Update README.md

README.md

@@ -7,6 +7,10 @@ datasets:
 language:
 - en
 - th
+- zh
+metrics:
+- accuracy
+pipeline_tag: question-answering
 ---
 
 
@@ -18,7 +22,6 @@ language:
 <!-- Provide a longer summary of what this model is. -->
 
 
-
 - **Developed by:** [Jixin Yang @ HKUST]
 - **Model type:** [PEFT (LoRA) fine-tuned LLaMA-2 7B for backward text generation]
 - **Finetuned from model [optional]:** [meta-llama/Llama-2-7b-hf]
@@ -26,14 +29,7 @@ language:
 
 
 ## Uses
-
-<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
-
-### Direct Use
-
-<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
-
-[This model is designed for backward text generation - given an output text, it generates the corresponding input.]
+This model is designed for backward text generation - given an output text, it generates the corresponding input.
 
 
 
@@ -41,7 +37,7 @@ language:
 
 Use the code below to get started with the model.
 
-[from transformers import AutoModelForCausalLM, AutoTokenizer
+from transformers import AutoModelForCausalLM, AutoTokenizer
 
 model_name = "jasperyeoh2/llama2-7b-backward-model"
 tokenizer = AutoTokenizer.from_pretrained(model_name)
@@ -50,7 +46,7 @@ model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")
 input_text = "Output text to reverse"
 inputs = tokenizer(input_text, return_tensors="pt").to("cuda")
 outputs = model.generate(**inputs, max_new_tokens=50)
-print(tokenizer.decode(outputs[0], skip_special_tokens=True))]
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
 
 ## Training Details
 
@@ -58,9 +54,9 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))]
 
 <!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
 
-[- Dataset: [OpenAssistant-Guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco)
+- Dataset: [OpenAssistant-Guanaco](https://huggingface.co/datasets/timdettmers/openassistant-guanaco)
 - Number of examples used: ~3,200
-- Task: Instruction Backtranslation (Answer → Prompt)]
+- Task: Instruction Backtranslation (Answer → Prompt)
 
 ### Training Procedure
 
@@ -68,7 +64,7 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))]
 
 #### Preprocessing [optional]
 
-[- Method: PEFT with LoRA (Low-Rank Adaptation)
+- Method: PEFT with LoRA (Low-Rank Adaptation)
 - Quantization: 4-bit (NF4)
 - LoRA config:
   - `r`: 8
@@ -83,7 +79,7 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))]
 - Learning rate: 2e-5
 - Scheduler: linear with warmup
 - Optimizer: AdamW
-- Early stopping: enabled (patience=2)]
+- Early stopping: enabled (patience=2)
 
 
 #### Metrics
@@ -102,8 +98,6 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))]
 
 ### Compute Infrastructure
 
-[#### Hardware
-
 - GPU: 1× NVIDIA A800 (80GB)
 - CUDA Version: 12.1
 
@@ -118,7 +112,7 @@ print(tokenizer.decode(outputs[0], skip_special_tokens=True))]
 
 #### Hardware
 
-[NVIDIA A800 GPU]
+NVIDIA A800 GPU
 
 
 ### Framework versions