license: apache-2.0
language:
- fr
pipeline_tag: text-generation
library_name: transformers
tags:
- LLM
inference: false
I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information
vigogne-falcon-7b-chat - GGUF
- Model creator: bofenghuang
- Original model: vigogne-falcon-7b-chat
K-Quants in Falcon 7b models
New releases of Llama.cpp now support K-quantization for previously incompatible models, in particular all Falcon 7B models (While Falcon 40b is and always has been fully compatible with K-Quantisation). This is achieved by employing a fallback solution for model layers that cannot be quantized with real K-quants.
For Falcon 7B models, although only a quarter of the layers can be quantized with true K-quants, this approach still benefits from utilizing different legacy quantization types Q4_0, Q4_1, Q5_0, and Q5_1. As a result, it offers better quality at the same file size or smaller file sizes with comparable performance.
So this solution ensures improved performance and efficiency over legacy Q4_0, Q4_1, Q5_0 and Q5_1 Quantizations.
Brief
Vigogne-Falcon-7B-Chat is a Falcon-7B model fine-tuned to conduct multi-turn dialogues in French between human user and AI assistant.
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 to cater to your specific needs. Here's how to choose the best option 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.
Note:
Now there's a new option to use K-quants even for previously 'incompatible' models, although this involves some fallback solution that makes them not real K-quants. More details can be found in affected model descriptions. (This mainly refers to Falcon 7b and Starcoder models)
K-quants
K-quants are designed with the idea that different levels of quantization in specific parts of the model can optimize performance, file size, and memory load. So, if possible, use K-quants. With a Q6_K, you'll likely find it challenging to discern a quality difference from the original model - ask your model two times the same question and you may encounter bigger quality differences.
Original Model Card:
Vigogne-Falcon-7B-Chat: A French Chat Falcon Model
Vigogne-Falcon-7B-Chat is a Falcon-7B model fine-tuned to conduct multi-turn dialogues in French between human user and AI assistant.
For more information, please visit the Github repo: https://github.com/bofenghuang/vigogne
Changelog
All versions are available in branches.
- V1.0: Initial release.
- V2.0: Expanded training dataset to 419k for better performance.
Usage
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer, GenerationConfig
from vigogne.preprocess import generate_inference_chat_prompt
model_name_or_path = "bofenghuang/vigogne-falcon-7b-chat"
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_inference_chat_prompt([[user_query, ""]], tokenizer=tokenizer)
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)
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.
