Adding Evaluation Results (#1)

4a9b9a9 verified 4 months ago

No virus

5.76 kB

	---
	license: apache-2.0
	datasets:
	- teknium/openhermes
	base_model: BEE-spoke-data/smol_llama-220M-GQA
	inference:
	parameters:
	do_sample: true
	renormalize_logits: true
	temperature: 0.25
	top_p: 0.95
	top_k: 50
	min_new_tokens: 2
	max_new_tokens: 96
	repetition_penalty: 1.03
	no_repeat_ngram_size: 5
	epsilon_cutoff: 0.0008
	widget:
	- text: "Below is an instruction that describes a task, paired with an input that\
	\ provides further context. Write a response that appropriately completes the\
	\ request. \n \n### Instruction: \n \nWrite an ode to Chipotle burritos.\
	\ \n \n### Response: \n"
	example_title: burritos
	model-index:
	- name: smol_llama-220M-openhermes
	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: 25.17
	name: normalized accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-openhermes
	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: 28.98
	name: normalized accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-openhermes
	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: 26.17
	name: accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-openhermes
	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: 43.08
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-openhermes
	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: 52.01
	name: accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-openhermes
	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: 0.61
	name: accuracy
	source:
	url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=BEE-spoke-data/smol_llama-220M-openhermes
	name: Open LLM Leaderboard
	---


	# BEE-spoke-data/smol_llama-220M-openhermes

	> Please note that this is an experiment, and the model has limitations because it is smol.


	prompt format is alpaca


	```
	Below is an instruction that describes a task, paired with an input that
	provides further context. Write a response that appropriately completes
	the request.

	### Instruction:

	How can I increase my meme production/output? Currently, I only create them in ancient babylonian which is time consuming.

	### Inputs:

	### Response:
	```

	It was trained on inputs so if you have inputs (like some text to ask a question about) then include it under `### Inputs:`


	## Example

	Output on the text above ^. The inference API is set to sample with low temp so you should see (_at least slightly_) different generations each time.


	![image/png](https://cdn-uploads.huggingface.co/production/uploads/60bccec062080d33f875cd0c/0nFP2jsBkritnryKmI8NV.png)

	Note that the inference API parameters used here are an initial educated guess, and may be updated over time:

	```yml
	inference:
	parameters:
	do_sample: true
	renormalize_logits: true
	temperature: 0.25
	top_p: 0.95
	top_k: 50
	min_new_tokens: 2
	max_new_tokens: 96
	repetition_penalty: 1.03
	no_repeat_ngram_size: 5
	epsilon_cutoff: 0.0008
	```

	Feel free to experiment with the parameters using the model in Python and let us know if you have improved results with other params!

	## Data

	Note that this checkpoint was fine-tuned on `teknium/openhermes`, which is generated/synthetic data by an OpenAI model. This means usage of this checkpoint should follow their terms of use: https://openai.com/policies/terms-of-use


	---

	# [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_BEE-spoke-data__smol_llama-220M-openhermes)

	\| Metric \|Value\|
	\|---------------------------------\|----:\|
	\|Avg. \|29.34\|
	\|AI2 Reasoning Challenge (25-Shot)\|25.17\|
	\|HellaSwag (10-Shot) \|28.98\|
	\|MMLU (5-Shot) \|26.17\|
	\|TruthfulQA (0-shot) \|43.08\|
	\|Winogrande (5-shot) \|52.01\|
	\|GSM8k (5-shot) \| 0.61\|