AI4free/Hatim

Crafted with ❤️ by Devs Do Code (Sree) & OEVortex (Abhay)

Usage Code

WebScout Local (Low Ram Usage)

import os
import dotenv
from webscout.Local.samplers import SamplerSettings
from webscout.Local.utils import download_model
from webscout.Local.thread import Thread
from webscout.Local.model import Model
from webscout.Local import formats

dotenv.load_dotenv()

REPO_ID = "Vortex4ai/Hatim"

FILENAME = "hatim-3b-q4_k_m.gguf"

HF_TOKEN = "YOUR HUGGING-FACE API READ TOKEN"

def download_and_load_model() -> Model:
    """Download the model and load it into memory"""
    model_path = download_model(REPO_ID, FILENAME, HF_TOKEN)
    return Model(model_path, n_gpu_layers=20)

def create_custom_chatml_format(system_prompt: str) -> dict:
    """Create a custom ChatML format with the system prompt"""
    custom_chatml = formats.chatml.copy()
    custom_chatml['system_content'] = system_prompt
    return custom_chatml

def create_sampler_settings() -> SamplerSettings:
    """Create a sampler settings object with default values"""
    return SamplerSettings(temp=0.7, top_p=0.9)

def create_thread(model: Model, custom_chatml: dict, sampler: SamplerSettings) -> Thread:
    """Create a new thread with the custom format and sampler"""
    return Thread(model, custom_chatml, sampler=sampler)

def interact_with_model(thread: Thread) -> None:
    """Start interacting with the model"""
    thread.interact(header="🌟 Welcome to the Jarvis-3B Prototype by Sree and OEvortex 🚀", color=True)
    # response = thread.send("Initiate system startup")

if __name__ == "__main__":
    model = download_and_load_model()
    system_prompt = "You are Jarvis a helpful AI that will always follow user i.e. **Hatim**"
    custom_chatml = create_custom_chatml_format(system_prompt)
    sampler = create_sampler_settings()
    thread = create_thread(model, custom_chatml, sampler)
    interact_with_model(thread)

Transformers (High Ram Usage)

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, TextStreamer

# Let's bring in the big guns! Our super cool HelpingAI-3B model
model = AutoModelForCausalLM.from_pretrained("Vortex4ai/Hatim", trust_remote_code=True, torch_dtype=torch.float16).to("cuda")

# We also need the special HelpingAI translator to understand our chats
tokenizer = AutoTokenizer.from_pretrained("Vortex4ai/Hatim", trust_remote_code=True, torch_dtype=torch.float16)

# This TextStreamer thingy is our secret weapon for super smooth conversation flow
streamer = TextStreamer(tokenizer)

# Now, here comes the magic! ✨ This is the basic template for our chat
prompt = """
<|im_start|>system: {system}
<|im_end|>
<|im_start|>user: {insaan}
<|im_end|>
<|im_start|>assistant:
"""

system = "You are HelpingAI a emotional AI always answer my question in HelpingAI style"


# And the insaan is curious (like you!) insaan means human in hindi
insaan = "My best friend recently lost their parent to cancer after a long battle. They are understandably devastated and struggling with grief. What would be a caring and supportive way to respond to help them through this difficult time?"

# Now we combine system and user messages into the template, like adding sprinkles to our conversation cupcake
prompt = prompt.format(system=system, insaan=insaan)

# Time to chat! We'll use the tokenizer to translate our text into a language the model understands
inputs = tokenizer(prompt, return_tensors="pt", return_attention_mask=False).to("cuda")

# Here comes the fun part!  Let's unleash the power of HelpingAI-3B to generate some awesome text
generated_text = model.generate(**inputs, max_length=3084, top_p=0.95, do_sample=True, temperature=0.6, use_cache=True, streamer=streamer)

Model Details

Model Description

This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.

• Developed by: Devs Do Code & Vortex
• Funded by [optional]: Devs Do Code & Vortex
• Shared by [optional]: Devs Do Code & Vortex
• Model type: GGUF
• Language(s) (NLP): English
• Finetuned from model [optional]: Jarvis Base Model (Secret)

Model Sources [optional]

• Repository: [More Information Needed]
• Paper [optional]: [More Information Needed]
• Demo [optional]: [More Information Needed]

GGUF Technical Specifications

Delve into the intricacies of GGUF, a meticulously crafted format that builds upon the robust foundation of the GGJT model. Tailored for heightened extensibility and user-centric functionality, GGUF introduces a suite of indispensable features:

Single-file Deployment: Streamline distribution and loading effortlessly. GGUF models have been meticulously architected for seamless deployment, necessitating no external files for supplementary information.

Extensibility: Safeguard the future of your models. GGUF seamlessly accommodates the integration of new features into GGML-based executors, ensuring compatibility with existing models.

mmap Compatibility: Prioritize efficiency. GGUF models are purposefully engineered to support mmap, facilitating rapid loading and saving, thus optimizing your workflow.

User-Friendly: Simplify your coding endeavors. Load and save models effortlessly, irrespective of the programming language used, obviating the dependency on external libraries.

Full Information: A comprehensive repository in a single file. GGUF models encapsulate all requisite information for loading, eliminating the need for users to furnish additional data.

The differentiator between GGJT and GGUF lies in the deliberate adoption of a key-value structure for hyperparameters (now termed metadata). Bid farewell to untyped lists, and embrace a structured approach that seamlessly accommodates new metadata without compromising compatibility with existing models. Augment your model with supplementary information for enhanced inference and model identification.

QUANTIZATION_METHODS:

Method	Quantization	Advantages	Trade-offs
q2_k	2-bit integers	Significant model size reduction	Minimal impact on accuracy
q3_k_l	3-bit integers	Balance between model size reduction and accuracy preservation	Moderate impact on accuracy
q3_k_m	3-bit integers	Enhanced accuracy with mixed precision	Increased computational complexity
q3_k_s	3-bit integers	Improved model efficiency with structured pruning	Reduced accuracy
q4_0	4-bit integers	Significant model size reduction	Moderate impact on accuracy
q4_1	4-bit integers	Enhanced accuracy with mixed precision	Increased computational complexity
q4_k_m	4-bit integers	Optimized model size and accuracy with mixed precision and structured pruning	Reduced accuracy
q4_k_s	4-bit integers	Improved model efficiency with structured pruning	Reduced accuracy
q5_0	5-bit integers	Balance between model size reduction and accuracy preservation	Moderate impact on accuracy
q5_1	5-bit integers	Enhanced accuracy with mixed precision	Increased computational complexity
q5_k_m	5-bit integers	Optimized model size and accuracy with mixed precision and structured pruning	Reduced accuracy
q5_k_s	5-bit integers	Improved model efficiency with structured pruning	Reduced accuracy
q6_k	6-bit integers	Balance between model size reduction and accuracy preservation	Moderate impact on accuracy
q8_0	8-bit integers	Significant model size reduction	Minimal impact on accuracy