AI PC: Text Generation - a Intel Collection

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

AurelPx/Pegasus-7b-slerp

Text Generation • 7B • Updated Mar 22, 2024 • 6 • 1

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

BAAI/Aquila-7B

Updated Sep 18, 2023 • 536 • 18

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

BAAI/Aquila2-7B

Text Generation • 8B • Updated Jun 7, 2024 • 19 • 6

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

BAAI/AquilaChat-7B

Updated Sep 21, 2023 • 7.79k • 49

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

BAAI/AquilaChat2-7B

Text Generation • Updated Aug 15, 2024 • 7.69k • 15

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

BigSalmon/GPT2Neo1.3BPoints

Text Generation • Updated Apr 4, 2022 • 6

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

EleutherAI/pythia-1.4b

Text Generation • 2B • Updated Jul 9, 2023 • 27.3k • 25

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

EleutherAI/pythia-12b

Text Generation • 12B • Updated Jul 9, 2024 • 6.08k • 139

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

EleutherAI/pythia-14m

Text Generation • 0.0B • Updated Jul 26, 2023 • 226k • 23

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

EleutherAI/pythia-160m

Text Generation • 0.2B • Updated Jul 9, 2023 • 129k • 32

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

EleutherAI/pythia-1b

Text Generation • 1B • Updated Jul 9, 2023 • 54.4k • 40

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

EleutherAI/pythia-2.8b

Text Generation • 3B • Updated Jun 9, 2023 • 19.6k • 31

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

EleutherAI/pythia-410m

Text Generation • 0.5B • Updated Jul 9, 2023 • 106k • 32

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

EleutherAI/pythia-6.9b

Text Generation • 7B • Updated Mar 10 • 21.9k • 56

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

EleutherAI/pythia-70m

0.1B • Updated Nov 21, 2023 • 187k • 71

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

HuggingFaceH4/zephyr-7b-beta

Text Generation • 7B • Updated Oct 16, 2024 • 597k • • 1.75k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Intel/neural-chat-7b-v1-1

Text Generation • Updated Jan 15, 2024 • 35 • 24

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Intel/neural-chat-7b-v3-3

Text Generation • 7B • Updated Nov 11, 2024 • 12.2k • • 78

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Qwen/CodeQwen1.5-7B-Chat

Text Generation • 7B • Updated Apr 30, 2024 • 3.94k • 339

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Qwen/Qwen-1_8B

Text Generation • 2B • Updated Dec 13, 2023 • 6.18k • 70

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Qwen/Qwen-1_8B-Chat

Text Generation • 2B • Updated Dec 13, 2023 • 6.86k • 121

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Qwen/Qwen-7B

Text Generation • 8B • Updated Jan 4, 2024 • 20.2k • 384

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Qwen/Qwen-7B-Chat

Text Generation • 8B • Updated Mar 19, 2024 • 126k • 782

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Qwen/Qwen1.5-0.5B

Text Generation • 0.6B • Updated Apr 5, 2024 • 99.6k • 165

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Qwen/Qwen1.5-0.5B-Chat

Text Generation • 0.6B • Updated Apr 30, 2024 • 809k • 82

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Qwen/Qwen1.5-1.8B

Text Generation • 2B • Updated Apr 5, 2024 • 51.5k • 52

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Qwen/Qwen1.5-1.8B-Chat

Text Generation • 2B • Updated Apr 30, 2024 • 56.4k • • 59

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Qwen/Qwen1.5-4B

Text Generation • 4B • Updated Apr 5, 2024 • 19.5k • 35

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Qwen/Qwen1.5-4B-Chat

Text Generation • 4B • Updated Apr 30, 2024 • 82.7k • 42

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Qwen/Qwen1.5-7B

Text Generation • 8B • Updated Apr 5, 2024 • 85k • 55

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Qwen/Qwen1.5-7B-Chat

Text Generation • 8B • Updated Apr 30, 2024 • 34.9k • 176

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Salesforce/codegen-2B-multi

Text Generation • Updated Jan 31 • 647 • 41

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Salesforce/codegen-350M-mono

