license: apache-2.0
language:
- fr
pipeline_tag: text-generation
library_name: transformers
tags:
- LLM
inference: false
I am continuously enhancing the structure of these model descriptions, and they now provide even more comprehensive information to help you find the best models for your specific needs.
vigogne-falcon-7b-instruct - GGUF
- Model creator: bofenghuang
- Original model: vigogne-falcon-7b-instruct
Note: Important Update for Falcon Models in llama.cpp Versions After October 18, 2023
As noted on the [Llama.cpp](ggerganov/llama.cpp: Port of Facebook's LLaMA model in C/C++ (github.com) GitHub repository, all new releases of Llama.cpp will require a re-quantization due to the implementation of the new BPE tokenizer. I am working diligently to make the updated models available for you.
Here's what you need to know:
Stay Informed: Application software using llama.cpp libraries will follow soon. Keep an eye on the release schedules of your favorite software applications that rely on llama.cpp. They will likely provide instructions on how to integrate the new models. Monitor Upload Times: Please keep a close watch on the upload times of the available files on my Hugging Face Model pages. This will help you identify which files have already been updated and are ready for download, ensuring you have the most current Falcon models at your disposal. Download Promptly: Once the updated Falcon models are available on my Hugging Face page, be sure to download them promptly to ensure compatibility with the latest [llama.cpp](ggerganov/llama.cpp: Port of Facebook's LLaMA model in C/C++ (github.com) versions. Please understand that this change specifically affects Falcon and Starcoder models, other models remain unaffected. Consequently, software providers may not emphasize this change as prominently. As a solo operator of this page, I'm doing my best to expedite the process, but please bear with me as this may take some time.
Brief
Vigogne-Falcon-7B-Instruct is a Falcon-7B model fine-tuned to follow the French instructions.
About GGUF format
gguf is the current file format used by the ggml library.
A growing list of Software is using it and can therefore use this model.
The core project making use of the ggml library is the llama.cpp project by Georgi Gerganov
Quantization variants
There is a bunch of quantized files available. How to choose the best for you:
Legacy quants
Q4_0, Q4_1, Q5_0, Q5_1 and Q8 are legacy quantization types.
Nevertheless, they are fully supported, as there are several circumstances that cause certain model not to be compatible with the modern K-quants.
Falcon 7B models cannot be quantized to K-quants.
K-quants
K-quants are based on the idea that the quantization of certain parts affects the quality in different ways. If you quantize certain parts more and others less, you get a more powerful model with the same file size, or a smaller file size and lower memory load with comparable performance. So, if possible, use K-quants. With a Q6_K you should find it really hard to find a quality difference to the original model - ask your model two times the same question and you may encounter bigger quality differences.
Original Model Card:
Vigogne-Falcon-7B-Instruct: A French Instruction-following Falcon Model
Vigogne-Falcon-7B-Instruct is a Falcon-7B model fine-tuned to follow the French instructions.
For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne
Usage
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
from vigogne.preprocess import generate_instruct_prompt
model_name_or_path = "bofenghuang/vigogne-falcon-7b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path, padding_side="right", use_fast=False)
tokenizer.pad_token = tokenizer.eos_token
model = AutoModelForCausalLM.from_pretrained(
model_name_or_path,
torch_dtype=torch.float16,
device_map="auto",
trust_remote_code=True,
)
user_query = "Expliquez la différence entre DoS et phishing."
prompt = generate_instruct_prompt(user_query)
input_ids = tokenizer(prompt, return_tensors="pt")["input_ids"].to(model.device)
input_length = input_ids.shape[1]
generated_outputs = model.generate(
input_ids=input_ids,
generation_config=GenerationConfig(
temperature=0.1,
do_sample=True,
repetition_penalty=1.0,
max_new_tokens=512,
),
return_dict_in_generate=True,
pad_token_id=tokenizer.eos_token_id,
eos_token_id=tokenizer.eos_token_id,
)
generated_tokens = generated_outputs.sequences[0, input_length:]
generated_text = tokenizer.decode(generated_tokens, skip_special_tokens=True)
print(generated_text)
You can also infer this model by using the following Google Colab Notebook.
Limitations
Vigogne is still under development, and there are many limitations that have to be addressed. Please note that it is possible that the model generates harmful or biased content, incorrect information or generally unhelpful answers.
End of original Model File
Please consider to support my work
Coming Soon: I'm in the process of launching a sponsorship/crowdfunding campaign for my work. I'm evaluating Kickstarter, Patreon, or the new GitHub Sponsors platform, and I am hoping for some support and contribution to the continued availability of these kind of models. Your support will enable me to provide even more valuable resources and maintain the models you rely on. Your patience and ongoing support are greatly appreciated as I work to make this page an even more valuable resource for the community.
