language:
- en
- code
license: apache-2.0
tags:
- merge
- computer science
datasets:
- open-phi/programming_books_llama
- open-phi/textbooks
inference:
parameters:
do_sample: true
temperature: 0.2
top_p: 0.14
top_k: 12
max_new_tokens: 250
repetition_penalty: 1.15
widget:
- text: 'To calculate the factorial of n, we can use the following function:'
model-index:
- name: TinyMistral-248M-v2.5
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: 24.57
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
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: 27.49
name: normalized accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
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: 23.15
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
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: 46.72
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
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: 47.83
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
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
name: accuracy
source:
url: >-
https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5
name: Open LLM Leaderboard
TinyMistral-248M-v2.5
This model was created by merging TinyMistral-248M-v1 and v2, then further pretraining on synthetic textbooks. The resulting model's performance is superior to both, after personal evaluation.
During training, this model reached an average perplexity score of 4, outperforming V1 by nearly 7x, and V2 by 4x.
You can use the following config to reproduce the merged model:
base_model: Locutusque/TinyMistral-248M-v2
dtype: float16
merge_method: ties
parameters:
int8_mask: 1.0
normalize: 1.0
slices:
- sources:
- layer_range: [0, 12]
model: Locutusque/TinyMistral-248M
parameters:
density: [1.0, 0.7, 0.1]
weight: 1.0
- layer_range: [0, 12]
model: Locutusque/TinyMistral-248M-v2
parameters:
density: 0.5
weight: [0.0, 0.3, 0.7, 1.0]
This model can also answer basic questions, without needing to do any fine-tuning.
This model was also created as an attempt to fix the issue with V2 - the weights were prone to exploding gradients, making it difficult to fine-tune. This model is easier to fine-tune.
To get the best out of this model, I recommend installing it, and trying it out yourself, as the model's performance seems to degrade in the inference API.
Open LLM Leaderboard Evaluation Results
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 28.29 |
| AI2 Reasoning Challenge (25-Shot) | 24.57 |
| HellaSwag (10-Shot) | 27.49 |
| MMLU (5-Shot) | 23.15 |
| TruthfulQA (0-shot) | 46.72 |
| Winogrande (5-shot) | 47.83 |
| GSM8k (5-shot) | 0.00 |