Update README.md

README.md

@@ -1,10 +1,11 @@
 ---
 license: llama3
-library_name: peft
+library_name: transformers
 tags:
-- trl
-- sft
 - generated_from_trainer
+- medical
+- Healthcare & Lifesciences
+- BioMed
 base_model: meta-llama/Meta-Llama-3-8B-Instruct
 thumbnail: https://collaiborate.com/logo/logo-blue-bg-1.png
 model-index:
@@ -74,13 +75,10 @@ Collaiborator-MEDLLM-Llama-3-8b-v1 was trained using an NVIDIA A40 GPU, which pr
 ## How to use
 
 import transformers
-
 import torch
 
-
 model_id = "collaiborateorg/Collaiborator-MEDLLM-Llama-3-8B-v1"
 
-
 pipeline = transformers.pipeline(
     "text-generation",
     model=model_id,
@@ -88,26 +86,22 @@ pipeline = transformers.pipeline(
     device_map="auto",
 )
 
-
 messages = [
     {"role": "system", "content": "You are an expert trained on healthcare and biomedical domain!"},
     {"role": "user", "content": "I'm a 35-year-old male and for the past few months, I've been experiencing fatigue, increased sensitivity to cold, and dry, itchy skin. What is the diagnosis here?"},
 ]
 
-
 prompt = pipeline.tokenizer.apply_chat_template(
         messages, 
         tokenize=False, 
         add_generation_prompt=True
 )
 
-
 terminators = [
     pipeline.tokenizer.eos_token_id,
     pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
 ]
 
-
 outputs = pipeline(
     prompt,
     max_new_tokens=256,
@@ -116,7 +110,6 @@ outputs = pipeline(
     temperature=0.6,
     top_p=0.9,
 )
-
 print(outputs[0]["generated_text"][len(prompt):])
 
 ### Contact Information
@@ -131,7 +124,7 @@ Website: https://www.collaiborate.com
 
 The following hyperparameters were used during training:
 - learning_rate: 0.0002
-- train_batch_size: 8
+- train_batch_size: 12
 - eval_batch_size: 8
 - seed: 42
 - gradient_accumulation_steps: 4
@@ -139,6 +132,7 @@ The following hyperparameters were used during training:
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - lr_scheduler_warmup_ratio: 0.03
+- training_steps: 2000
 - mixed_precision_training: Native AMP
 
 ### Framework versions
@@ -151,7 +145,7 @@ The following hyperparameters were used during training:
 
 ### Citation
 
-If you use Collaiborator-MEDLLM-Llama-3-8b-v1 in your research or applications, please cite it as follows:
+If you use Collaiborator-MEDLLM-Llama-3-8b in your research or applications, please cite it as follows:
 
 @misc{Collaiborator_MEDLLM,
   author = Collaiborator,