Int4 Issue 45 Openmossmoss Github
INT4 Quantization · Issue #461 · intel/intel-extension-for-pytorch · GitHub
Int4 Support · Issue #571 · NVIDIA/FasterTransformer · GitHub
int4量化版本运行报错 · Issue #45 · OpenMOSS/MOSS · GitHub
使用moss-moon-003-sft-plugin-int4后报错 · Issue #90 · OpenMOSS/MOSS · GitHub
INT8 and INT4 Quantization ValueError · Issue #35 · moojink/openvla-oft ...
INT4模型 · Issue #83 · ssbuild/chatglm_finetuning · GitHub
[Feature request] Add support for Int4 data-type · Issue #5776 · onnx ...
ORT would be crashed while loading the specific INT4 model · Issue ...
INT4 and other low-precision conversion support status · Issue #64193 ...
weight only int4 is slower than cutlass int4 · Issue #362 · ModelTC ...
Advertisement Space (300x250)
请问2.5支持int4的量化推理吗？ · Issue #353 · InternLM/InternLM-XComposer · GitHub
Questions about int4 quantization · Issue #60125 · tensorflow ...
Feature request: INT4 format support · Issue #74627 · pytorch/pytorch ...
如何在ChatGLM-6B-INT4模型上使用微调模型 · Issue #167 · mymusise/ChatGLM-Tuning · GitHub
int4量化模型存在显存占用逐步增加的情况。且代码无法消除。 · Issue #538 · QwenLM/Qwen · GitHub
💡 [REQUEST] - Int4 quantized model for Qwen-VL-Chat v1.1 · Issue #113 ...
fnlp/moss-moon-003-sft-int4 量化版本 报错 · Issue #65 · OpenMOSS/MOSS · GitHub
[Bug] INT4模型输出乱码 · Issue #349 · InternLM/lmdeploy · GitHub
[Question] kimi k2.5 sft int4训练报错 · Issue #1783 · THUDM/slime · GitHub
KV Cache INT8 and INT4 quantization precision reduction · Issue #772 ...
Advertisement Space (336x280)
[QST]Bugs when using int4 gemm in python · Issue #756 · NVIDIA/cutlass ...
![[BUG/Help] · Issue #562 · zai-org/ChatGLM-6B · GitHub](https://user-images.githubusercontent.com/78424351/231521150-45967d79-75bf-4f99-86ae-f9e1449ead28.png)
[BUG/Help] · Issue #562 · zai-org/ChatGLM-6B · GitHub
微调14b-int4模型，loss始终不下降，甚至还有升高 · Issue #565 · QwenLM/Qwen · GitHub
v100 support int4 （gptq or awq）, Whether it really work? · Issue #3141 ...
hf上DPO的Int4量化版没看到 · Issue #87 · OpenBMB/MiniCPM · GitHub
Using INT4 Quantization to Save VRAM with ollama · Issue #3114 · ollama ...
请求int4量化模型 · Issue #18 · QwenLM/Qwen · GitHub
数据怎么能看到原文？多谢多谢！ · Issue #208 · OpenMOSS/MOSS · GitHub
chat-rag-int4 · Issue #3 · OrionStarAI/Orion · GitHub
performance loss for int4 compare with AWQ? · Issue #10 · meta-pytorch ...
Advertisement Space (336x280)
千问14b-int4模型加载失败 · Issue #2993 · chatchat-space/Langchain-Chatchat · GitHub
Question about INT4 weight only GEMM · Issue #12 · tlc-pack/cutlass_fpA ...
💡 [REQUEST] - · Issue #775 · QwenLM/Qwen · GitHub
int4量化模型，减少显存占用提高速度 · Issue #294 · Tencent-Hunyuan/Hunyuan3D-2 · GitHub
qwen-7b-int4用vllm推理，为什么结果是乱码? · Issue #1315 · QwenLM/Qwen · GitHub
大佬们，目前int4版本支持微调吗？ · Issue #102 · ssbuild/chatglm_finetuning · GitHub