提交

353 次代码提交

作者 SHA1 备注 提交日期
James Crook 43994a365f Update README.md with benchmark for 5700G (#87) 2023-10-09 15:20:17 +05:30
Mayank Chhabra ab4daab908 Add CUDA support for Nvidia GPUs (#72) 2023-08-27 19:44:38 +07:00
Mayank Chhabra e15e511358 Updated default model message in run-mac.sh script to include a list of supported models. 2023-08-27 18:39:14 +07:00
Mayank Chhabra 99444f57fa Fix run commands in README.md 2023-08-27 18:37:46 +07:00
Mayank Chhabra 4b66ea3f20 Add support for Code Llama models (#71) 2023-08-27 18:31:18 +07:00
Mayank Chhabra 8152c85bfa Add Code Llama to immediate roadmap README.md 2023-08-26 19:13:29 +07:00
Mayank Chhabra 1dbb54937c Update 70B model with Nous Hermes Llama 2 Chat 70B 2023-08-25 10:49:15 +07:00
Mayank Chhabra a1fabbe369 Re-add GCP c2-standard-16 (70B) benchmark 2023-08-23 19:14:36 +07:00
Rafael Gallardo 90ddc93f90 Add benchmarks for more GCP c2 instances (#54) 2023-08-23 19:11:36 +07:00
Mayank Chhabra 76b04db75e Add memlock to 7b docker-compose.yml 2023-08-22 04:44:02 +07:00
Mayank Chhabra 87dfbe265c Update README.md 2023-08-22 03:45:56 +07:00
Mayank Chhabra 7687c52094 Update README.md 2023-08-22 03:29:00 +07:00
Mayank Chhabra b51037fc22 Update formatting in README.md 2023-08-22 03:15:35 +07:00
Mayank Chhabra ee8c4a559d Fix link in README.md 2023-08-22 03:13:55 +07:00
Mayank Chhabra 7f9c0bb1c0 Fix link in README.md 2023-08-22 03:10:51 +07:00
Mayank Chhabra 877847fcb3 Update README.md with banner 2023-08-22 03:07:45 +07:00
Mayank Chhabra 5453f63d34 Bugfix: llama-cpp-python check on macOS 2023-08-22 02:18:04 +07:00
Mayank Chhabra 3a4d09b94f Update README.md with Table of Contents 2023-08-21 21:48:11 +07:00
Mayank Chhabra 37f046a70d Add Metal (GPU) support for M1/M2 Macs (#45) 2023-08-21 21:39:32 +07:00
Mayank Chhabra 29199836c4 Expose OpenAI-compatible API server 2023-08-21 18:49:22 +07:00
Mayank Chhabra 5ef7c9ab01 Update README.md 2023-08-21 18:47:45 +07:00
Mayank Chhabra 632e720a70 Update README.md 2023-08-21 18:28:55 +07:00
Mayank Chhabra 52affdc80b Update roadmap in README.md 2023-08-21 18:28:14 +07:00
Mayank Chhabra aaef05b05c Retry curl with TLS 1.2
Co-authored-by: Alex Oliveira <alexoliveira7x@gmail.com>
2023-08-21 18:23:03 +07:00
Mayank Chhabra e06587386d Install curl only if we need to download the model 2023-08-21 18:15:20 +07:00
Maik 9c0e62e10e Annotate and logically arrange run.sh (#37) 2023-08-21 18:11:06 +07:00
Mayank Chhabra 07a9fe0f3a Increase UI container timeouts considering model download 2023-08-21 18:08:36 +07:00
Mayank Chhabra 8c23274376 Update README.md 2023-08-21 17:50:14 +07:00
Mayank Chhabra 7324a62fe5 Commit models dir 2023-08-21 17:46:13 +07:00
Edgar Pino 4dc2369fcf Move models out of the Docker image to a volume (#19) 2023-08-21 17:43:06 +07:00
Jasper Blues aa8b266466 Add 70B GCP e2-standard-16 benchmark to README (#36) 2023-08-21 17:33:49 +07:00
Miroslav Genov cf8f22455d Add benchmark for 70B model on M2 Max 96GB in README (#30) 2023-08-21 17:31:28 +07:00
Ikko Eltociear Ashimine 297e81d0df Update "Save & Submit" japanese translation (#31) 2023-08-21 17:29:56 +07:00
Mayank Chhabra 3553e20a3d Add Kubernetes deployment instructions to README.md 2023-08-18 23:56:43 +07:00
Dan Garfield ca6ec9b370 Add Kubernetes support (#18) 2023-08-18 23:48:24 +07:00
Mayank Chhabra bd50076aae Update README.md with careers CTA 2023-08-18 22:51:46 +07:00
Mayank Chhabra 31005ca992 Update roadmap with WIP in README.md 2023-08-18 22:36:34 +07:00
Mayank Chhabra 9d086c2e28 Lock 13B and 70B models in memory for faster interference 2023-08-18 03:11:42 +07:00
Mayank Chhabra 339cf66be6 Add .gitattributes to enforce consistent line endings 2023-08-18 00:41:04 +07:00
Mayank Chhabra 2a24cb9e60 Set 70B's GQA to 8 2023-08-18 00:18:19 +07:00
Mayank Chhabra bc1300fba5 Update docker service names for different model APIs 2023-08-17 23:28:55 +07:00
Mayank Chhabra c9cfd24234 Update README.md 2023-08-17 05:56:59 +07:00
Mayank Chhabra 131ef302f1 Update README.md with benchmarks and contribution guide 2023-08-17 05:44:13 +07:00
Mayank Chhabra bb8e5fccaa Add restart on-failure policy 2023-08-17 04:17:47 +07:00
Mayank Chhabra 70eb9e0176 Build 7B model api instead of pulling 2023-08-17 04:14:13 +07:00
Luke Childs c76225a6fc Fix images 2023-08-16 23:58:24 +07:00
Mayank Chhabra 007119b067 Update video in README.md 2023-08-16 21:49:02 +07:00
Mayank Chhabra f8211b4305 Update app store badge in README.md 2023-08-16 21:46:53 +07:00
Mayank Chhabra b7a58fa6b4 Update demo video in README.md 2023-08-16 21:17:03 +07:00
Luke Childs e145cf0249 Build images on tag
Build Docker images on master push / build (api) (push) Has been cancelled
Build Docker images on master push / build (ui) (push) Has been cancelled
1.0.0 1.0.1
2023-08-16 18:39:44 +07:00