Tom Jobbins's picture

Tom Jobbins PRO

TheBloke

·

AI & ML interests

LLM: quantisation, fine tuning

Organizations

Articles 1

Article

55

Making LLMs lighter with AutoGPTQ and transformers

Collections 1

models 3,863

TheBloke/CapybaraHermes-2.5-Mistral-7B-GPTQ

1B • Updated Jan 31, 2024 • 603 • 60

TheBloke/CapybaraHermes-2.5-Mistral-7B-AWQ

1B • Updated Jan 31, 2024 • 219 • 22

TheBloke/CapybaraHermes-2.5-Mistral-7B-GGUF

7B • Updated Jan 31, 2024 • 7.39k • 118

TheBloke/KafkaLM-70B-German-V0.1-GPTQ

Text Generation • 9B • Updated Jan 31, 2024 • 54 • 4

TheBloke/KafkaLM-70B-German-V0.1-AWQ

Text Generation • 10B • Updated Jan 31, 2024 • 63 • 3

TheBloke/KafkaLM-70B-German-V0.1-GGUF

Text Generation • 69B • Updated Jan 31, 2024 • 2.41k • 40

TheBloke/CodeLlama-70B-Python-GPTQ

Text Generation • 9B • Updated Jan 31, 2024 • 49 • 20

TheBloke/CodeLlama-70B-Python-AWQ

Text Generation • 10B • Updated Jan 31, 2024 • 54 • 5

TheBloke/CodeLlama-70B-Python-GGUF

Text Generation • 69B • Updated Jan 31, 2024 • 1.64k • 43

TheBloke/CodeLlama-70B-Instruct-GPTQ

Text Generation • 9B • Updated Jan 31, 2024 • 74 • 13

View 3,863 models

datasets 0

None public yet