Text Generation • Updated Jan 31 • 19.1k • 95

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Salesforce/codegen-6B-multi

Text Generation • Updated Jan 31 • 1.19k • 20

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Salesforce/codegen2-1B_P

Text Generation • Updated Jan 31 • 1.05k • 41

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Salesforce/codegen2-3_7B_P

Text Generation • Updated Jan 31 • 5 • 15

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

Salesforce/codegen2-7B_P

Text Generation • Updated Jan 31 • 3.28k • 26

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

WizardLMTeam/WizardMath-7B-V1.1

Text Generation • Updated Jan 12, 2024 • 2.01k • • 82

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

X-D-Lab/MindChat-Qwen2-4B

Text Generation • 4B • Updated Feb 4, 2024 • 7 • 5

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

adept/persimmon-8b-chat

Text Generation • Updated Oct 11, 2023 • 7.6k • 42

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

baichuan-inc/Baichuan2-13B-Chat

Text Generation • Updated Feb 26, 2024 • 7.7k • 428

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

baichuan-inc/Baichuan2-7B-Base

Text Generation • Updated Jan 31, 2024 • 6.32k • 83

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

baichuan-inc/Baichuan2-7B-Chat

Text Generation • Updated Feb 26, 2024 • 24.2k • 166

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

bigscience/bloom-560m

Text Generation • 0.6B • Updated Sep 26, 2023 • 139k • 361

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

bigscience/bloomz-1b1

Text Generation • 1B • Updated May 27, 2023 • 5.31k • 33

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

bigscience/bloomz-3b

Text Generation • 3B • Updated May 27, 2023 • 9.37k • 81

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

bigscience/bloomz-7b1-mt

Text Generation • 7B • Updated Jan 10, 2024 • 3.07k • 142

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

facebook/opt-1.3b

Text Generation • Updated Sep 15, 2023 • 58k • 176

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

facebook/opt-125m

Text Generation • Updated Sep 15, 2023 • 6.56M • 209

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

facebook/opt-13b

Text Generation • Updated Jan 24, 2023 • 19.6k • 65

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

facebook/opt-2.7b

Text Generation • Updated Sep 15, 2023 • 36k • 86

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

facebook/opt-350m

Text Generation • Updated Sep 15, 2023 • 130k • 146

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

facebook/opt-6.7b

Text Generation • Updated Jan 24, 2023 • 46k • 118

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

facebook/opt-iml-1.3b

Text Generation • Updated Jan 26, 2023 • 1.01k • 29

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

google/codegemma-1.1-2b

Text Generation • 3B • Updated Aug 7, 2024 • 1.79k • 19

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

google/codegemma-1.1-7b-it

Text Generation • 9B • Updated Aug 7, 2024 • 314 • 50

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

google/codegemma-2b

Text Generation • 3B • Updated Aug 7, 2024 • 8.32k • 83

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

google/codegemma-7b

Text Generation • 9B • Updated Aug 7, 2024 • 4.12k • 196

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

google/gemma-1.1-2b-it

Text Generation • 3B • Updated Jun 27, 2024 • 162k • 165

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

google/gemma-1.1-7b-it

Text Generation • 9B • Updated Jun 27, 2024 • 15.6k • 273

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

google/gemma-2b

Text Generation • 3B • Updated Sep 27, 2024 • 231k • 1.06k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

google/gemma-2b-it

Text Generation • 3B • Updated Sep 27, 2024 • 152k • 777

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

google/gemma-7b

Text Generation • 9B • Updated Jun 27, 2024 • 150k • 3.19k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

google/gemma-7b-it

Text Generation • 9B • Updated Aug 14, 2024 • 100k • 1.2k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

ibm-granite/granite-3b-code-base-2k

Text Generation • 3B • Updated Sep 2, 2024 • 1.32k • 37

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

ibm-granite/granite-3b-code-instruct-2k

Text Generation • 3B • Updated Sep 2, 2024 • 1.57k • 37

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

ibm-granite/granite-8b-code-base-4k

Text Generation • 8B • Updated Sep 2, 2024 • 3.43k • 30

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

ibm-granite/granite-8b-code-instruct-4k

Text Generation • 8B • Updated Sep 2, 2024 • 1.63k • 115

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

internlm/internlm2-1_8b

Text Generation • Updated Aug 20, 2024 • 10.4k • 32

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

internlm/internlm2-7b

Text Generation • Updated Mar 13 • 28.1k • 42

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

internlm/internlm2-chat-1_8b

Text Generation • 2B • Updated Mar 13 • 8.49k • 34

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

internlm/internlm2-chat-7b

Text Generation • 8B • Updated Mar 13 • 54k • 83

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

internlm/internlm2-chat-7b-sft

Text Generation • 8B • Updated Aug 20, 2024 • 6.08k • 6

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

internlm/internlm2-math-7b

Text Generation • 8B • Updated Mar 13 • 822 • 27

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

internlm/internlm2-math-base-7b

Text Generation • 8B • Updated Mar 13 • 36 • 2

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

ise-uiuc/Magicoder-CL-7B

Text Generation • 7B • Updated Dec 6, 2023 • 8 • 21

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

ise-uiuc/Magicoder-DS-6.7B

Text Generation • 7B • Updated Mar 6, 2024 • 936 • 38

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

ise-uiuc/Magicoder-S-CL-7B

Text Generation • 7B • Updated Dec 6, 2023 • 1.03k • 44

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

ise-uiuc/Magicoder-S-DS-6.7B

Text Generation • 7B • Updated Mar 6, 2024 • 4.44k • 204

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

meta-llama/Llama-2-13b-chat-hf

Text Generation • 13B • Updated Apr 17, 2024 • 180k • • 1.09k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

meta-llama/Llama-2-13b-hf

Text Generation • 13B • Updated Apr 17, 2024 • 64.3k • 607

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

meta-llama/Llama-2-7b-chat-hf

Text Generation • 7B • Updated Apr 17, 2024 • 973k • 4.54k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

meta-llama/Llama-2-7b-hf

Text Generation • 7B • Updated Apr 17, 2024 • 692k • 2.12k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

