README.md

---
language:
- en,
license: other
license_name: yi-license
license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
pipeline_tag: text-generation
model-index:
- name: SG-Raccoon-Yi-200k-2.0
  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: 62.54
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlinmg/SG-Raccoon-Yi-200k-2.0
      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: 80.26
      name: normalized accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlinmg/SG-Raccoon-Yi-200k-2.0
      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: 73.29
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlinmg/SG-Raccoon-Yi-200k-2.0
      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: 53.21
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlinmg/SG-Raccoon-Yi-200k-2.0
      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: 76.32
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlinmg/SG-Raccoon-Yi-200k-2.0
      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: 30.71
      name: accuracy
    source:
      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=mlinmg/SG-Raccoon-Yi-200k-2.0
      name: Open LLM Leaderboard
---
<p align="center">
  <img src="https://cdn-uploads.huggingface.co/production/uploads/644ba0c76ebb3ebf7264dbe9/PWn9I-0XH7kSP_YXcyxIg.png" width="400"/>
</p>

---

# SG Raccoon 55B 2.0

The first 55B auto-regressive causal LM created by combining 2x finetuned llamafied [Yi 34b](https://huggingface.co/01-ai/Yi-34B) with *200K context* into one.


# Prompting Format

```
SYSTEM: <ANY SYSTEM CONTEXT>
USER: 
ASSISTANT:
```

# Merge process

The models used in the merge are [Tess-M-v1.3](https://huggingface.co/migtissera/Tess-M-v1.3/) and [airoboros-3_1-yi-34b-200k](bhenrym14/airoboros-3_1-yi-34b-200k).

The layer ranges used are as follows:

```yaml
- model: bhenrym14/airoboros-3_1-yi-34b-200k
  layer_range: [0, 14]
- model: migtissera/Tess-M-v1.3
  layer_range: [7, 21]  
- model: bhenrym14/airoboros-3_1-yi-34b-200k
  layer_range: [15, 29] 
- model: migtissera/Tess-M-v1.3
  layer_range: [22, 36] 
- model: bhenrym14/airoboros-3_1-yi-34b-200k
  layer_range: [30, 44] 
- model: migtissera/Tess-M-v1.3
  layer_range: [37, 51]  
- model: bhenrym14/airoboros-3_1-yi-34b-200k
  layer_range: [45, 59] 
```

# Tips

Being a Yi model, try disabling the BOS token and/or running a lower temperature with MinP (and no other samplers) if output doesn't seem right. Yi tends to run "hot" by default.

Sometimes the model "spells out" the stop token as </s> like Capybara, so you may need to add </s> as an additional stopping condition.


# Benchmarks
Coming soon.

# Acknowledgements
- Special thanks to [MSS](https://milanosamplesale.com/) for sponsoring this project

- [@chargoddard](https://huggingface.co/chargoddard) for developing the framework used to merge the model - [mergekit](https://github.com/cg123/mergekit).

- Great thanks to [@Undi95](https://huggingface.co/Undi95) for helping figuring out model merge options

- Also credits to the [01-ai](https://huggingface.co/01-ai) team for their amazing models

- This merged model is inspired by [Goliath 120B](https://huggingface.co/alpindale/goliath-120b)
# [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_mlinmg__SG-Raccoon-Yi-200k-2.0)

|             Metric              |Value|
|---------------------------------|----:|
|Avg.                             |62.72|
|AI2 Reasoning Challenge (25-Shot)|62.54|
|HellaSwag (10-Shot)              |80.26|
|MMLU (5-Shot)                    |73.29|
|TruthfulQA (0-shot)              |53.21|
|Winogrande (5-shot)              |76.32|
|GSM8k (5-shot)                   |30.71|