metadata
license: cc-by-nc-nd-4.0
model-index:
- name: caigun-lora-model-34B-v2
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: 65.02
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=APMIC/caigun-lora-model-34B-v2
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: 85.28
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=APMIC/caigun-lora-model-34B-v2
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: 75.69
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=APMIC/caigun-lora-model-34B-v2
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: 58.03
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=APMIC/caigun-lora-model-34B-v2
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: 83.03
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=APMIC/caigun-lora-model-34B-v2
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: 60.12
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=APMIC/caigun-lora-model-34B-v2
name: Open LLM Leaderboard
This is model finetuned on Orca style dataset.
Model Details:
Model Name: caigun-lora-model-33B
Model Version: 1.0
Date Created: 2023/12/21
Model Overview:
Intended Use: caigun-lora-model-33B is a LLM designed for various purpose.
Training Data: Orca style dataset
Model Architecture: It is based on LLaMA architecture.
Training Procedure: [Stay tuned for updates]
Model Performance: [Stay tuned for updates]
Potential Risks: It's important to consider ethical implications related to the use of our model.
Updates and Version History:
Version 1.0: finetuned on fake news detection.
Version 2.0: finetuned on Orca style dataset.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
Metric | Value |
---|---|
Avg. | 71.19 |
AI2 Reasoning Challenge (25-Shot) | 65.02 |
HellaSwag (10-Shot) | 85.28 |
MMLU (5-Shot) | 75.69 |
TruthfulQA (0-shot) | 58.03 |
Winogrande (5-shot) | 83.03 |
GSM8k (5-shot) | 60.12 |