- 18 7月, 2023 2 次提交
-
-
* Add files via upload * Update README.md * fix: make get_vs_list return folders only * fix: bugs when create new knowledgebase --------- Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
liunux4odoo authored -
imClumsyPanda authored
-
- 17 7月, 2023 5 次提交
-
-
imClumsyPanda authored
-
imClumsyPanda authored
-
imClumsyPanda authored
-
imClumsyPanda authored
-
Fix LocalDocQA object has no attribute llm when adding docs
glide-the authored
-
- 16 7月, 2023 5 次提交
-
-
Signed-off-by: Benjamin Huo <benjamin@kubesphere.io>
Benjamin Huo authored -
glide-the authored
-
glide-the authored
-
glide-the authored
-
glide-the authored
-
- 15 7月, 2023 3 次提交
-
-
liunux4odoo authored
-
taokuizu authored
-
taokuizu authored
-
- 14 7月, 2023 2 次提交
-
-
imClumsyPanda authored
-
imClumsyPanda authored
-
- 12 7月, 2023 1 次提交
-
-
修改模型切换的bug
glide-the authored
-
- 11 7月, 2023 14 次提交
-
-
Zhi-guo Huang authored
-
imClumsyPanda authored
-
imClumsyPanda authored
-
* 修复 bing_search.py的typo;更新model_config.py中Bing Subscription Key申请方式及注意事项 * 更新FAQ,增加了[Errno 110] Connection timed out的原因与解决方案 * 修改loader.py中load_in_8bit失败的原因和详细解决方案 * update loader.py * stream_chat_bing * 修改stream_chat的接口,在请求体中选择knowledge_base_id;增加stream_chat_bing接口 * 优化cli_demo.py的逻辑:支持 输入提示;多输入;重新输入 * update cli_demo.py * 按照review建议进行修改 * 修改默认的多卡部署方案,基本保证针对新模型也不会失败 --------- Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
Zhi-guo Huang authored -
imClumsyPanda authored
-
imClumsyPanda authored
-
imClumsyPanda authored
-
1. 接口增加参数校验,防止攻击 2. 优化接口参数和逻辑 3. 规范接口错误响应 4. 增加接口描述 Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
NieLamu authored -
1.增加对llama-cpp模型的支持;2.增加对bloom/chatyuan/baichuan模型的支持;3. 修复多GPU部署的bug;4. 修复了moss_llm.py的bug;5. 增加对openai支持(没有api,未测试);6. 支持在多卡情况自定义设备GPU (#664) * 修复 bing_search.py的typo;更新model_config.py中Bing Subscription Key申请方式及注意事项 * 更新FAQ,增加了[Errno 110] Connection timed out的原因与解决方案 * 修改loader.py中load_in_8bit失败的原因和详细解决方案 * update loader.py * stream_chat_bing * 修改stream_chat的接口,在请求体中选择knowledge_base_id;增加stream_chat_bing接口 * 优化cli_demo.py的逻辑:支持 输入提示;多输入;重新输入 * update cli_demo.py * add bloom-3b,bloom-7b1,ggml-vicuna-13b-1.1 * 1.增加对llama-cpp模型的支持;2.增加对bloom模型的支持;3. 修复多GPU部署的bug;4. 增加对openai支持(没有api,未测试);5.增加了llama-cpp模型部署的说明 * llama模型兼容性说明 * modified: ../configs/model_config.py modified: ../docs/INSTALL.md 在install.md里增加对llama-cpp模型调用的说明 * 修改llama_llm.py以适应llama-cpp模型 * 完成llama-cpp模型的支持; * make fastchat and openapi compatiable * 1. 修复/增加对chatyuan,bloom,baichuan-7等模型的支持;2. 修复了moss_llm.py的bug; * set default model be chatglm-6b * 在多卡情况下也支持自定义GPU设备 --------- Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
Zhi-guo Huang authored -
* Update README.md * fix:The knowledge base name cannot be empty. * Update webui.py --------- Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
kztao authored -
* fix:The knowledge base name cannot be empty. * Update webui.py --------- Co-authored-by: imClumsyPanda <littlepanda0716@gmail.com>
kztao authored -
imClumsyPanda authored
-
imClumsyPanda authored
-
ysyx2008 authored
-
- 07 7月, 2023 2 次提交
-
-
imClumsyPanda authored
-
imClumsyPanda authored
-
- 05 7月, 2023 2 次提交
-
-
imClumsyPanda authored
-
imClumsyPanda authored
-
- 04 7月, 2023 2 次提交
- 02 7月, 2023 2 次提交
-
-
imClumsyPanda authored
-
imClumsyPanda authored
-