2024-08-13 14:30:11 -04:00
|
|
|
gptq_marlin, robertgshaw2/zephyr-7b-beta-channelwise-gptq, main
|
|
|
|
gptq_marlin, TheBloke/Llama-2-7B-GPTQ, main
|
|
|
|
gptq_marlin, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, main
|
|
|
|
gptq_marlin, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit--1g-actorder_True
|
|
|
|
gptq_marlin, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit-32g-actorder_True
|
|
|
|
gptq_marlin, TechxGenus/gemma-1.1-2b-it-GPTQ, main
|
2024-09-03 17:21:44 -04:00
|
|
|
gptq, robertgshaw2/zephyr-7b-beta-channelwise-gptq, main
|
|
|
|
gptq, TheBloke/Llama-2-7B-GPTQ, main
|
|
|
|
gptq, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, main
|
|
|
|
gptq, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit--1g-actorder_True
|
|
|
|
gptq, TheBloke/TinyLlama-1.1B-Chat-v1.0-GPTQ, gptq-8bit-32g-actorder_True
|
|
|
|
gptq, TechxGenus/gemma-1.1-2b-it-GPTQ, main
|
2024-08-13 14:30:11 -04:00
|
|
|
compressed-tensors, nm-testing/tinyllama-oneshot-w8w8-test-static-shape-change, main
|
|
|
|
compressed-tensors, nm-testing/tinyllama-oneshot-w8-channel-a8-tensor, main
|
|
|
|
compressed-tensors, nm-testing/tinyllama-oneshot-w8a8-dynamic-token-v2, main
|
|
|
|
compressed-tensors, nm-testing/tinyllama-oneshot-w8a8-channel-dynamic-token-v2, main
|
|
|
|
compressed-tensors, nm-testing/tinyllama-oneshot-w4a16-group128-v2, main
|
|
|
|
compressed-tensors, nm-testing/tinyllama-oneshot-w8a16-per-channel, main
|
|
|
|
compressed-tensors, nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test, main
|
|
|
|
compressed-tensors, nm-testing/Phi-3-mini-128k-instruct-FP8, main
|
2024-08-13 17:08:20 -04:00
|
|
|
compressed-tensors, neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16, main
|
2024-09-09 16:27:26 -04:00
|
|
|
compressed-tensors, nm-testing/TinyLlama-1.1B-Chat-v1.0-actorder-group, main
|
2025-01-31 02:49:37 -05:00
|
|
|
#compressed-tensors, mgoin/DeepSeek-Coder-V2-Lite-Instruct-FP8, main
|
2024-12-18 09:57:16 -05:00
|
|
|
compressed-tensors, nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-FP8-Dynamic-testing, main, 90
|
|
|
|
compressed-tensors, nm-testing/SparseLlama-3.1-8B-gsm8k-pruned.2of4-W8A8-testing, main, 90
|
2024-08-13 17:08:20 -04:00
|
|
|
awq, casperhansen/mixtral-instruct-awq, main
|
|
|
|
awq_marlin, casperhansen/mixtral-instruct-awq, main
|
2024-08-23 14:30:52 -04:00
|
|
|
fp8, neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV, main
|
|
|
|
marlin, nm-testing/zephyr-beta-7b-marlin-g128, main
|
2024-08-26 15:16:15 -04:00
|
|
|
marlin, robertgshaw2/zephyr-7b-beta-channelwise-marlin, main
|
|
|
|
qqq, HandH1998/QQQ-Llama-3-8b-g128, main
|
2024-11-19 22:31:12 +01:00
|
|
|
qqq, HandH1998/QQQ-Llama-3-8b, main
|
2025-01-19 19:40:40 +01:00
|
|
|
hqq, nm-testing/Llama-3.2-1B-Instruct-HQQ, main
|
|
|
|
None, mgleize/fairseq2-dummy-Llama-3.2-1B, main
|