README.md

---
language:
- en
license: apache-2.0
datasets:
- appvoid/no-prompt-15k
pipeline_tag: text-generation
model-index:
- name: palmer-002
  results:
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: AI2 Reasoning Challenge (25-Shot)
      type: ai2_arc
      config: ARC-Challenge
      split: test
      args:
        num_few_shot: 25
    metrics:
    - type: acc_norm
      value: 34.47
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=appvoid/palmer-002
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: HellaSwag (10-Shot)
      type: hellaswag
      split: validation
      args:
        num_few_shot: 10
    metrics:
    - type: acc_norm
      value: 59.41
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=appvoid/palmer-002
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: MMLU (5-Shot)
      type: cais/mmlu
      config: all
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 25.94
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=appvoid/palmer-002
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: TruthfulQA (0-shot)
      type: truthful_qa
      config: multiple_choice
      split: validation
      args:
        num_few_shot: 0
    metrics:
    - type: mc2
      value: 37.06
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=appvoid/palmer-002
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: Winogrande (5-shot)
      type: winogrande
      config: winogrande_xl
      split: validation
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 62.67
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=appvoid/palmer-002
      name: Open LLM Leaderboard
  - task:
      type: text-generation
      name: Text Generation
    dataset:
      name: GSM8k (5-shot)
      type: gsm8k
      config: main
      split: test
      args:
        num_few_shot: 5
    metrics:
    - type: acc
      value: 1.21
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=appvoid/palmer-002
      name: Open LLM Leaderboard
---
![palmer](https://huggingface.co/appvoid/palmer-001/resolve/main/new-logo.jpg)
# palmer
### a better base model 
palmer is a series of ~1b parameters language models fine-tuned to be used as base models instead of using custom prompts for tasks. This means that it can be further fine-tuned on more data with custom prompts as usual or be used for downstream tasks as any base model you can get. The model has the best of both worlds: some "bias" to act as an assistant, but also the abillity to predict the next-word from its internet knowledge base. It's a 1.1b llama 2 model so you can use it with your favorite tools/frameworks.

### evaluation 🧪
note that this is a zero-shot setting as opposite to open llm leaderboard's few-shot evals
```
   Model           ARC_C   HellaSwag  PIQA  Winogrande Average
tinyllama-2      | 0.2807 | 0.5463 | 0.7067 | 0.5683 | 0.5255 |
palmer-001	     | 0.2807 | 0.5524 | 0.7106 | 0.5896 | 0.5333 |
babbage-001      | 0.2944 | 0.5448 | 0.7410 | 0.5935 | 0.5434 |
deacon-1b        | 0.2944 | 0.5727 | 0.7040 | 0.5801 | 0.5434 |
tinyllama-2.5    | 0.3191 | 0.5896 | 0.7307 | 0.5872 | 0.5566 |
palmer-002       | 0.3242 | 0.5956 | 0.7345 | 0.5888 | 0.5607 |
babbage-002      | 0.3285 | 0.6380 | 0.7606 | 0.6085 | 0.5839 |
```

This model shows exceptional performance and as of now is the best tinyllama-size base model. Furthermore, this proves LIMA paper point and serves as a good open-source alternative to openai's `babbage-002`.

### training 🦾
Training took ~3.5 P100 gpu hours. It was trained on 15,000 gpt-4 shuffled samples. palmer was fine-tuned using lower learning rates ensuring it keeps as much general knowledge as possible.

### prompt 📝
```
no prompt 🚀
```
<a href="https://ko-fi.com/appvoid" target="_blank"><img src="https://cdn.buymeacoffee.com/buttons/v2/default-yellow.png" alt="Buy Me A Coffee" style="height: 48px !important;width: 180px !important; filter: invert(70%);" ></a>
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_appvoid__palmer-002)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |36.79|
|AI2 Reasoning Challenge (25-Shot)|34.47|
|HellaSwag (10-Shot)              |59.41|
|MMLU (5-Shot)                    |25.94|
|TruthfulQA (0-shot)              |37.06|
|Winogrande (5-shot)              |62.67|
|GSM8k (5-shot)                   | 1.21|