metadata
license: other
license_name: yi-license
license_link: >-
https://huggingface.co/cognitivecomputations/dolphin-2.2-yi-34b-200k/blob/main/LICENSE
model-index:
- name: SmaugDolphin-60B
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: 73.38
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SmaugDolphin-60B
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: 86.55
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SmaugDolphin-60B
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: 76.78
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SmaugDolphin-60B
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: 67.44
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SmaugDolphin-60B
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: 83.5
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SmaugDolphin-60B
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: 70.96
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=macadeliccc/SmaugDolphin-60B
name: Open LLM Leaderboard
Smaug Dolphin 60B
This model is a MoErge of abacusai/Smaug-34B-v0.1 and cognitivecomputations/dolphin-2.2-yi-34b-200k
This model works as expected. Evaluations are running now.
GGUF + iMatrix
Available here
AWQ
TODO
Example output
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 76.44 |
AI2 Reasoning Challenge (25-Shot) | 73.38 |
HellaSwag (10-Shot) | 86.55 |
MMLU (5-Shot) | 76.78 |
TruthfulQA (0-shot) | 67.44 |
Winogrande (5-shot) | 83.50 |
GSM8k (5-shot) | 70.96 |