Ben Li's picture

13 25

Ben Li

bash99

·

bash99

AI & ML interests

AIGC, stable diffusion, chatgpt

Organizations

None yet

bash99's activity

New activity in Qwen/Qwen2-VL-72B-Instruct-GPTQ-Int4 8 days ago

Any one can use VLLM or any other engine support dynamic batch to run this with more than 1 GPU?

#1 opened 8 days ago by

New activity in Alibaba-NLP/gte-multilingual-base about 1 month ago

How do I got token_weights from onnx inference?

#9 opened about 1 month ago by

New activity in Alibaba-NLP/gte-multilingual-reranker-base about 1 month ago

反问句的重排似乎效果不佳

#5 opened about 1 month ago by

New activity in Alibaba-NLP/gte-multilingual-base about 1 month ago

某些特殊情况匹配排序会有错）

#5 opened about 1 month ago by

New activity in OpenBuddy/openbuddy-llama2-13b-v8.1-fp16 about 1 year ago

最好能给出Instruction模板和示例，另外请问底层是llama2-base还是llama2-chat？

#3 opened about 1 year ago by

New activity in jondurbin/airoboros-13b-gpt4-1.4 about 1 year ago

4 bit GPTQ

#1 opened over 1 year ago by

New activity in IDEA-CCNL/Ziya-LLaMA-13B-v1 about 1 year ago

能给出转换后的3个pytorch bin文件的sha256sum吗？

#30 opened about 1 year ago by

New activity in THUDM/chatglm2-6b-int4 over 1 year ago

如果这个是用Bitsandsbyte的NF4量化的，能否直接在这个基础上用qlora继续训练？

#1 opened over 1 year ago by

New activity in coyude/Nous-Hermes-13b-Chinese-plus-GPTQ over 1 year ago

请问这个带Plus的版本和不带的有什么区别？

#1 opened over 1 year ago by

New activity in TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ over 1 year ago

Gibberish on 'latest', with recent qwopqwop GPTQ/triton and ooba?

#2 opened over 1 year ago by

New activity in thatname/Ziya-LLaMA-13B-v1-ggml over 1 year ago

convert ziya to ggml shell

#1 opened over 1 year ago by

New activity in anon8231489123/vicuna-13b-GPTQ-4bit-128g over 1 year ago

Vram usage

#3 opened over 1 year ago by