metadata

inference: false
license: other

Want to contribute? TheBloke's Patreon page

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.

GGML files are for CPU + GPU inference using llama.cpp and libraries and UIs which support this format, such as:

Repositories available

Compatibility

Original llama.cpp quant methods: `q4_0, q4_1, q5_0, q5_1, q8_0`

I have quantized these 'original' quantisation methods using an older version of llama.cpp so that they remain compatible with llama.cpp as of May 19th, commit 2d5db48.

These are guaranteed to be compatbile with any UIs, tools and libraries released since late May.

New k-quant methods: `q2_K, q3_K_S, q3_K_M, q3_K_L, q4_K_S, q4_K_M, q5_K_S, q6_K`

These new quantisation methods are compatible with llama.cpp as of June 6th, commit 2d43387.

They are now also compatible with recent releases of text-generation-webui, KoboldCpp, llama-cpp-python and ctransformers. Other tools and libraries may or may not be compatible - check their documentation if in doubt.

Explanation of the new k-quant methods

The new methods available are:

GGML_TYPE_Q2_K - "type-1" 2-bit quantization in super-blocks containing 16 blocks, each block having 16 weight. Block scales and mins are quantized with 4 bits. This ends up effectively using 2.5625 bits per weight (bpw)
GGML_TYPE_Q3_K - "type-0" 3-bit quantization in super-blocks containing 16 blocks, each block having 16 weights. Scales are quantized with 6 bits. This end up using 3.4375 bpw.
GGML_TYPE_Q4_K - "type-1" 4-bit quantization in super-blocks containing 8 blocks, each block having 32 weights. Scales and mins are quantized with 6 bits. This ends up using 4.5 bpw.
GGML_TYPE_Q5_K - "type-1" 5-bit quantization. Same super-block structure as GGML_TYPE_Q4_K resulting in 5.5 bpw
GGML_TYPE_Q6_K - "type-0" 6-bit quantization. Super-blocks with 16 blocks, each block having 16 weights. Scales are quantized with 8 bits. This ends up using 6.5625 bpw
GGML_TYPE_Q8_K - "type-0" 8-bit quantization. Only used for quantizing intermediate results. The difference to the existing Q8_0 is that the block size is 256. All 2-6 bit dot products are implemented for this quantization type.

Refer to the Provided Files table below to see what files use which methods, and how.

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	Original llama.cpp quant method, 4-bit.
h2ogpt-falcon-40b.ggmlv3.q4_1.bin	q4_1	4	26.16 GB	28.66 GB	Original llama.cpp 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	Original llama.cpp 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	Original llama.cpp 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	Original llama.cpp 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.

How to run in `llama.cpp`

I use the following command line; adjust for your tastes and needs:

./main -t 10 -ngl 32 -m h2ogpt-gm-oasst1-en-2048-falcon-40b0v2.ggmlv3.q5_0.bin --color -c 2048 --temp 0.7 --repeat_penalty 1.1 -n -1 -p "### Instruction: Write a story about llamas\n### Response:"

If you're able to use full GPU offloading, you should use -t 1 to get best performance.

If not able to fully offload to GPU, you should use more cores. Change -t 10 to the number of physical CPU cores you have, or a lower number depending on what gives best performance.

Change -ngl 32 to the number of layers to offload to GPU. Remove it if you don't have GPU acceleration.

If you want to have a chat-style conversation, replace the -p <PROMPT> argument with -i -ins

How to run in `text-generation-webui`

Further instructions here: text-generation-webui/docs/llama.cpp-models.md.

Discord

For further support, and discussions on these models and AI in general, join us at:

TheBloke AI's Discord server

Thanks, and how to contribute.

Thanks to the 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.

Base model: tiiuae/falcon-40b
Dataset preparation: OpenAssistant/oasst1

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.