license: mit
datasets:
- garage-bAInd/Open-Platypus
pipeline_tag: text-generation
model-index:
- name: Tinypus-1.5B
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: 33.45
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ba2han/Tinypus-1.5B
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: 57.35
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ba2han/Tinypus-1.5B
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: 25.53
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ba2han/Tinypus-1.5B
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: 39.35
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ba2han/Tinypus-1.5B
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: 57.7
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ba2han/Tinypus-1.5B
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: 0.99
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Ba2han/Tinypus-1.5B
name: Open LLM Leaderboard
*drumroll please*
Introducing Tinypus!
I passthrough merged base Tiny Llama Chat with itself, then fine-tuned with around 1/3 of Platypus dataset.
Observations:
It's smarter (I think?)
It sometimes throws "### Instruction:" line. This could be due to the platypus dataset, or the fact that I know jackshit about programming. You can add it to "custom stopping strings" in oobaboga.
It may be possible to train very specialized mini experts and merge them???
Template
Same with TinyLlama/TinyLlama-1.1B-Chat-v1.0
Merge details
slices:
sources:
model: E://text-generation-webui//models//TinyLlama
layer_range: [0, 12]
sources:
model: E://text-generation-webui//models//TinyLlama
layer_range: [4, 22]
merge_method: passthrough
dtype: bfloat16
QLoRA Details
Chunk Length: 1152 R/A: 64/128 Epoch: 1 q-k-v-o
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 35.73 |
| AI2 Reasoning Challenge (25-Shot) | 33.45 |
| HellaSwag (10-Shot) | 57.35 |
| MMLU (5-Shot) | 25.53 |
| TruthfulQA (0-shot) | 39.35 |
| Winogrande (5-shot) | 57.70 |
| GSM8k (5-shot) | 0.99 |