meta-llama/Llama-2-70b-chat-hf download history
meta-llama/Llama-2-70b-chat-hf is a 69.0B-parameter text generation model by meta-llama. In the last 30 days it was downloaded 5,238 times (1,251 in the last 7 days), and 4,934,810 times in total.
It ranks #11,371 on the Hub by monthly downloads and #2,920 among text generation models.
It has 2,212 likes, 1 of them in the last week.
30 models build on Llama-2-70b-chat-hf: 14 quantized, 3 fine-tuned, 13 adapters and 0 merges. Together with the original they were downloaded 17,061 times in the last 30 days. See the Llama-2-70b-chat-hf galaxy.
Most downloaded derivatives
- TheBloke/Llama-2-70B-Chat-GGUF (quantized), 9.9K downloads in 30 days
- TheBloke/Llama-2-70B-Chat-GPTQ (quantized), 985 downloads in 30 days
- TheBloke/Llama-2-70B-Chat-AWQ (quantized), 300 downloads in 30 days
- amd/Llama-2-70b-chat-hf_FP8_MLPerf_V2 (quantized), 165 downloads in 30 days
- amd/Llama-2-70b-chat-hf-WMXFP4FP8-AMXFP4FP8-AMP-KVFP8 (quantized), 103 downloads in 30 days
- TheBloke/Llama-2-70B-Chat-GGML (finetune), 93 downloads in 30 days
- strangervb/Llama-2-70B-Chat-GPTQ-2 (quantized), 29 downloads in 30 days
- jamesdborin/llama2-70b-chat-4bit-AWQ (quantized), 25 downloads in 30 days
- AIgroup-CVM-utokyohospital/Llama-2-70b-chat-4bit-japanese (adapter), 19 downloads in 30 days
- MaziyarPanahi/WizardLM-70B-V1.0-GPTQ (finetune), 18 downloads in 30 days
- softmax/Llama-2-70b-chat-hf-marlin (quantized), 18 downloads in 30 days
- amd/Llama-2-70b-chat-hf-WMXFP4-AMXFP4-KVFP8-Scale-UINT8-MLPerf-GPTQ (quantized), 16 downloads in 30 days