metadata

language:
  - en
license: mit
base_model:
  - unsloth/Phi-3-mini-4k-instruct
datasets:
  - cognitivecomputations/Dolphin-2.9.2
  - teknium/OpenHermes-2.5
  - m-a-p/CodeFeedback-Filtered-Instruction
  - cognitivecomputations/dolphin-coder
  - cognitivecomputations/samantha-data
  - microsoft/orca-math-word-problems-200k
  - internlm/Agent-FLAN
  - cognitivecomputations/SystemChat-2.0
model-index:
  - name: dolphin-2.9.2-Phi-3-Medium-abliterated
    results:
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: IFEval (0-Shot)
          type: HuggingFaceH4/ifeval
          args:
            num_few_shot: 0
        metrics:
          - type: inst_level_strict_acc and prompt_level_strict_acc
            value: 36.13
            name: strict accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: BBH (3-Shot)
          type: BBH
          args:
            num_few_shot: 3
        metrics:
          - type: acc_norm
            value: 45.44
            name: normalized accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MATH Lvl 5 (4-Shot)
          type: hendrycks/competition_math
          args:
            num_few_shot: 4
        metrics:
          - type: exact_match
            value: 12.39
            name: exact match
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: GPQA (0-shot)
          type: Idavidrein/gpqa
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 10.4
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MuSR (0-shot)
          type: TAUR-Lab/MuSR
          args:
            num_few_shot: 0
        metrics:
          - type: acc_norm
            value: 10.36
            name: acc_norm
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
          name: Open LLM Leaderboard
      - task:
          type: text-generation
          name: Text Generation
        dataset:
          name: MMLU-PRO (5-shot)
          type: TIGER-Lab/MMLU-Pro
          config: main
          split: test
          args:
            num_few_shot: 5
        metrics:
          - type: acc
            value: 38.82
            name: accuracy
        source:
          url: >-
            https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=cognitivecomputations/dolphin-2.9.2-Phi-3-Medium-abliterated
          name: Open LLM Leaderboard

Dolphin 2.9.2 Phi 3 Medium (Abliterated) 🐬

Curated and trained by Eric Hartford, Lucas Atkins, Fernando Fernandes, and with help from the community of Cognitive Computations
Uncensored by FailSpy

Discord: https://discord.gg/cognitivecomputations

Our appreciation for the sponsor of Dolphin 2.9.2:

Crusoe Cloud - provided excellent on-demand 8xL40Snode

This model is based on Phi-3-Medium-Instruct-4k, and is governed by the MIT license with which Microsoft released Phi-3.

Since Microsoft only released the fine-tuned model - Dolphin-2.9.2-Phi-3-Medium has not been entirely cleaned of refusals.

The base model has 4k context, and the qLoRA fine-tuning was with 4k sequence length.

The model's weights were then adjusted to ablate and inhibit refusals based on the methodology described in 'Refusal in LLMs is mediated by a single direction' This effectively uncensors the model whilst minimizing affecting other features in the model.

It took 3.5 days on 8xL40S node provided by Crusoe Cloud

This model uses the ChatML prompt template.

example:

<|im_start|>system
You are Dolphin, a helpful AI assistant.<|im_end|>
<|im_start|>user
{prompt}<|im_end|>
<|im_start|>assistant

Dolphin-2.9.2 has a variety of instruction, conversational, and coding skills. It also has initial agentic abilities and supports function calling. We have filtered the dataset to remove alignment and bias. This makes the model more compliant. You are advised to implement your own alignment layer before exposing the model as a service. Please read my blog post about uncensored models. https://erichartford.com/uncensored-models You are responsible for any content you create using this model. Enjoy responsibly.

evals:

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	25.59
IFEval (0-Shot)	36.13
BBH (3-Shot)	45.44
MATH Lvl 5 (4-Shot)	12.39
GPQA (0-shot)	10.40
MuSR (0-shot)	10.36
MMLU-PRO (5-shot)	38.82