Update README.md

README.md

@@ -1,3 +1,54 @@
 ---
 license: mit
 ---
+LoRA weights only and trained for research - nothing from the foundation model. Trained using Open-Assistant's dataset. Shout-out to Open-Assistant and LAION for giving us early research access to the dataset.
+
+Sample usage
+
+import torch
+import os
+import transformers
+from peft import PeftModel
+from transformers import LlamaTokenizer, LlamaForCausalLM
+
+model_path = "decapoda-research/llama-7b-hf"
+peft_path = 'serpdotai/llama-oasst-lora-7B'
+tokenizer_path = 'decapoda-research/llama-7b-hf'
+
+model = LlamaForCausalLM.from_pretrained(model_path, load_in_8bit=True, device_map="auto") # or something like {"": 0}
+model = PeftModel.from_pretrained(model, peft_path, torch_dtype=torch.float16, device_map="auto") # or something like {"": 0}
+tokenizer = LlamaTokenizer.from_pretrained(tokenizer_path)
+
+batch = tokenizer("\n\nUser: Are you sentient?\n\nAssistant:", return_tensors="pt")
+
+with torch.no_grad():
+    out = model.generate(
+        input_ids=batch["input_ids"].cuda(),
+        attention_mask=batch["attention_mask"].cuda(),
+        max_length=100,
+        do_sample=True,
+        top_k=50,
+        top_p=1.0,
+        temperature=1.0
+    )
+print(tokenizer.decode(out[0]))
+
+The model will continue the conversation between the user and itself. If you want to use as a chatbot you can alter the generate method to include stop sequences for 'User:' and 'Assistant:' or strip off anything past the assistant's original response before returning.
+
+Trained for 4 epochs with a sequence length of 2048 on 8 A6000s with an effective batch size of 120.
+
+Training settings:
+
+lr: 2.0e-04
+lr_scheduler_type: linear
+warmup_ratio: 0.06
+weight_decay: 0.1
+optimizer: adamw_torch
+LoRA config:
+
+target_modules: ['q_proj', 'k_proj', 'v_proj', 'o_proj']
+r: 64
+lora_alpha: 32
+lora_dropout: 0.05
+bias: "none"
+task_type: "CAUSAL_LM"