TinyMistral-248M-v2.5/README.md

language, license, tags, datasets, inference, widget, model-index

language	license	tags	datasets	inference	widget	model-index
en code	apache-2.0	merge computer science	open-phi/programming_books_llama open-phi/textbooks	parameters do_sample temperature top_p top_k max_new_tokens repetition_penalty true 0.2 0.14 12 250 1.15	text To calculate the factorial of n, we can use the following function:	name results TinyMistral-248M-v2.5 task dataset metrics source type name text-generation Text Generation name type config split args AI2 Reasoning Challenge (25-Shot) ai2_arc ARC-Challenge test num_few_shot 25 type value name acc_norm 24.57 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type split args HellaSwag (10-Shot) hellaswag validation num_few_shot 10 type value name acc_norm 27.49 normalized accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU (5-Shot) cais/mmlu all test num_few_shot 5 type value name acc 23.15 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args TruthfulQA (0-shot) truthful_qa multiple_choice validation num_few_shot 0 type value mc2 46.72 url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args Winogrande (5-shot) winogrande winogrande_xl validation num_few_shot 5 type value name acc 47.83 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args GSM8k (5-shot) gsm8k main test num_few_shot 5 type value name acc 0.0 accuracy url name https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args IFEval (0-Shot) HuggingFaceH4/ifeval num_few_shot 0 type value name inst_level_strict_acc and prompt_level_strict_acc 13.36 strict accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args BBH (3-Shot) BBH num_few_shot 3 type value name acc_norm 3.18 normalized accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MATH Lvl 5 (4-Shot) hendrycks/competition_math num_few_shot 4 type value name exact_match 0.0 exact match url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args GPQA (0-shot) Idavidrein/gpqa num_few_shot 0 type value name acc_norm 0.11 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type args MuSR (0-shot) TAUR-Lab/MuSR num_few_shot 0 type value name acc_norm 5.07 acc_norm url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5 Open LLM Leaderboard task dataset metrics source type name text-generation Text Generation name type config split args MMLU-PRO (5-shot) TIGER-Lab/MMLU-Pro main test num_few_shot 5 type value name acc 1.5 accuracy url name https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=Locutusque/TinyMistral-248M-v2.5 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

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	3.87
IFEval (0-Shot)	13.36
BBH (3-Shot)	3.18
MATH Lvl 5 (4-Shot)	0.00
GPQA (0-shot)	0.11
MuSR (0-shot)	5.07
MMLU-PRO (5-shot)	1.50