# H2O's GPT-GM-OASST1-Falcon 40B v2 GGML
These files are GGML format model files for [H2O's GPT-GM-OASST1-Falcon 40B v2](https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2).
These GGML files will **not** work in llama.cpp, text-generation-webui or KoboldCpp.
They can be used from:
* [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui).
* The ctransformers Python library, which includes LangChain support: [ctransformers](https://github.com/marella/ctransformers).
* A new fork of llama.cpp that introduced this new Falcon GGML support: [cmp-nc/ggllm.cpp](https://github.com/cmp-nct/ggllm.cpp).
## Prompt template
```
<|prompt|>prompt<|endoftext|>
<|answer|>
```
## Repositories available
* [4-bit GPTQ models for GPU inference](https://huggingface.co/TheBloke/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2-GPTQ)
* [2, 3, 4, 5, 6 and 8-bit GGML models for CPU+GPU inference](https://huggingface.co/TheBloke/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2-GGML)
* [Unquantised fp16 model in pytorch format, for GPU inference and for further conversions](https://huggingface.co/h2oai/h2ogpt-gm-oasst1-en-2048-falcon-40b-v2)
## Compatibility
The recommended UI for these GGMLs is [LoLLMS Web UI](https://github.com/ParisNeo/lollms-webui). Preliminary CUDA GPU acceleration is provided.
For use from Python code, use [ctransformers](https://github.com/marella/ctransformers). Again, with preliminary CUDA GPU acceleration
Or to build cmp-nct's fork of llama.cpp with Falcon 7B support plus preliminary CUDA acceleration, please try the following steps:
```
git clone https://github.com/cmp-nct/ggllm.cpp
cd ggllm.cpp
rm -rf build && mkdir build && cd build && cmake -DGGML_CUBLAS=1 .. && cmake --build . --config Release
```
Compiling on Windows: developer cmp-nct notes: 'I personally compile it using VScode. When compiling with CUDA support using the Microsoft compiler it's essential to select the "Community edition build tools". Otherwise CUDA won't compile.'
Once compiled you can then use `bin/falcon_main` just like you would use llama.cpp. For example:
```
bin/falcon_main -t 8 -ngl 100 -b 1 -m h2ogpt-falcon-40b.ggmlv3.q3_k.bin -p "What is a falcon?\n### Response:"
```
You can specify `-ngl 100` regardles of your VRAM, as it will automatically detect how much VRAM is available to be used.
Adjust `-t 8` (the number of CPU cores to use) according to what performs best on your system. Do not exceed the number of physical CPU cores you have.
`-b 1` reduces batch size to 1. This slightly lowers prompt evaluation time, but frees up VRAM to load more of the model on to your GPU. If you find prompt evaluation too slow and have enough spare VRAM, you can remove this parameter.
## Provided files
| Name | Quant method | Bits | Size | Max RAM required | Use case |
| ---- | ---- | ---- | ---- | ---- | ----- |
| h2ogpt-falcon-40b.ggmlv3.q2_k.bin | q2_k | 2 | 13.74 GB | 16.24 GB | New k-quant method. Uses GGML_TYPE_Q5_K for the attention.vw and feed_forward.w2 tensors, GGML_TYPE_Q2_K for the other tensors. |
| h2ogpt-falcon-40b.ggmlv3.q3_k.bin | q3_k | 3 | 17.98 GB | 20.48 GB | New k-quant method. Uses GGML_TYPE_Q3_K for all tensors |
| h2ogpt-falcon-40b.ggmlv3.q4_0.bin | q4_0 | 4 | 23.54 GB | 26.04 GB | Old quant method, 4-bit. |
| h2ogpt-falcon-40b.ggmlv3.q4_1.bin | q4_1 | 4 | 26.16 GB | 28.66 GB | Old quant method, 4-bit. Higher accuracy than q4_0 but not as high as q5_0. However has quicker inference than q5 models. |
| h2ogpt-falcon-40b.ggmlv3.q4_k.bin | q4_k | 4 | 23.54 GB | 26.04 GB | New k-quant method. Uses GGML_TYPE_Q4_K for all tensors |
| h2ogpt-falcon-40b.ggmlv3.q5_0.bin | q5_0 | 5 | 28.77 GB | 31.27 GB | Old quant method, 5-bit. Higher accuracy, higher resource usage and slower inference. |
| h2ogpt-falcon-40b.ggmlv3.q5_1.bin | q5_1 | 5 | 31.38 GB | 33.88 GB | Old quant method, 5-bit. Even higher accuracy, resource usage and slower inference. |
| h2ogpt-falcon-40b.ggmlv3.q5_k.bin | q5_k | 5 | 28.77 GB | 31.27 GB | New k-quant method. Uses GGML_TYPE_Q5_K for all tensors |
| h2ogpt-falcon-40b.ggmlv3.q6_k.bin | q6_k | 6 | 34.33 GB | 36.83 GB | New k-quant method. Uses GGML_TYPE_Q8_K - 6-bit quantization - for all tensors |
| h2ogpt-falcon-40b.ggmlv3.q8_0.bin | q8_0 | 8 | 44.46 GB | 46.96 GB | Old quant method, 8-bit. Almost indistinguishable from float16. High resource use and slow. Not recommended for most users. |
**Note**: the above RAM figures assume no GPU offloading. If layers are offloaded to the GPU, this will reduce RAM usage and use VRAM instead.
