---
license: apache-2.0
datasets:
- Open-Orca/OpenOrca
- HuggingFaceH4/ultrachat_200k
language:
- en
---

# Model Card

![image/png](https://cdn-uploads.huggingface.co/production/uploads/659755f81b663b1e5380de8e/H58b-ZYOxGZ35ZVW6OQjJ.png)

## Summary

This model was trained using H2O LLM Studio then converted to GGUF.  These quantised GGUF files are compatible with llama.cpp.

    Base model: https://huggingface.co/MicroHealth/Pathfinder-3b-v1

License: Apache 2.0 https://www.apache.org/licenses/LICENSE-2.0 given that is the license of the base model.

V1 was fine tuned with the full openorca set. V2 stacked the fine tuning with full ultrachat set.  V3 will stack training on top of V2 to strengthen wikipedia weights.

Don't use FAST. It will give you erratic tokenization as identified by the base model creator and confirmed by us.

Looking for feedback on a 3b permissive model to understand how to better train it. Our intent is to use it in cpu mode for rag with HF transformers.

## Prompt template:

<pre>
{%- set ns = namespace(found=false) -%} 
{%- for message in messages -%} 
    {%- if message['role'] == 'system' -%} 
        {%- set ns.found = true -%} 
    {%- endif -%} 
{%- endfor -%} 
{%- if not ns.found -%} 
    {{- '' + 'Below is an instruction that describes a task. Write a response that appropriately completes the request.' + '\n\n' -}} 
{%- endif %} 
{%- for message in messages %} 
    {%- if message['role'] == 'system' -%} 
        {{- '' + message['content'] + '\n\n' -}} 
    {%- else -%} 
        {%- if message['role'] == 'user' -%} 
            {{-'### Instruction:\n' + message['content'] + '\n\n'-}} 
        {%- else -%} 
            {{-'### Response:\n' + message['content'] + '\n\n' -}} 
        {%- endif -%} 
    {%- endif -%} 
{%- endfor -%} 
{%- if add_generation_prompt -%} 
    {{-'### Response:\n'-}} 
{%- endif -%} 
</pre>

## 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, 3200, padding_idx=0)
    (layers): ModuleList(
      (0-25): 26 x LlamaDecoderLayer(
        (self_attn): LlamaSdpaAttention(
          (q_proj): Linear(in_features=3200, out_features=3200, bias=False)
          (k_proj): Linear(in_features=3200, out_features=3200, bias=False)
          (v_proj): Linear(in_features=3200, out_features=3200, bias=False)
          (o_proj): Linear(in_features=3200, out_features=3200, bias=False)
          (rotary_emb): LlamaRotaryEmbedding()
        )
        (mlp): LlamaMLP(
          (gate_proj): Linear(in_features=3200, out_features=8640, bias=False)
          (up_proj): Linear(in_features=3200, out_features=8640, bias=False)
          (down_proj): Linear(in_features=8640, out_features=3200, bias=False)
          (act_fn): SiLU()
        )
        (input_layernorm): LlamaRMSNorm()
        (post_attention_layernorm): LlamaRMSNorm()
      )
    )
    (norm): LlamaRMSNorm()
  )
  (lm_head): Linear(in_features=3200, out_features=32000, 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.