README.md

metadata

license: cc-by-nc-4.0
tags:
  - merge
  - mergekit
  - lazymergekit
  - pruning
  - alnrg2arg/blockchainlabs_7B_merged_test2_4
  - mlabonne/NeuralBeagle14-7B
  - udkai/Turdus
model-index:
  - name: blockchainlabs_7B_merged_test2_4_prune
    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: 60.58
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/blockchainlabs_7B_merged_test2_4_prune
          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: 77.74
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/blockchainlabs_7B_merged_test2_4_prune
          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: 52.27
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/blockchainlabs_7B_merged_test2_4_prune
          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: 59.03
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/blockchainlabs_7B_merged_test2_4_prune
          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: 76.4
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/blockchainlabs_7B_merged_test2_4_prune
          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: 21.46
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=alnrg2arg/blockchainlabs_7B_merged_test2_4_prune
          name: Open LLM Leaderboard

blockchainlabs_7B_merged_test2_4_prune

blockchainlabs_7B_merged_test2_4_prune is a pruned model based on alnrg2arg/blockchainlabs_7B_merged_test2_4, which is a merged model using following models using mergekit:

• mlabonne/NeuralBeagle14-7B
• udkai/Turdus

Pruning Kit I used: wanda

🧩 Configuration

{
  "_name_or_path": "alnrg2arg/blockchainlabs_7B_merged_test2_4_prun",
  "architectures": [
    "MistralForCausalLM"
  ],
  "attention_dropout": 0.0,
  "bos_token_id": 1,
  "eos_token_id": 2,
  "hidden_act": "silu",
  "hidden_size": 4096,
  "initializer_range": 0.02,
  "intermediate_size": 14336,
  "max_position_embeddings": 32768,
  "model_type": "mistral",
  "num_attention_heads": 32,
  "num_hidden_layers": 32,
  "num_key_value_heads": 8,
  "rms_norm_eps": 1e-05,
  "rope_theta": 10000.0,
  "sliding_window": 4096,
  "tie_word_embeddings": false,
  "torch_dtype": "float16",
  "transformers_version": "4.36.2",
  "use_cache": false,
  "vocab_size": 32000
}

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	57.91
AI2 Reasoning Challenge (25-Shot)	60.58
HellaSwag (10-Shot)	77.74
MMLU (5-Shot)	52.27
TruthfulQA (0-shot)	59.03
Winogrande (5-shot)	76.40
GSM8k (5-shot)	21.46