## Discord
For further support, and discussions on these models and AI in general, join us at:
[TheBloke AI's Discord server](https://discord.gg/Jq4vkcDakD)
## Thanks, and how to contribute.
Thanks to the [chirper.ai](https://chirper.ai) team!
I've had a lot of people ask if they can contribute. I enjoy providing models and helping people, and would love to be able to spend even more time doing it, as well as expanding into new projects like fine tuning/training.
If you're able and willing to contribute it will be most gratefully received and will help me to keep providing more models, and to start work on new AI projects.
Donaters will get priority support on any and all AI/LLM/model questions and requests, access to a private Discord room, plus other benefits.
* Patreon: https://patreon.com/TheBlokeAI
* Ko-Fi: https://ko-fi.com/TheBlokeAI
**Special thanks to**: Luke from CarbonQuill, Aemon Algiz, Dmitriy Samsonov.
**Patreon special mentions**: Mano Prime, Fen Risland, Derek Yates, Preetika Verma, webtim, Sean Connelly, Alps Aficionado, Karl Bernard, Junyu Yang, Nathan LeClaire, Chris McCloskey, Lone Striker, Asp the Wyvern, Eugene Pentland, Imad Khwaja, trip7s trip, WelcomeToTheClub, John Detwiler, Artur Olbinski, Khalefa Al-Ahmad, Trenton Dambrowitz, Talal Aujan, Kevin Schuppel, Luke Pendergrass, Pyrater, Joseph William Delisle, terasurfer , vamX, Gabriel Puliatti, David Flickinger, Jonathan Leane, Iucharbius , Luke, Deep Realms, Cory Kujawski, ya boyyy, Illia Dulskyi, senxiiz, Johann-Peter Hartmann, John Villwock, K, Ghost , Spiking Neurons AB, Nikolai Manek, Rainer Wilmers, Pierre Kircher, biorpg, Space Cruiser, Ai Maven, subjectnull, Willem Michiel, Ajan Kanaga, Kalila, chris gileta, Oscar Rangel.
Thank you to all my generous patrons and donaters!
# Original model card: H2O's GPT-GM-OASST1-Falcon 40B v2
# Model Card
## Summary
This model was trained using [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio).
- Base model: [tiiuae/falcon-40b](https://huggingface.co/tiiuae/falcon-40b)
- Dataset preparation: [OpenAssistant/oasst1](https://github.com/h2oai/h2o-llmstudio/blob/1935d84d9caafed3ee686ad2733eb02d2abfce57/app_utils/utils.py#LL1896C5-L1896C28)
## 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.
```bash
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
```
```python
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:
```python
print(generate_text.preprocess("Why is drinking water so healthy?")["prompt_text"])
```
```bash
<|prompt|>Why is drinking water so healthy?<|endoftext|><|answer|>
```
Alternatively, you can download [h2oai_pipeline.py](h2oai_pipeline.py), store it alongside your notebook, and construct the pipeline yourself from the loaded model and tokenizer:
```python
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:
```python
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](cfg.yaml). Visit [H2O LLM Studio](https://github.com/h2oai/h2o-llmstudio) 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.
