Model Card for alokabhishek/Mistral-7B-Instruct-v0.2-5.0-bpw-exl2

This repo contains 5-bit quantized (using ExLlamaV2) model Mistral AI_'s Mistral-7B-Instruct-v0.2

Model Details

• Model creator: Mistral AI_
• Original model: Mistral-7B-Instruct-v0.2

About quantization using ExLlamaV2

• ExLlamaV2 github repo: ExLlamaV2 github repo

How to Get Started with the Model

Use the code below to get started with the model.

How to run from Python code

First install the package

# Install ExLLamaV2
!git clone https://github.com/turboderp/exllamav2
!pip install -e exllamav2

Import

from huggingface_hub import login, HfApi, create_repo
from torch import bfloat16
import locale
import torch
import os

set up variables

# Define the model ID for the desired model
model_id = "alokabhishek/Mistral-7B-Instruct-v0.2-5.0-bpw-exl2"
BPW = 5.0

# define variables
model_name =  model_id.split("/")[-1]

Download the quantized model

!git-lfs install
# download the model to loacl directory
!git clone https://{username}:{HF_TOKEN}@huggingface.co/{model_id} {model_name}

Run Inference on quantized model using

# Run model
!python exllamav2/test_inference.py -m {model_name}/ -p "Tell me a funny joke about Large Language Models meeting a Blackhole in an intergalactic Bar."

import sys, os

sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from exllamav2 import (
    ExLlamaV2,
    ExLlamaV2Config,
    ExLlamaV2Cache,
    ExLlamaV2Tokenizer,
)

from exllamav2.generator import ExLlamaV2BaseGenerator, ExLlamaV2Sampler

import time

# Initialize model and cache

model_directory = "/model_path/Mistral-7B-Instruct-v0.2-5.0-bpw-exl2/"
print("Loading model: " + model_directory)

config = ExLlamaV2Config(model_directory)
model = ExLlamaV2(config)
cache = ExLlamaV2Cache(model, lazy=True)
model.load_autosplit(cache)
tokenizer = ExLlamaV2Tokenizer(config)

# Initialize generator

generator = ExLlamaV2BaseGenerator(model, cache, tokenizer)

# Generate some text

settings = ExLlamaV2Sampler.Settings()
settings.temperature = 0.85
settings.top_k = 50
settings.top_p = 0.8
settings.token_repetition_penalty = 1.01
settings.disallow_tokens(tokenizer, [tokenizer.eos_token_id])

prompt = "Tell me a funny joke about Large Language Models meeting a Blackhole in an intergalactic Bar."

max_new_tokens = 512

generator.warmup()
time_begin = time.time()

output = generator.generate_simple(prompt, settings, max_new_tokens, seed=1234)

time_end = time.time()
time_total = time_end - time_begin

print(output)
print()
print(f"Response generated in {time_total:.2f} seconds")

Uses

Direct Use

[More Information Needed]

Out-of-Scope Use

[More Information Needed]

Bias, Risks, and Limitations

[More Information Needed]

Evaluation

Metrics

[More Information Needed]

Results

[More Information Needed]

Model Card Authors [optional]

[More Information Needed]

Model Card Contact

[More Information Needed]