Quantization made by Richard Erkhov.

Magic-Dolphin-7b - GGUF

Model creator: https://huggingface.co/InferenceIllusionist/
Original model: https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b/

Name	Quant method	Size
Magic-Dolphin-7b.Q2_K.gguf	Q2_K	2.53GB
Magic-Dolphin-7b.IQ3_XS.gguf	IQ3_XS	2.81GB
Magic-Dolphin-7b.IQ3_S.gguf	IQ3_S	2.96GB
Magic-Dolphin-7b.Q3_K_S.gguf	Q3_K_S	2.95GB
Magic-Dolphin-7b.IQ3_M.gguf	IQ3_M	3.06GB
Magic-Dolphin-7b.Q3_K.gguf	Q3_K	3.28GB
Magic-Dolphin-7b.Q3_K_M.gguf	Q3_K_M	3.28GB
Magic-Dolphin-7b.Q3_K_L.gguf	Q3_K_L	3.56GB
Magic-Dolphin-7b.IQ4_XS.gguf	IQ4_XS	3.67GB
Magic-Dolphin-7b.Q4_0.gguf	Q4_0	3.83GB
Magic-Dolphin-7b.IQ4_NL.gguf	IQ4_NL	3.87GB
Magic-Dolphin-7b.Q4_K_S.gguf	Q4_K_S	3.86GB
Magic-Dolphin-7b.Q4_K.gguf	Q4_K	4.07GB
Magic-Dolphin-7b.Q4_K_M.gguf	Q4_K_M	4.07GB
Magic-Dolphin-7b.Q4_1.gguf	Q4_1	4.24GB
Magic-Dolphin-7b.Q5_0.gguf	Q5_0	4.65GB
Magic-Dolphin-7b.Q5_K_S.gguf	Q5_K_S	4.65GB
Magic-Dolphin-7b.Q5_K.gguf	Q5_K	4.78GB
Magic-Dolphin-7b.Q5_K_M.gguf	Q5_K_M	4.78GB
Magic-Dolphin-7b.Q5_1.gguf	Q5_1	5.07GB
Magic-Dolphin-7b.Q6_K.gguf	Q6_K	5.53GB
Magic-Dolphin-7b.Q8_0.gguf	Q8_0	7.17GB

Original model description:

license: apache-2.0 base_model: - cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser - Locutusque/Hyperion-1.5-Mistral-7B - ibm/merlinite-7b library_name: transformers tags: - mergekit - merge - code model-index: - name: Magic-Dolphin-7b 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: 65.78 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b 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: 85.61 name: normalized accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b 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: 64.64 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b 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: 58.01 source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b 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: 79.64 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b 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: 51.18 name: accuracy source: url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=InferenceIllusionist/Magic-Dolphin-7b name: Open LLM Leaderboard

Magic-Dolphin-7b

The follow-up to this model has been released, check out the updated benchmarks here for Excalibur-7b

For GGUF files please look here

A linear merge of:

These three models showed excellent acumen in technical topics so I wanted to see how they would behave together in a merge. Several different ratios were tested before this release, in the end a higher weighting for merlinite-7b helped smooth out some edges. This model is a test of how LAB tuning is impacted by merges with models leveraging DPO.

Benchmark Performance

Name	Avg.	ARC	HellaSwag	MMLU	TruthfulQA	Winogrande	GSM8K
Magic-Dolphin-7b	67.48	65.78	85.61	64.64	58.01	79.64	51.18
dolphin-2.6-mistral-7b-dpo-laser	67.28	66.3	85.73	63.16	61.71	79.16	47.61
merlinite-7b	64	63.65	84.52	64.91	50.15	79.72	41.09
Hyperion-1.5-Mistral-7B	61.43	60.49	83.64	63.57	41.78	78.61	40.49

This was my first experiment with merging models so any feedback is greatly appreciated.

Uses Alpaca template.

Sample Question

Merge Details

Merge Method

This model was merged using the linear merge method.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: models/dolphin-2.6-mistral-7b-dpo-laser
    parameters:
      weight: 1.0
  - model: models/Hyperion-1.5-Mistral-7B
    parameters:
      weight: 0.3
  - model: models/merlinite-7b
    parameters:
      weight: 0.5
merge_method: linear
dtype: float16

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	67.48
AI2 Reasoning Challenge (25-Shot)	65.78
HellaSwag (10-Shot)	85.61
MMLU (5-Shot)	64.64
TruthfulQA (0-shot)	58.01
Winogrande (5-shot)	79.64
GSM8k (5-shot)	51.18