Hugging Face's logo

h2oai
/
h2o-danube3-500m-base

Text Generation
Transformers
ONNX
Safetensors
English
llama
gpt
llm
large language model
h2o-llmstudio
text-generation-inference
Inference Endpoints
Model card Files Community
6
h2o-danube3-500m-base / README.md
ilu000's picture
ilu000
Update README.md
56620a2 verified
preview code
|
raw
history blame contribute delete
6.61 kB
metadata
language:
  - en
library_name: transformers
license: apache-2.0
tags:
  - gpt
  - llm
  - large language model
  - h2o-llmstudio
thumbnail: >-
  https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
pipeline_tag: text-generation
Slightly cropped image

Summary

h2o-danube3-500m-base is a foundation model trained by H2O.ai with 500 million parameters. We release two versions of this model:

Model Name Description
h2oai/h2o-danube3-500m-base Base model
h2oai/h2o-danube3-500m-chat Chat model

Can be run natively and fully offline on phones - try it yourself with H2O AI Personal GPT.

Model Architecture

We adjust the Llama 2 architecture for a total of around 500m parameters. For details, please refer to our Technical Report. We use the Mistral tokenizer with a vocabulary size of 32,000 and train our model up to a context length of 8,192.

The details of the model architecture are:

Hyperparameter Value
n_layers 16
n_heads 16
n_query_groups 8
n_embd 1536
vocab size 32000
sequence length 8192

Usage

To use the model with the transformers library on a machine with GPUs, first make sure you have the transformers library installed.

pip install transformers>=4.42.3

import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("h2oai/h2o-danube3-500m-base")

model = AutoModelForCausalLM.from_pretrained(
    "h2oai/h2o-danube3-500m-base",
    torch_dtype=torch.bfloat16,
)
model.cuda()

inputs = tokenizer("The Danube is the second longest river in Europe", return_tensors="pt").to(model.device)
res = model.generate(
    **inputs,
    max_new_tokens=32,
    do_sample=False,
)
print(tokenizer.decode(res[0], skip_special_tokens=True))

Quantization and sharding

You can load the models using quantization by specifying load_in_8bit=True or load_in_4bit=True. Also, sharding on multiple GPUs is possible by setting device_map=auto.

Model Architecture 

LlamaForCausalLM(
  (model): LlamaModel(
    (embed_tokens): Embedding(32000, 1536, padding_idx=0)
    (layers): ModuleList(
      (0-15): 16 x LlamaDecoderLayer(
        (self_attn): LlamaSdpaAttention(
          (q_proj): Linear(in_features=1536, out_features=1536, bias=False)
          (k_proj): Linear(in_features=1536, out_features=768, bias=False)
          (v_proj): Linear(in_features=1536, out_features=768, bias=False)
          (o_proj): Linear(in_features=1536, out_features=1536, bias=False)
          (rotary_emb): LlamaRotaryEmbedding()
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=1536, out_features=4096, bias=False)
          (up_proj): Linear(in_features=1536, out_features=4096, bias=False)
          (down_proj): Linear(in_features=4096, out_features=1536, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm()
        (post_attention_layernorm): LlamaRMSNorm()
      )
    )
    (norm): LlamaRMSNorm()
  )
  (lm_head): Linear(in_features=1536, out_features=32000, bias=False)
)

Benchmarks

🤗 Open LLM Leaderboard v1

Benchmark acc_n
Average 40.38
ARC-challenge 40.61
Hellaswag 60.52
MMLU 25.72
TruthfulQA 37.67
Winogrande 62.19
GSM8K 15.54

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.