Update README.md

README.md

@@ -5,8 +5,8 @@ license: other
 license_name: llama3
 license_link: LICENSE
 language:
-- en
 - ko
+- en
 tags:
 - meta
 - llama
@@ -20,6 +20,7 @@ library_name: transformers
 
 
 # AKALLAMA
+
 We introduce AKALLAMA-70B, korean focused opensource 70b large language model. 
 It demonstrate considerable improvement in korean fluence, specially compared to base llama 3 model.
 To our knowledge, this is one of the first 70b opensource Korean-speaking language models.
@@ -28,30 +29,77 @@ To our knowledge, this is one of the first 70b opensource Korean-speaking langua
 
 This is the model card of a 🤗 transformers model that has been pushed on the Hub.
 
-- **Developed by:** [mirlab](https://mirlab.yonsei.ac.kr/)
+- **Developed by:** [Yonsei MIRLab](https://mirlab.yonsei.ac.kr/)
 - **Language(s) (NLP):** Korean, English
 - **License:** llama3
-- **Finetuned from model:** [meta-llama/Meta-Llama-3-70B](https://huggingface.co/meta-llama/Meta-Llama-3-70B)
+- **Finetuned from model:** [meta-llama/Meta-Llama-3-70B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-70B-Instruct)
+
+## How to use
+
+This repo provides full model weight files for AkaLlama-70B-v0.1.
+
+# Use with transformers
+
+See the snippet below for usage with Transformers:
+
+```
+import transformers
+import torch
+
+model_id = "mirlab/AkaLlama-llama3-70b-v0.1"
+
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": torch.bfloat16},
+    device="auto",
+)
+
+system_prompt = """
+"""
+
+messages = [
+    {"role": "system", "content": "system_prompt"},
+    {"role": "user", "content": "네 이름은 뭐야?"},
+]
+
+prompt = pipeline.tokenizer.apply_chat_template(
+        messages, 
+        tokenize=False, 
+        add_generation_prompt=True
+)
 
-## Evaluation
+terminators = [
+    pipeline.tokenizer.eos_token_id,
+    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
 
-For local inferencing and evaluation, we highly recommend using the Ollama library. 
-Check _Customize a model section_ of [Ollama github page](https://github.com/ollama/ollama)
+outputs = pipeline(
+    prompt,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+print(outputs[0]["generated_text"][len(prompt):])
+```
 
 ## Training Details
 ### Training Procedure
 
-We closely followed training procedure of Zephyr ORPO model.
+We trained AkaLlama using a preference learning alignment algorithm called [Odds Ratio Preference Optimization (ORPO)](https://huggingface.co/papers/2403.07691).
+Our training pipeline is almost identical to that of [HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1](https://huggingface.co/HuggingFaceH4/zephyr-orpo-141b-A35b-v0.1), aside from minor hyperparameter changes.
 Please check out Huggingface's [alignment handbook](https://github.com/huggingface/alignment-handbook?tab=readme-ov-file) for further details, including the chat template. 
 
 ### Training Data
 
-Detailed descriptions regarding training data will be announced later. 
+Detailed descriptions regarding training data will be announced later.
 
 ### Examples
 
-## Thanks to
+WIP
 
-- A100 클러스터를 제공해주신, 연세대학교 인공지능학과 데이터센터
-- 
+## Special Thanks
 
+- Data Center of the Department of Artificial Intelligence at Yonsei University for the computation resources