Duplicate from IlyaGusev/llama_7b_ru_turbo_alpaca_lora

Co-authored-by: Ilya Gusev <[email protected]>

.gitattributes

@@ -0,0 +1,34 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Llama 7B ru_turbo_alpaca LoRA
+emoji: 👁
+colorFrom: indigo
+colorTo: yellow
+sdk: gradio
+sdk_version: 3.23.0
+app_file: app.py
+pinned: false
+duplicated_from: IlyaGusev/llama_7b_ru_turbo_alpaca_lora
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,84 @@
+import gradio as gr
+
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
+from peft import PeftModel, PeftConfig
+
+MODEL_NAME = "IlyaGusev/llama_7b_ru_turbo_alpaca_lora"
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME)
+config = PeftConfig.from_pretrained(MODEL_NAME)
+model = AutoModelForCausalLM.from_pretrained(
+    config.base_model_name_or_path,
+    load_in_8bit=True,
+    device_map="auto"
+)
+model = PeftModel.from_pretrained(model, MODEL_NAME)
+model.eval()
+
+
+def generate_prompt(instruction, input=None):
+    if input:
+        return f"Задание: {instruction}\nВход: {input}\nОтвет:"
+    return f"Задание: {instruction}\n\nОтвет:"
+
+
+def evaluate(
+    instruction,
+    input=None,
+    temperature=1.0,
+    top_p=1.0,
+    top_k=40,
+    num_beams=3,
+    max_new_tokens=256,
+    **kwargs,
+):
+    prompt = generate_prompt(instruction, input)
+    inputs = tokenizer(prompt, return_tensors="pt")
+    input_ids = inputs["input_ids"].to(model.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, skip_special_tokens=True)
+    return output.strip()
+
+
+g = gr.Interface(
+    fn=evaluate,
+    inputs=[
+        gr.components.Textbox(
+            lines=2, label="Задание", placeholder="Почему трава зеленая?"
+        ),
+        gr.components.Textbox(lines=2, label="Вход", placeholder="Нет"),
+        gr.components.Slider(minimum=0, maximum=2, value=1.0, label="Temperature"),
+        gr.components.Slider(minimum=0, maximum=1, value=0.8, label="Top p"),
+        gr.components.Slider(minimum=0, maximum=100, value=40, label="Top k"),
+        gr.components.Slider(minimum=1, maximum=5, step=1, value=4, label="Beams"),
+        gr.components.Slider(
+            minimum=1, maximum=256, step=1, value=256, label="Max tokens"
+        ),
+    ],
+    outputs=[
+        gr.inputs.Textbox(
+            lines=5,
+            label="Output",
+        )
+    ],
+    title="LLaMA 7B Ru Turbo Alpaca",
+    description="",
+)
+g.queue(concurrency_count=1)
+g.launch()

requirements.txt

@@ -0,0 +1,6 @@
+torch
+sentencepiece
+accelerate
+bitsandbytes
+git+https://github.com/huggingface/transformers.git
+git+https://github.com/huggingface/peft.git