24 lines
1.5 KiB
Plaintext
24 lines
1.5 KiB
Plaintext
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
|
|
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
|
|
compressed-tensors, neuralmagic/Phi-3-medium-128k-instruct-quantized.w4a16, main
|
|
compressed-tensors, nm-testing/Mixtral-8x7B-Instruct-v0.1-W4A16-quantized, main
|
|
compressed-tensors, nm-testing/Mixtral-8x7B-Instruct-v0.1-W4A16-channel-quantized, main
|
|
awq, casperhansen/mixtral-instruct-awq, main
|
|
awq_marlin, casperhansen/mixtral-instruct-awq, main
|
|
fp8, neuralmagic/Meta-Llama-3-8B-Instruct-FP8-KV, main
|
|
marlin, nm-testing/zephyr-beta-7b-marlin-g128, main
|
|
marlin, robertgshaw2/zephyr-7b-beta-channelwise-marlin, main
|
|
qqq, HandH1998/QQQ-Llama-3-8b-g128, main
|
|
qqq, HandH1998/QQQ-Llama-3-8b, main |