Update README.md

README.md

@@ -4,75 +4,26 @@ language:
 - en
 pipeline_tag: question-answering
 ---
-# Llama-mt-lora
+# git_20
 
 <!-- Provide a quick summary of what the model is/does. -->
 
 This model is fine-tuned with LLaMA with 8 Nvidia A100-80G GPUs using 3,000,000 groups of conversations in the context of mathematics by students and facilitators on Algebra Nation (https://www.mathnation.com/). Llama-mt-lora consists of 32 layers and over 7 billion parameters, consuming up to 13.5 gigabytes of disk space. Researchers can experiment with and finetune the model to help construct math conversational AI that can effectively respond generation in a mathematical context.
 ### Here is how to use it with texts in HuggingFace
 ```python
-import torch
-import transformers
-from transformers import LlamaTokenizer, AutoModelForCausalLM
-tokenizer = LlamaTokenizer.from_pretrained("Fan21/Llama-mt-lora")
-mdoel = LlamaForCausalLM.from_pretrained(
-        "Fan21/Llama-mt-lora",
-        load_in_8bit=False,
-        torch_dtype=torch.float16,
-        device_map="auto",
-    )
-def generate_prompt(instruction, input=None):
-    if input:
-        return f"""Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.
-### Instruction:
-{instruction}
-### Input:
-{input}
-### Response:"""
-    else:
-        return f"""Below is an instruction that describes a task. Write a response that appropriately completes the request.
-### Instruction:
-{instruction}
-### Response:"""
+from transformers import AutoModelForCausalLM
+from transformers import AutoProcessor
 
-def evaluate(
-    instruction,
-    input=None,
-    temperature=0.1,
-    top_p=0.75,
-    top_k=40,
-    num_beams=4,
-    max_new_tokens=128,
-    **kwargs,
-):
-    prompt = generate_prompt(instruction, input)
-    inputs = tokenizer(prompt, return_tensors="pt")
-    input_ids = inputs["input_ids"].to(device)
-    generation_config = GenerationConfig(
-        temperature=temperature,
-        top_p=top_p,
-        top_k=top_k,
-        num_beams=num_beams,
-        **kwargs,
-    )
-    with torch.no_grad():
-        generation_output = model.generate(
-            input_ids=input_ids,
-            generation_config=generation_config,
-            return_dict_in_generate=True,
-            output_scores=True,
-            max_new_tokens=max_new_tokens,
-        )
-    s = generation_output.sequences[0]
-    output = tokenizer.decode(s)
-    return output.split("### Response:")[1].strip()
-instruction = 'write your instruction here'
-inputs = 'write your inputs here'
-output= evaluate(instruction,
-                 input=inputs,
-                 temperature=0.1,#change the parameters by yourself
-                 top_p=0.75,
-                 top_k=40,
-                 num_beams=4,
-                  max_new_tokens=128,)
+model = AutoModelForCausalLM.from_pretrained("Fan21/git_20")
+processor = AutoProcessor.from_pretrained("Fan21/git_20")
+
+image_path ='Please enter the image address here'
+image = Image.open(image_path)
+width, height = image.size
+display(image.resize((int(1 * width), int(1 * height))))
+pixel_values = processor(images=image, return_tensors="pt").pixel_values
+with torch.no_grad():
+    outputs = model.generate(pixel_values=pixel_values, max_length=50)
+
+answer = tokenizer.decode(outputs[0], skip_special_tokens=True)
 ```