gemma-2b-it-tamil-v0.1-alpha / README.md

Adding Evaluation Results (#1)

10cb994 verified 4 months ago

No virus

7.56 kB

	---
	language:
	- en
	- ta
	license: other
	datasets:
	- vicgalle/alpaca-gpt4
	- abhinand/tamil-alpaca
	license_name: gemma-terms-of-use
	license_link: https://ai.google.dev/gemma/terms
	base_model: abhinand/gemma-2b-tamil
	model-index:
	- name: gemma-2b-it-tamil-v0.1-alpha
	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: 50.09
	name: normalized accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-it-tamil-v0.1-alpha
	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: 71.41
	name: normalized accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-it-tamil-v0.1-alpha
	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: 39.94
	name: accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-it-tamil-v0.1-alpha
	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: 42.63
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-it-tamil-v0.1-alpha
	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: 64.96
	name: accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-it-tamil-v0.1-alpha
	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: 16.6
	name: accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=abhinand/gemma-2b-it-tamil-v0.1-alpha
	name: Open LLM Leaderboard
	---

	# Gemma 2B Tamil v0.1 Alpha [Experimental Release]

	This is a Tamil instruction finetuned version of Google's Gemma 2B model. This is an experiment to see if Gemma can be adapted for Tamil without expanding vocabulary. While the responses may be rusty at times, it shows a lot of promise for a 2B parameter model.

	Procedure:

	1. The [Gemma base model](https://huggingface.co/google/gemma-2b) was continually pretrained on all available Tamil Wikipedia data for 3 epochs.
	2. The updated model was then finetuned on a mix of English and Tamil alpaca datasets for 5 epochs.

	> Note: This project is currently under development (FOR TAMIL). The initial pretraining phase may not have been extensive enough, which suggests that the model's performance could improve by extending the pretraining on a larger dataset, such as CulturaX.

	### 🏆 Benchmarks

	This model outperforms Google's Gemma 2B base and instruct models on all benchmarks in Nous evaluation suite. It also surprisingly outperforms [mlabonne/Gemmalpaca-2B](https://huggingface.co/mlabonne/Gemmalpaca-2B) (the best performing 2B model in benchmarks as of Feb 25, 2024) despite being a model aimed at language adaptation.

	\| Model \| Average \| AGIEval \| GPT4All \| TruthfulQA \| Bigbench \|
	\|---\|---:\|---:\|---:\|---:\|---:\|
	\|[gemma-2b-it-tamil-v0.1-alpha](https://huggingface.co/abhinand/gemma-2b-it-tamil-v0.1-alpha)[📄](https://gist.github.com/abhinand5/559d542437f6b7060fee94cc1f7861f5)\| 39.41\| 23.38\| 58.94\| 43.18\| 32.14\|
	\| [mlabonne/Gemmalpaca-2B](https://huggingface.co/mlabonne/Gemmalpaca-2B) [📄](https://gist.github.com/mlabonne/4b638752fc3227df566f9562064cb864) \| 38.39 \| 24.48 \| 51.22 \| 47.02 \| 30.85 \|
	\| [google/gemma-2b-it](https://huggingface.co/google/gemma-2b-it) [📄](https://gist.github.com/mlabonne/db0761e74175573292acf497da9e5d95) \| 36.1 \| 23.76 \| 43.6 \| 47.64 \| 29.41 \|
	\| [google/gemma-2b](https://huggingface.co/google/gemma-2b) [📄](https://gist.github.com/mlabonne/7df1f238c515a5f63a750c8792cef59e) \| 34.26 \| 22.7 \| 43.35 \| 39.96 \| 31.03 \|

	## Model description

	- Model type: A 2B parameter GPT-like model finetuned on 100,000 samples consisting of an equal proportion of English and Tamil samples.
	- Language(s): Bilingual. English and Tamil.
	- License: [Google Gemma Terms of Use](https://ai.google.dev/gemma/terms)
	- Finetuned from model: [abhinand/gemma-2b-tamil](https://huggingface.co/abhinand/gemma-2b-tamil)
	- Training Precision: `bfloat16`
	- Training Hardware: 4x Nvidia RTX 3090 GPUs
	- Training Cost: $20


	## Support my work

	If you appreciate this work and would like to support its continued development, consider [buying me a coffee](https://www.buymeacoffee.com/abhinand.b). Your support is invaluable and greatly appreciated.

	[!["Buy Me A Coffee"](https://www.buymeacoffee.com/assets/img/custom_images/orange_img.png)](https://www.buymeacoffee.com/abhinand.b)

	## Prompting Format [Alpaca]

	Prompt Template Without Input

	```
	{system_prompt}

	### Instruction:
	{instruction or query}

	### Response:
	{response}
	```

	Prompt Template With Input

	```
	{system_prompt}

	### Instruction:
	{instruction or query}

	### Input:
	{input}

	### Response:
	{response}
	```

	## Usage Note

	It's important to note that the models have not undergone detoxification. Therefore, while they possess impressive linguistic capabilities, there is a possibility for them to generate content that could be deemed harmful or offensive. We urge users to exercise discretion and supervise the model's outputs closely, especially in public or sensitive applications.

	## Meet the Developers

	Get to know the creators behind this innovative model and follow their contributions to the field:

	- [Abhinand Balachandran](https://www.linkedin.com/in/abhinand-05/)

	We hope this model serves as a valuable tool in your NLP toolkit and look forward to seeing the advancements it will enable in the understanding and generation of the Tamil language.
	# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
	Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_abhinand__gemma-2b-it-tamil-v0.1-alpha)

	\| Metric \|Value\|
	\|---------------------------------\|----:\|
	\|Avg. \|47.60\|
	\|AI2 Reasoning Challenge (25-Shot)\|50.09\|
	\|HellaSwag (10-Shot) \|71.41\|
	\|MMLU (5-Shot) \|39.94\|
	\|TruthfulQA (0-shot) \|42.63\|
	\|Winogrande (5-shot) \|64.96\|
	\|GSM8k (5-shot) \|16.60\|