language:
- en
library_name: transformers
tags:
- gpt
- llm
- large language model
- h2o-llmstudio
inference: false
thumbnail: >-
https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
license: apache-2.0
datasets:
- OpenAssistant/oasst1
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.
h2ogpt-gm-oasst1-en-2048-falcon-40b-v2 - GGUF
- Model creator: h2oai
- Original model: h2ogpt-gm-oasst1-en-2048-falcon-40b-v2
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, which impacts both the original Falcon models and their derived variants.
Here's what you need to know:
Original Falcon Models: I am diligently working to provide updated quantized versions of the four original Falcon models to ensure their compatibility with the new llama.cpp versions. Please keep an eye on my Hugging Face Model pages for updates on the availability of these models. Promptly downloading them is essential to maintain compatibility with the latest llama.cpp releases.
Derived Falcon Models: Right now, the derived Falcon-Models cannot be re-converted without adjustments from the original model creators. So far, these models cannot be used in recent llama.cpp versions at all. ** Good news!** It's in the pipeline that the capability for quantizing even the older derived Falcon models will be incorporated soon. However, the exact timeline is beyond my control.
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.
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:
Model Card
Summary
This model was trained using H2O LLM Studio.
- Base model: tiiuae/falcon-40b
- Dataset preparation: OpenAssistant/oasst1 personalized
Usage
To use the model with the transformers library on a machine with GPUs, first make sure you have the transformers, accelerate and torch libraries installed.
pip install transformers==4.29.2
pip install bitsandbytes==0.39.0
pip install accelerate==0.19.0
pip install torch==2.0.0
pip install einops==0.6.1
import torch
from transformers import pipeline, BitsAndBytesConfig, AutoTokenizer
model_kwargs = {}
quantization_config = None
# optional quantization
quantization_config = BitsAndBytesConfig(
load_in_8bit=True,
llm_int8_threshold=6.0,
)
model_kwargs["quantization_config"] = quantization_config
tokenizer = AutoTokenizer.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
use_fast=False,
padding_side="left",
trust_remote_code=True,
)
generate_text = pipeline(
model="h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
tokenizer=tokenizer,
torch_dtype=torch.float16,
trust_remote_code=True,
use_fast=False,
device_map={"": "cuda:0"},
model_kwargs=model_kwargs,
)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
You can print a sample prompt after the preprocessing step to see how it is feed to the tokenizer:
print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"])
<|prompt|>Why is drinking water so healthy?<|endoftext|><|answer|>
Alternatively, you can download h2oai_pipeline.py, store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:
import torch
from h2oai_pipeline import H2OTextGenerationPipeline
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
quantization_config = None
# optional quantization
quantization_config = BitsAndBytesConfig(
load_in_8bit=True,
llm_int8_threshold=6.0,
)
tokenizer = AutoTokenizer.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
use_fast=False,
padding_side="left",
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
trust_remote_code=True,
torch_dtype=torch.float16,
device_map={"": "cuda:0"},
quantization_config=quantization_config
).eval()
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer)
res = generate_text(
"Why is drinking water so healthy?",
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)
print(res[0]["generated_text"])
You may also construct the pipeline from the loaded model and tokenizer yourself and consider the preprocessing steps:
from transformers import AutoModelForCausalLM, AutoTokenizer, BitsAndBytesConfig
# Important: The prompt needs to be in the same format the model was trained with.
# You can find an example prompt in the experiment logs.
prompt = "<|prompt|>How are you?<|endoftext|><|answer|>"
quantization_config = None
# optional quantization
quantization_config = BitsAndBytesConfig(
load_in_8bit=True,
llm_int8_threshold=6.0,
)
tokenizer = AutoTokenizer.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
use_fast=False,
padding_side="left",
trust_remote_code=True,
)
model = AutoModelForCausalLM.from_pretrained(
"h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2",
trust_remote_code=True,
torch_dtype=torch.float16,
device_map={"": "cuda:0"},
quantization_config=quantization_config
).eval()
inputs = tokenizer(prompt, return_tensors="pt", add_special_tokens=False).to("cuda")
# generate configuration can be modified to your needs
tokens = model.generate(
**inputs,
min_new_tokens=2,
max_new_tokens=1024,
do_sample=False,
num_beams=1,
temperature=float(0.3),
repetition_penalty=float(1.2),
renormalize_logits=True
)[0]
tokens = tokens[inputs["input_ids"].shape[1]:]
answer = tokenizer.decode(tokens, skip_special_tokens=True)
print(answer)
Model Architecture
RWForCausalLM(
(transformer): RWModel(
(word_embeddings): Embedding(65024, 8192)
(h): ModuleList(
(0-59): 60 x DecoderLayer(
(ln_attn): LayerNorm((8192,), eps=1e-05, elementwise_affine=True)
(ln_mlp): LayerNorm((8192,), eps=1e-05, elementwise_affine=True)
(self_attention): Attention(
(maybe_rotary): RotaryEmbedding()
(query_key_value): Linear(in_features=8192, out_features=9216, bias=False)
(dense): Linear(in_features=8192, out_features=8192, bias=False)
(attention_dropout): Dropout(p=0.0, inplace=False)
)
(mlp): MLP(
(dense_h_to_4h): Linear(in_features=8192, out_features=32768, bias=False)
(act): GELU(approximate='none')
(dense_4h_to_h): Linear(in_features=32768, out_features=8192, bias=False)
)
)
)
(ln_f): LayerNorm((8192,), eps=1e-05, elementwise_affine=True)
)
(lm_head): Linear(in_features=8192, out_features=65024, bias=False)
)
Model Configuration
This model was trained using H2O LLM Studio and with the configuration in cfg.yaml. Visit H2O LLM Studio to learn how to train your own large language models.
Disclaimer
Please read this disclaimer carefully before using the large language model provided in this repository. Your use of the model signifies your agreement to the following terms and conditions.
- Biases and Offensiveness: The large language model is trained on a diverse range of internet text data, which may contain biased, racist, offensive, or otherwise inappropriate content. By using this model, you acknowledge and accept that the generated content may sometimes exhibit biases or produce content that is offensive or inappropriate. The developers of this repository do not endorse, support, or promote any such content or viewpoints.
- Limitations: The large language model is an AI-based tool and not a human. It may produce incorrect, nonsensical, or irrelevant responses. It is the user's responsibility to critically evaluate the generated content and use it at their discretion.
- Use at Your Own Risk: Users of this large language model must assume full responsibility for any consequences that may arise from their use of the tool. The developers and contributors of this repository shall not be held liable for any damages, losses, or harm resulting from the use or misuse of the provided model.
- Ethical Considerations: Users are encouraged to use the large language model responsibly and ethically. By using this model, you agree not to use it for purposes that promote hate speech, discrimination, harassment, or any form of illegal or harmful activities.
- Reporting Issues: If you encounter any biased, offensive, or otherwise inappropriate content generated by the large language model, please report it to the repository maintainers through the provided channels. Your feedback will help improve the model and mitigate potential issues.
- Changes to this Disclaimer: The developers of this repository reserve the right to modify or update this disclaimer at any time without prior notice. It is the user's responsibility to periodically review the disclaimer to stay informed about any changes.
By using the large language model provided in this repository, you agree to accept and comply with the terms and conditions outlined in this disclaimer. If you do not agree with any part of this disclaimer, you should refrain from using the model and any content generated by it.
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.
