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6028a12471abd09662eaa30f35be31f3f713722d6976a8353253548e4678a2b5
+size 11203584

compiled/366225effb325603b39c.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8651aa6df6702dcd52dbfd3036c70b14c4b95f1f5cf4a86c18044dfff9a1bb1f
+size 10415104

compiled/43618e9d5a7af44b2f47.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c4830d140e1421d7943f55d974b2a9fd51aa01b4b8df9c68ba488a4b04dc20c
+size 10251264

compiled/5ca18545e6b19c345a40.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:766383b4fd27ceb3cd94c05a2abcb240dcc7b224ca2b2f59ea46a20d689f23a2
+size 12073984

compiled/6a7ed55d61647f668cae.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3d4f58ae1633c4027277dd7a0fff2309b770f6275eab78295e24c839d8db84a
+size 10404864

compiled/954e6d9355da77842d33.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85df1700ded0c026400ccee4c8d6109102bda2f958b4b170ff21080600a55e3c
+size 12657664

compiled/9e760b2f376143a0f380.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8ba49fb1e19c1fcacff2cca4dff9e12140c9a6c72929cead974dca6fc9f9353
+size 10681344

compiled/a0cb8512168ca10205b9.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a3b2415a03dd53c0935cc85c8638ce308411c5c9a91a5cda3bed79e54043e22
+size 12329984

compiled/bc969b06aa6c80aab625.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:630a0f03933dbcf7f962197a6c8641da1059a6e317cd9eb5e4f91149a2e1c0aa
+size 10179584

compiled/c6bc2fbdbc03296ac8a5.neff

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d76f2109261297c222e593e124ce2af9067944f516e74ae801fddfae58219ba
+size 4895744

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "meta-llama/Llama-2-7b-hf",
+  "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": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.31.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,17 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "max_memory": {
+    "cpu": 507036852224
+  },
+  "no_split_module_classes": [
+    "LlamaDecoderLayer"
+  ],
+  "pad_token_id": 0,
+  "special_dtypes": {},
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.31.0"
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,33 @@
+{
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}