I'm constantly enhancing these model descriptions to provide you with the most relevant and comprehensive information
gpt4all-falcon - GGUF
- Model creator: nomic-ai
- Original model: gpt4all-falcon
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.
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:
Model Card for GPT4All-Falcon
An Apache-2 licensed chatbot trained over a massive curated corpus of assistant interactions including word problems, multi-turn dialogue, code, poems, songs, and stories.
Model Details
Model Description
This model has been finetuned from Falcon
- Developed by: Nomic AI
- Model Type: A finetuned Falcon 7B model on assistant style interaction data
- Language(s) (NLP): English
- License: Apache-2
- Finetuned from model [optional]: Falcon
To download a model with a specific revision run
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("nomic-ai/gpt4all-falcon", trust_remote_code=True)
Downloading without specifying revision defaults to main/v1.0.
To use it for inference with Cuda, run
from transformers import AutoTokenizer, pipeline
import transformers
import torch
tokenizer = AutoTokenizer.from_pretrained(model_path, use_fast=False)
model.to("cuda:0")
prompt = "Describe a painting of a falcon in a very detailed way." # Change this to your prompt
prompt_template = f"### Instruction: {prompt}\n### Response:"
tokens = tokenizer(prompt_template, return_tensors="pt").input_ids.to("cuda:0")
output = model.generate(input_ids=tokens, max_new_tokens=256, do_sample=True, temperature=0.8)
# Print the generated text
print(tokenizer.decode(output[0]))
Model Sources [optional]
- Repository: https://github.com/nomic-ai/gpt4all
- Base Model Repository: https://huggingface.co/tiiuae/falcon-7b
- Demo [optional]: https://gpt4all.io/
Training Procedure
GPT4All is made possible by our compute partner Paperspace.
Trained on a DGX cluster with 8 A100 80GB GPUs for ~12 hours. Using Deepspeed + Accelerate, we use a global batch size of 256 with a learning rate of 2e-5. More information can be found in the repo.
Results
Results on common sense reasoning benchmarks
| Model | BoolQ | PIQA | HellaSwag | WinoGrande | ARC-e | ARC-c | OBQA | Avg. |
|:--------------------------|:--------:|:--------:|:---------:|:----------:|:--------:|:--------:|:--------:|:--------:|
| GPT4All-J 6B v1.0 | 73.4 | 74.8 | 63.4 | 64.7 | 54.9 | 36.0 | 40.2 | 58.2 |
| GPT4All-J v1.1-breezy | 74.0 | 75.1 | 63.2 | 63.6 | 55.4 | 34.9 | 38.4 | 57.8 |
| GPT4All-J v1.2-jazzy | 74.8 | 74.9 | 63.6 | 63.8 | 56.6 | 35.3 | 41.0 | 58.6 |
| GPT4All-J v1.3-groovy | 73.6 | 74.3 | 63.8 | 63.5 | 57.7 | 35.0 | 38.8 | 58.1 |
| GPT4All-J Lora 6B | 68.6 | 75.8 | 66.2 | 63.5 | 56.4 | 35.7 | 40.2 | 58.1 |
| GPT4All LLaMa Lora 7B | 73.1 | 77.6 | 72.1 | 67.8 | 51.1 | 40.4 | 40.2 | 60.3 |
| GPT4All 13B snoozy | **83.3** | 79.2 | 75.0 | **71.3** | 60.9 | 44.2 | 43.4 | 65.3 |
| GPT4All Falcon | 77.6 | 79.8 | 74.9 | 70.1 | 67.9 | 43.4 | 42.6 | 65.2 |
| Dolly 6B | 68.8 | 77.3 | 67.6 | 63.9 | 62.9 | 38.7 | 41.2 | 60.1 |
| Dolly 12B | 56.7 | 75.4 | 71.0 | 62.2 | 64.6 | 38.5 | 40.4 | 58.4 |
| Alpaca 7B | 73.9 | 77.2 | 73.9 | 66.1 | 59.8 | 43.3 | 43.4 | 62.4 |
| Alpaca Lora 7B | 74.3 | 79.3 | 74.0 | 68.8 | 56.6 | 43.9 | 42.6 | 62.8 |
| GPT-J 6.7B | 65.4 | 76.2 | 66.2 | 64.1 | 62.2 | 36.6 | 38.2 | 58.4 |
| LLama 7B | 73.1 | 77.4 | 73.0 | 66.9 | 52.5 | 41.4 | 42.4 | 61.0 |
| LLama 13B | 68.5 | 79.1 | 76.2 | 70.1 | 60.0 | **44.6** | 42.2 | 63.0 |
| Pythia 6.7B | 63.5 | 76.3 | 64.0 | 61.1 | 61.3 | 35.2 | 37.2 | 57.0 |
| Pythia 12B | 67.7 | 76.6 | 67.3 | 63.8 | 63.9 | 34.8 | 38 | 58.9 |
| Fastchat T5 | 81.5 | 64.6 | 46.3 | 61.8 | 49.3 | 33.3 | 39.4 | 53.7 |
| Fastchat Vicuña 7B | 76.6 | 77.2 | 70.7 | 67.3 | 53.5 | 41.2 | 40.8 | 61.0 |
| Fastchat Vicuña 13B | 81.5 | 76.8 | 73.3 | 66.7 | 57.4 | 42.7 | 43.6 | 63.1 |
| StableVicuña RLHF | 82.3 | 78.6 | 74.1 | 70.9 | 61.0 | 43.5 | **44.4** | 65.0 |
| StableLM Tuned | 62.5 | 71.2 | 53.6 | 54.8 | 52.4 | 31.1 | 33.4 | 51.3 |
| StableLM Base | 60.1 | 67.4 | 41.2 | 50.1 | 44.9 | 27.0 | 32.0 | 42.2 |
| Koala 13B | 76.5 | 77.9 | 72.6 | 68.8 | 54.3 | 41.0 | 42.8 | 62.0 |
| Open Assistant Pythia 12B | 67.9 | 78.0 | 68.1 | 65.0 | 64.2 | 40.4 | 43.2 | 61.0 |
| Mosaic MPT7B | 74.8 | 79.3 | 76.3 | 68.6 | 70.0 | 42.2 | 42.6 | 64.8 |
| Mosaic mpt-instruct | 74.3 | 80.4 | **77.2** | 67.8 | **72.2** | **44.6** | 43.0 | **65.6** |
| Mosaic mpt-chat | 77.1 | 78.2 | 74.5 | 67.5 | 69.4 | 43.3 | 44.2 | 64.9 |
| Wizard 7B | 78.4 | 77.2 | 69.9 | 66.5 | 56.8 | 40.5 | 42.6 | 61.7 |
| Wizard 7B Uncensored | 77.7 | 74.2 | 68.0 | 65.2 | 53.5 | 38.7 | 41.6 | 59.8 |
| Wizard 13B Uncensored | 78.4 | 75.5 | 72.1 | 69.5 | 57.5 | 40.4 | 44.0 | 62.5 |
| GPT4-x-Vicuna-13b | 81.3 | 75.0 | 75.2 | 65.0 | 58.7 | 43.9 | 43.6 | 62.2 |
| Falcon 7b | 73.6 | **80.7** | 76.3 | 67.3 | 71.0 | 43.3 | 44.4 | 65.2 |
| text-davinci-003 | 88.1 | 83.8 | 83.4 | 75.8 | 83.9 | 63.9 | 51.0 | 75.7 |
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.
