README.md

metadata

license: apache-2.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - gordicaleksa/YugoGPT
  - mlabonne/AlphaMonarch-7B
model-index:
  - name: Tito-7B-slerp
    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: 68.09
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/Tito-7B-slerp
          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: 86.38
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/Tito-7B-slerp
          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: 64.01
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/Tito-7B-slerp
          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: 57.01
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/Tito-7B-slerp
          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: 81.69
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/Tito-7B-slerp
          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: 63.61
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Stopwolf/Tito-7B-slerp
          name: Open LLM Leaderboard

Tito-7B-slerp

Tito-7B-slerp is a merge of the following models using mergekit:

• gordicaleksa/YugoGPT
• mlabonne/AlphaMonarch-7B

🧩 Configuration

slices:
  - sources:
      - model: gordicaleksa/YugoGPT
        layer_range: [0, 32]
      - model: mlabonne/AlphaMonarch-7B
        layer_range: [0, 32]
merge_method: slerp
base_model: mlabonne/AlphaMonarch-7B
parameters:
  t:
    - filter: self_attn
      value: [0, 0.5, 0.3, 0.7, 1]
    - filter: mlp
      value: [1, 0.5, 0.7, 0.3, 0]
    - value: 0.6
dtype: bfloat16

Results

Evaluations on Serbian LLM eval suite (or rather, performance and knowledge of Serbian):

	ARC-E	ARC-C	Hellaswag	BoolQ	Winogrande	OpenbookQA	PiQA	NQ Open	TriviaQA	Avg.
Zamfir-7B	51.85	32.25	46.03	75.59	62.59	26.00	66.81	16.09	36.11	45.92
Mustra-7B	52.95	33.70	45.89	77.55	64.17	30.60	67.25	15.40	34.84	46.93
Tito-7B	55.43	34.73	48.19	77.37	65.27	30.00	67.30	16.7	35.38	47.82
YugoGPT	57.79	34.73	49.89	69.45	64.56	28.20	72.03	15.82	36.14	47.62

Here, all benchmarks were done 0-shot, on the exception of NQ Open and TriviaQA which were done in 5-shot manner, in order to be comparable to Mistral paper.

Evalutaions on Open LLM Leaderboard (or rather, performance and knowledge of English):

	ARC	Hellaswag	Winogrande	MMLU	GSM8k	ThruthfulQA	Avg.
Tito-7B	68.08	86.37	81.69	64.01	63.61	57.01	70.13
YugoGPT	58.10	81.44	76.56	60.68	30.70	36.60	57.34

Here, Winogrande, GSM8k, MMLU were done in 5-shot manner, Hellaswag in 10-shot manner, and finally ARC in 25-shot manner.

If we try to replicate these approaches on available Serbian datasets (running an appropriate amount of shots instead of 0), we get:

	ARC	Hellaswag	Winogrande	Avg.
Tito-7B	47.27	-	69.93	-
YugoGPT	44.03	-	70.64	-

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	70.13
AI2 Reasoning Challenge (25-Shot)	68.09
HellaSwag (10-Shot)	86.38
MMLU (5-Shot)	64.01
TruthfulQA (0-shot)	57.01
Winogrande (5-shot)	81.69
GSM8k (5-shot)	63.61