meta-llama/Meta-Llama-3-8B

Text Generation • 8B • Updated Sep 27, 2024 • 513k • • 6.27k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

meta-llama/Meta-Llama-3-8B-Instruct

Text Generation • 8B • Updated Jun 18 • 1.13M • • 4.12k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

meta-llama/Meta-Llama-Guard-2-8B

Text Generation • 8B • Updated May 13, 2024 • 7.22k • 297

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

microsoft/Phi-3-medium-4k-instruct

Text Generation • 14B • Updated Mar 11 • 16k • 221

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

microsoft/Phi-3-mini-128k-instruct

Text Generation • 4B • Updated Mar 2 • 1.09M • 1.66k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

microsoft/phi-2

Text Generation • 3B • Updated Apr 29, 2024 • 855k • 3.38k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

mistralai/Mistral-7B-Instruct-v0.2

Text Generation • 7B • Updated 16 days ago • 1.13M • • 2.91k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

mistralai/Mistral-7B-Instruct-v0.3

7B • Updated 16 days ago • 1.02M • 1.98k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

mistralai/Mistral-7B-v0.3

7B • Updated 16 days ago • 76.1k • 512

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

mosaicml/mpt-7b

Text Generation • Updated Mar 5, 2024 • 11.7k • 1.17k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

mosaicml/mpt-7b-8k

Text Generation • Updated Mar 5, 2024 • 1.9k • 26

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

mosaicml/mpt-7b-8k-chat

Text Generation • Updated Mar 5, 2024 • 1.71k • 40

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

mosaicml/mpt-7b-chat

Text Generation • Updated Mar 5, 2024 • 81k • 516

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

mosaicml/mpt-7b-instruct

Text Generation • Updated Mar 5, 2024 • 5.64k • 470

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

mosaicml/mpt-7b-storywriter

Text Generation • Updated Mar 5, 2024 • 2.1k • 837

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

openai-community/gpt2

Text Generation • 0.1B • Updated Feb 19, 2024 • 14.1M • 2.89k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

openbmb/MiniCPM-2B-sft-bf16

Text Generation • Updated Sep 7, 2024 • 25k • 119

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

openchat/openchat-3.6-8b-20240522

Text Generation • 8B • Updated May 28, 2024 • 13.6k • • 155

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

stabilityai/stablelm-2-12b

Text Generation • 12B • Updated Jul 10, 2024 • 815 • 120

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

stabilityai/stablelm-2-12b-chat

Text Generation • 12B • Updated May 20, 2024 • 1.45k • 87

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

stabilityai/stablelm-2-1_6b

Text Generation • 2B • Updated Jul 10, 2024 • 1.82k • 191

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

stabilityai/stablelm-2-1_6b-chat

Text Generation • 2B • Updated Jun 3, 2024 • 3.1k • 32

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

stabilityai/stablelm-2-zephyr-1_6b

Text Generation • 2B • Updated Jun 3, 2024 • 5.85k • 185

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

stabilityai/stablelm-3b-4e1t

Text Generation • 3B • Updated Mar 7, 2024 • 15k • 311

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

stabilityai/stablelm-base-alpha-3b

Text Generation • Updated Oct 19, 2023 • 3.07k • 82

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

stabilityai/stablelm-tuned-alpha-7b

Text Generation • Updated Apr 19, 2023 • 3.77k • 360

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

stabilityai/stablelm-zephyr-3b

Text Generation • 3B • Updated Jul 10, 2024 • 14.5k • 257

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

stanford-crfm/BioMedLM

Text Generation • Updated Mar 28, 2024 • 3.38k • 433

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

tiiuae/falcon-11B

Text Generation • 11B • Updated Dec 17, 2024 • 42.8k • 212

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

tiiuae/falcon-7b

Text Generation • 7B • Updated Oct 12, 2024 • 79.1k • 1.09k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

tiiuae/falcon-7b-instruct

Text Generation • 7B • Updated Oct 12, 2024 • 143k • 1k

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

togethercomputer/Pythia-Chat-Base-7B

Text Generation • Updated Mar 29, 2023 • 1.87k • 68

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

togethercomputer/RedPajama-INCITE-7B-Base

Text Generation • Updated Jun 6, 2023 • 2.85k • 92

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

togethercomputer/RedPajama-INCITE-7B-Chat

Text Generation • Updated Jun 5, 2023 • 1.88k • 94

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

togethercomputer/RedPajama-INCITE-7B-Instruct

Text Generation • Updated Aug 9, 2023 • 2.06k • 106

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

togethercomputer/RedPajama-INCITE-Chat-3B-v1

Text Generation • Updated May 9, 2023 • 1.89k • 152

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation

xverse/XVERSE-7B-Chat

Text Generation • Updated Nov 6, 2023 • 7.56k • 8

Note This model was tested with OpenVINO version 2024.1.0, using the OVModelForCausalLM library with INT4 weight compression for the lowest memory footprint. To convert the model to OpenVINO, follow instructions at: https://huggingface.co/docs/optimum/main/en/intel/installation