ParaLlama-p-medium

crumb/ParaLlama-p-medium

ParaLlama-p-medium is a text generation model from crumb. Use it when you need the model to write or continue text. It is set up for transformers.

Downloads · 30 days

5% of all-time downloads

All-time downloads

522

Public

Parameters

545M

2.2 GB on disk

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.safetensors1.1 GB · 100%

At a glance

Task: Text Generation
Library: transformers
Model type: nano
Access: Public
Created: Jan 25, 2024
Updated: Jan 27, 2024
SHA: 02bc5c18

Try a prompt

Model card

From the Hugging Face model README

Tasks	Version	Filter	n-shot	Metric	Value		Stderr
arc_challenge	1	none	25	acc	0.1809	±	0.0112
		none	25	acc_norm	0.2201	±	0.0121
truthfulqa_mc2	2	none	0	acc	0.4543	±	0.0154
winogrande	1	none	5	acc	0.5154	±	0.014
hellaswag	1	none	10	acc	0.2822	±	0.0045
		none	10	acc_norm	0.3009	±	0.0046

0.26024912280701756

Tasks	Filter	n-shot	Metric	Value		Stderr
abstract_algebra	none	5	acc	0.3100	±	0.0465
anatomy	none	5	acc	0.2667	±	0.0382
astronomy	none	5	acc	0.1776	±	0.0311
business_ethics	none	5	acc	0.2200	±	0.0416
clinical_knowledge	none	5	acc	0.2528	±	0.0267
college_biology	none	5	acc	0.2153	±	0.0344
college_chemistry	none	5	acc	0.2300	±	0.0423
college_computer_science	none	5	acc	0.3400	±	0.0476
college_mathematics	none	5	acc	0.3200	±	0.0469
college_medicine	none	5	acc	0.2370	±	0.0324
college_physics	none	5	acc	0.1961	±	0.0395
computer_security	none	5	acc	0.2700	±	0.0446
conceptual_physics	none	5	acc	0.2383	±	0.0279
econometrics	none	5	acc	0.2982	±	0.0430
electrical_engineering	none	5	acc	0.2552	±	0.0363
elementary_mathematics	none	5	acc	0.2513	±	0.0223
formal_logic	none	5	acc	0.1667	±	0.0333
global_facts	none	5	acc	0.1600	±	0.0368
high_school_biology	none	5	acc	0.3000	±	0.0261
high_school_chemistry	none	5	acc	0.2167	±	0.0290
high_school_computer_science	none	5	acc	0.2300	±	0.0423
high_school_european_history	none	5	acc	0.2242	±	0.0326
high_school_geography	none	5	acc	0.3283	±	0.0335
high_school_government_and_politics	none	5	acc	0.3627	±	0.0347
high_school_macroeconomics	none	5	acc	0.3513	±	0.0242
high_school_mathematics	none	5	acc	0.2630	±	0.0268
high_school_microeconomics	none	5	acc	0.3067	±	0.0300
high_school_physics	none	5	acc	0.2583	±	0.0357
high_school_psychology	none	5	acc	0.3174	±	0.0200
high_school_statistics	none	5	acc	0.4722	±	0.0340
high_school_us_history	none	5	acc	0.2353	±	0.0298
high_school_world_history	none	5	acc	0.2616	±	0.0286
human_aging	none	5	acc	0.2108	±	0.0274
human_sexuality	none	5	acc	0.2977	±	0.0401
international_law	none	5	acc	0.2645	±	0.0403
jurisprudence	none	5	acc	0.2130	±	0.0396
logical_fallacies	none	5	acc	0.2331	±	0.0332
machine_learning	none	5	acc	0.2857	±	0.0429
management	none	5	acc	0.1748	±	0.0376
marketing	none	5	acc	0.1838	±	0.0254
medical_genetics	none	5	acc	0.3000	±	0.0461
miscellaneous	none	5	acc	0.2720	±	0.0159
moral_disputes	none	5	acc	0.2457	±	0.0232
moral_scenarios	none	5	acc	0.2391	±	0.0143
nutrition	none	5	acc	0.2255	±	0.0239
philosophy	none	5	acc	0.1961	±	0.0226
prehistory	none	5	acc	0.2284	±	0.0234
professional_accounting	none	5	acc	0.2553	±	0.0260
professional_law	none	5	acc	0.2458	±	0.0110
professional_medicine	none	5	acc	0.4485	±	0.0302
professional_psychology	none	5	acc	0.2516	±	0.0176
public_relations	none	5	acc	0.2727	±	0.0427
security_studies	none	5	acc	0.3551	±	0.0306
sociology	none	5	acc	0.2587	±	0.0310
us_foreign_policy	none	5	acc	0.2100	±	0.0409
virology	none	5	acc	0.2229	±	0.0324
world_religions	none	5	acc	0.2105	±	0.0313

Task: Text Generation
Library: transformers
Type: nano
Created: Jan 25, 2024
Updated: Jan 27, 2024