Upload README.md

README.md

@@ -81,22 +81,24 @@ The following `bitsandbytes` quantization config was used during training:
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 
-model_id = "mrm8488/llama-2-coder-7b"
+model_id = "edumunozsala/llama-2-7b-int4-python-code-20k"
 
-tokenizer = AutoTokenizer.from_pretrained(model_id)
+tokenizer = AutoTokenizer.from_pretrained(hf_model_repo)
 
-model = AutoModelForCausalLM.from_pretrained(model_id).to("cuda")
+model = AutoModelForCausalLM.from_pretrained(hf_model_repo, load_in_4bit=True, torch_dtype=torch.float16, 
+                                             device_map=device_map)
 
-sample = dataset[randrange(len(dataset))]
+instruction="Write a Python function to display the first and last elements of a list."
+input=""
 
 prompt = f"""### Instruction:
 Use the Task below and the Input given to write the Response, which is a programming code that can solve the Task.
 
 ### Task:
-{sample['instruction']}
+{instruction}
 
 ### Input:
-{sample['input']}
+{input}
 
 ### Response:
 """
@@ -107,7 +109,6 @@ outputs = model.generate(input_ids=input_ids, max_new_tokens=100, do_sample=True
 
 print(f"Prompt:\n{prompt}\n")
 print(f"Generated instruction:\n{tokenizer.batch_decode(outputs.detach().cpu().numpy(), skip_special_tokens=True)[0][len(prompt):]}")
-print(f"Ground truth:\n{sample['output']}")
 
 ```