---
license: apache-2.0
language:
- en
library_name: transformers
inference: false
thumbnail: https://h2o.ai/etc.clientlibs/h2o/clientlibs/clientlib-site/resources/images/favicon.ico
tags:
- gpt
- llm
- large language model
- open-source
datasets:
- h2oai/openassistant_oasst1
---
# h2oGPT Model Card
## Summary

H2O.ai's `h2ogpt-oasst1-512-20b` is a 20 billion parameter instruction-following large language model licensed for commercial use.

- Base model: [EleutherAI/gpt-neox-20b](https://huggingface.co/EleutherAI/gpt-neox-20b)
- Fine-tuning dataset: [h2oai/openassistant_oasst1](https://huggingface.co/datasets/h2oai/openassistant_oasst1)
- Data-prep and fine-tuning code: [H2O.ai Github](https://github.com/h2oai/h2ogpt)
- Training logs: [zip](https://huggingface.co/h2oai/h2ogpt-oasst1-512-20b/blob/main/gpt-neox-20b.openassistant_oasst1.json.6.0_epochs.5a14ea8b3794c0d60476fc262d0a297f98dd712d.1013.zip)

## Chatbot

- Run your own chatbot: [H2O.ai Github](https://github.com/h2oai/h2ogpt)

![Chatbot](https://user-images.githubusercontent.com/6147661/232924684-6c0e2dfb-2f24-4098-848a-c3e4396f29f6.mov)

## Usage

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

```bash
pip install transformers==4.28.1
pip install accelerate==0.18.0
```

```python
import torch
from transformers import pipeline

generate_text = pipeline(model="h2oai/h2ogpt-oasst1-512-20b", torch_dtype=torch.bfloat16, trust_remote_code=True, device_map="auto")

res = generate_text("Why is drinking water so healthy?", max_new_tokens=100)
print(res[0]["generated_text"])
```

Alternatively, if you prefer to not use `trust_remote_code=True` you can download [instruct_pipeline.py](https://huggingface.co/h2oai/h2ogpt-oasst1-512-20b/blob/main/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

tokenizer = AutoTokenizer.from_pretrained("h2oai/h2ogpt-oasst1-512-20b", padding_side="left")
model = AutoModelForCausalLM.from_pretrained("h2oai/h2ogpt-oasst1-512-20b", torch_dtype=torch.bfloat16, device_map="auto")
generate_text = H2OTextGenerationPipeline(model=model, tokenizer=tokenizer)

res = generate_text("Why is drinking water so healthy?", max_new_tokens=100)
print(res[0]["generated_text"])
```

## Model Architecture

```
GPTNeoXForCausalLM(
  (gpt_neox): GPTNeoXModel(
    (embed_in): Embedding(50432, 6144)
    (layers): ModuleList(
      (0-43): 44 x GPTNeoXLayer(
        (input_layernorm): LayerNorm((6144,), eps=1e-05, elementwise_affine=True)
        (post_attention_layernorm): LayerNorm((6144,), eps=1e-05, elementwise_affine=True)
        (attention): GPTNeoXAttention(
          (rotary_emb): RotaryEmbedding()
          (query_key_value): Linear(in_features=6144, out_features=18432, bias=True)
          (dense): Linear(in_features=6144, out_features=6144, bias=True)
        )
        (mlp): GPTNeoXMLP(
          (dense_h_to_4h): Linear(in_features=6144, out_features=24576, bias=True)
          (dense_4h_to_h): Linear(in_features=24576, out_features=6144, bias=True)
          (act): FastGELUActivation()
        )
      )
    )
    (final_layer_norm): LayerNorm((6144,), eps=1e-05, elementwise_affine=True)
  )
  (embed_out): Linear(in_features=6144, out_features=50432, bias=False)
)
```

## Model Configuration

```json
GPTNeoXConfig {
  "_name_or_path": "h2oai/h2ogpt-oasst1-512-20b",
  "architectures": [
    "GPTNeoXForCausalLM"
  ],
  "attention_probs_dropout_prob": 0,
  "bos_token_id": 0,
  "custom_pipelines": {
    "text-generation": {
      "impl": "h2oai_pipeline.H2OTextGenerationPipeline",
      "pt": "AutoModelForCausalLM"
    }
  },
  "eos_token_id": 0,
  "hidden_act": "gelu_fast",
  "hidden_dropout_prob": 0,
  "hidden_size": 6144,
  "initializer_range": 0.02,
  "intermediate_size": 24576,
  "layer_norm_eps": 1e-05,
  "max_position_embeddings": 2048,
  "model_type": "gpt_neox",
  "num_attention_heads": 64,
  "num_hidden_layers": 44,
  "rotary_emb_base": 10000,
  "rotary_pct": 0.25,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.28.1",
  "use_cache": true,
  "use_parallel_residual": true,
  "vocab_size": 50432
}

```