library_name: transformers
license: apache-2.0
pipeline_tag: text-generation
tags:
- ExLlamaV2
- 4bit
- Mistral
- Mistral-7B
- quantized
- exl2
- 4.0-bpw
Model Card for alokabhishek/Mistral-7B-Instruct-v0.2-4.0-bpw-exl2
This repo contains 4-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 4 bit 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-v0.2-4.0-bpw-exl2"
BPW = 4.0
# 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-v0.2-4.0-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)
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]
Original Model Card for Mistral-7B-Instruct-v0.2
The Mistral-7B-Instruct-v0.2 Large Language Model (LLM) is an instruct fine-tuned version of the Mistral-7B-v0.2.
Mistral-7B-v0.2 has the following changes compared to Mistral-7B-v0.1
- 32k context window (vs 8k context in v0.1)
- Rope-theta = 1e6
- No Sliding-Window Attention
For full details of this model please read our paper and release blog post.
Instruction format
In order to leverage instruction fine-tuning, your prompt should be surrounded by [INST]
and [/INST]
tokens. The very first instruction should begin with a begin of sentence id. The next instructions should not. The assistant generation will be ended by the end-of-sentence token id.
E.g.
text = "<s>[INST] What is your favourite condiment? [/INST]"
"Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!</s> "
"[INST] Do you have mayonnaise recipes? [/INST]"
This format is available as a chat template via the apply_chat_template()
method:
from transformers import AutoModelForCausalLM, AutoTokenizer
device = "cuda" # the device to load the model onto
model = AutoModelForCausalLM.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
tokenizer = AutoTokenizer.from_pretrained("mistralai/Mistral-7B-Instruct-v0.2")
messages = [
{"role": "user", "content": "What is your favourite condiment?"},
{"role": "assistant", "content": "Well, I'm quite partial to a good squeeze of fresh lemon juice. It adds just the right amount of zesty flavour to whatever I'm cooking up in the kitchen!"},
{"role": "user", "content": "Do you have mayonnaise recipes?"}
]
encodeds = tokenizer.apply_chat_template(messages, return_tensors="pt")
model_inputs = encodeds.to(device)
model.to(device)
generated_ids = model.generate(model_inputs, max_new_tokens=1000, do_sample=True)
decoded = tokenizer.batch_decode(generated_ids)
print(decoded[0])
Troubleshooting
- If you see the following error:
Traceback (most recent call last):
File "", line 1, in
File "/transformers/models/auto/auto_factory.py", line 482, in from_pretrained
config, kwargs = AutoConfig.from_pretrained(
File "/transformers/models/auto/configuration_auto.py", line 1022, in from_pretrained
config_class = CONFIG_MAPPING[config_dict["model_type"]]
File "/transformers/models/auto/configuration_auto.py", line 723, in getitem
raise KeyError(key)
KeyError: 'mistral'
Installing transformers from source should solve the issue pip install git+https://github.com/huggingface/transformers
This should not be required after transformers-v4.33.4.
Limitations
The Mistral 7B Instruct model is a quick demonstration that the base model can be easily fine-tuned to achieve compelling performance. It does not have any moderation mechanisms. We're looking forward to engaging with the community on ways to make the model finely respect guardrails, allowing for deployment in environments requiring moderated outputs.
The Mistral AI Team
Albert Jiang, Alexandre Sablayrolles, Arthur Mensch, Blanche Savary, Chris Bamford, Devendra Singh Chaplot, Diego de las Casas, Emma Bou Hanna, Florian Bressand, Gianna Lengyel, Guillaume Bour, Guillaume Lample, Lélio Renard Lavaud, Louis Ternon, Lucile Saulnier, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Théophile Gervet, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed.