Downloads · 30 days
507
2% of all-time downloads
InferenceIllusionist_-_Magic-Dolphin-7b-gguf
RichardErkhov/InferenceIllusionist_-_Magic-Dolphin-7b-gguf
InferenceIllusionist_-_Magic-Dolphin-7b-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
All-time downloads
23.8K
Public
Repo size
82.2 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.gguf95.2 GB · 100%
At a glance
- Access
- Public
- Created
- Jun 20, 2024
- Updated
- Jun 20, 2024
- SHA
- 3699333c
Model card
From the Hugging Face model README
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
- 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:
Magic-Dolphin-7b
<img src="https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b/resolve/main/magic-dolphin.jfif" width="500"/><b>The follow-up to this model has been released, check out the updated benchmarks here for Excalibur-7b</b>
For GGUF files please look here
A linear merge of:
- cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
- Locutusque/Hyperion-1.5-Mistral-7B
- ibm/merlinite-7b
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 |
|---|---|---|---|---|---|---|---|
| <b>Magic-Dolphin-7b</b> | <u><b>67.48</b></u> | 65.78 | 85.61 | 64.64 | 58.01 | 79.64 | <u><b>51.18</b></u> |
| 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.
<p align="center"> </p><b>Sample Question</b> <img src="https://huggingface.co/InferenceIllusionist/Magic-Dolphin-7b/resolve/main/magic-dolphin.JPG" width="750"/>
Merge Details
Merge Method
This model was merged using the linear merge method.
Models Merged
The following models were included in the merge:
- cognitivecomputations/dolphin-2.6-mistral-7b-dpo-laser
- Locutusque/Hyperion-1.5-Mistral-7B
- ibm/merlinite-7b
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 |
- Created
- Jun 20, 2024
- Updated
- Jun 20, 2024