Update README.md

README.md

@@ -13,10 +13,14 @@ base_model: ai21labs/Jamba-v0.1
 
 # Jambatypus-v0.1
 
-This model is a fine-tuned version of [ai21labs/Jamba-v0.1](https://huggingface.co/ai21labs/Jamba-v0.1) on the [chargoddard/Open-Platypus-Chat](https://huggingface.co/datasets/chargoddard/Open-Platypus-Chat) dataset.
+This model is a QLoRA fine-tuned version of [ai21labs/Jamba-v0.1](https://huggingface.co/ai21labs/Jamba-v0.1) on the [chargoddard/Open-Platypus-Chat](https://huggingface.co/datasets/chargoddard/Open-Platypus-Chat) dataset.
 
 It has been trained on 2xA100 80 GB using my [LazyAxolotl - Jamba](https://colab.research.google.com/drive/1alsgwZFvLPPAwIgkAxeMKHQSJYfW7DeZ?usp=sharing) notebook.
 
+This repo contains both the adapter and the merged model in FP16 precision.
+
+I recommend using the ChatML template to use this model.
+
 [<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
 <details><summary>See axolotl config</summary>
 
@@ -130,4 +134,104 @@ The following hyperparameters were used during training:
 - Transformers 4.40.0.dev0
 - Pytorch 2.1.2+cu118
 - Datasets 2.18.0
-- Tokenizers 0.15.0
+- Tokenizers 0.15.0
+
+## 💻 Usage
+
+The following code creates a Gradio chat interface with Jambatypus.
+
+```python
+!pip install -qqq -U git+https://github.com/huggingface/transformers
+!pip install -qqq mamba-ssm causal-conv1d>=1.2.0
+!pip install -qqq accelerate bitsandbytes torch datasets peft gradio
+!pip install -qqq flash-attn --no-build-isolation
+
+
+import torch
+import gradio as gr
+from threading import Thread
+from peft import PeftModel, PeftConfig
+from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig, TextIteratorStreamer
+
+STOP_TOKEN = "<|im_end|>"
+
+def predict(message, history, system_prompt, temperature, max_new_tokens, top_k, repetition_penalty, top_p):
+    # Format history with a given chat template
+    stop_token = "<|im_end|>"
+    instruction = '<|im_start|>system\n' + system_prompt + '\n<|im_end|>\n'
+    for human, assistant in history:
+        instruction += '<|im_start|>user\n' + human + '\n<|im_end|>\n<|im_start|>assistant\n' + assistant
+    instruction += '\n<|im_start|>user\n' + message + '\n<|im_end|>\n<|im_start|>assistant\n'
+    
+    streamer = TextIteratorStreamer(tokenizer, skip_prompt=True, skip_special_tokens=True)
+    enc = tokenizer([instruction], return_tensors="pt", padding=True, truncation=True)
+    input_ids, attention_mask = enc.input_ids, enc.attention_mask
+
+    generate_kwargs = dict(
+        {"input_ids": input_ids.to(device), "attention_mask": attention_mask.to(device)},
+        streamer=streamer,
+        do_sample=True,
+        temperature=temperature,
+        max_new_tokens=max_new_tokens,
+        top_k=top_k,
+        repetition_penalty=repetition_penalty,
+        top_p=top_p
+    )
+    t = Thread(target=model.generate, kwargs=generate_kwargs)
+    t.start()
+    outputs = []
+    for new_token in streamer:
+        if STOP_TOKEN in new_token:
+            outputs.append(new_token[:-len(stop_token)-1])
+            yield "".join(outputs)
+            break
+        outputs.append(new_token)
+        yield "".join(outputs)
+
+
+# Load model
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+tokenizer = AutoTokenizer.from_pretrained("ai21labs/Jamba-v0.1")
+
+# 4-bit precision quant config
+quantization_config = BitsAndBytesConfig(
+    load_in_8bit=True,
+    llm_int8_skip_modules=["mamba"]
+)
+# Load model and tokenizer with ChatML format
+model = AutoModelForCausalLM.from_pretrained(
+    "ai21labs/Jamba-v0.1",
+    trust_remote_code=True,
+    torch_dtype=torch.cuda.is_bf16_supported() and torch.bfloat16 or torch.float16,
+    attn_implementation="flash_attention_2",
+    low_cpu_mem_usage=True,
+    quantization_config=quantization_config
+)
+config = PeftConfig.from_pretrained("mlabonne/Jambatypus-v0.1")
+model = PeftModel.from_pretrained(model, "mlabonne/Jambatypus-v0.1")
+
+# Create Gradio interface
+gr.ChatInterface(
+    predict,
+    title="Jambatypus",
+    description="Chat with Jambatypus!",
+    examples=[
+        ["Can you solve the equation 2x + 3 = 11 for x?"],
+        ["Write an epic poem about Ancient Rome."],
+        ["Who was the first person to walk on the Moon?"],
+        ["Use a list comprehension to create a list of squares for numbers from 1 to 10."],
+        ["Recommend some popular science fiction books."],
+        ["Can you write a short story about a time-traveling detective?"]
+    ],
+    additional_inputs_accordion=gr.Accordion(label="⚙️ Parameters", open=False),
+    additional_inputs=[
+        gr.Textbox("Perform the task to the best of your ability.", label="System prompt"),
+        gr.Slider(0, 1, 0.8, label="Temperature"),
+        gr.Slider(128, 4096, 1024, label="Max new tokens"),
+        gr.Slider(1, 80, 40, label="Top K sampling"),
+        gr.Slider(0, 2, 1.1, label="Repetition penalty"),
+        gr.Slider(0, 1, 0.95, label="Top P sampling"),
+    ],
+    theme=gr.themes.Soft(primary_hue="green"),
+).queue().launch(share=True)
+```