Ecosyste.ms: Timeline

Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.

shamanez

shamanez opened an issue on KhoomeiK/LlamaGym
Set up the mult GPU deepspeed or FSDP setup
This is an amazing work. Does this work with FSDP or Deepspeed?
shamanez starred allenai/open-instruct
shamanez pushed 1 commit to main shamanez/Minikube-tutorial

View on GitHub

shamanez created a repository: shamanez/Minikube-tutorial

https://github.com/shamanez/Minikube-tutorial - Just wanted to explore minikube to learn k8

shamanez created a branch on shamanez/Minikube-tutorial

main - Just wanted to explore minikube to learn k8

shamanez forked ShengranHu/ADAS

shamanez/ADAS

shamanez starred nirbar1985/ai-travel-agent
shamanez closed an issue on arcee-ai/DAM
Request to Integrate HuggingFace Accelerate or DeepSpeed to Address CUDA Memory Issues
Hi, Thank you for sharing this amazing work! I really appreciate the effort you have put into this project. I would like to request consideration for integrating HuggingFace Accelerate or [DeepSp...
shamanez starred awslabs/multi-agent-orchestrator
shamanez forked AIDC-AI/Marco-o1

shamanez/Marco-o1

shamanez created a comment on an issue on arcee-ai/DAM
Actually I tried to set it up. For some reason deepspeed coudn't work with our settings since the model had around 23B parameters.

View on GitHub

shamanez forked quotient-ai/judges

shamanez/judges

shamanez starred microsoft/autogen
shamanez pushed 7 commits to main shamanez/autogen-upstream
  • AgentChat pause, resume, and reset (#4088) * AgentChat pause and resume a task Resolves #3859 * Add * Update usage... 2e3155b
  • Initial web surfer implementation in extension (#4071) * Initial web surfer implementation in extension * Moved mod... 9e38892
  • Add task type that are messages to enable multi-modal tasks. (#4091) * Add task type that are messages to enable mul... 5fa38b0
  • Simplify publish events in agent (#4093) * simplify publishing imessage contracts use new api complete adoptio... 621b17e
  • Fix worker sample in core (#4104) 111e691
  • SocietyOfMind agent for nested teams (#4110) * Initial implementation of SOM agent * add tests * edit prompt * Up... 3f28aa8
  • Add Console function to stream result to pretty print console output (#4115) f40b0c2

View on GitHub

shamanez created a review on a pull request on arcee-ai/DALM
LGTM

View on GitHub

shamanez forked microsoft/autogen

shamanez/autogen-upstream

shamanez starred langflow-ai/langflow
shamanez starred facebookresearch/searchformer
shamanez pushed 1 commit to main arcee-ai/lm-evaluation-harness
  • non batch greedy decoing. b459177

View on GitHub

shamanez starred arcee-ai/DAM
shamanez starred arcee-ai/DAM
shamanez pushed 3 commits to main arcee-ai/optillm-upstream
  • simplified api calling and no cache da390f4
  • added the async df87d09
  • Merge pull request #2 from arcee-ai/remove_cache Added some optimization techniques to he API call 71188f5

View on GitHub

shamanez closed a pull request on arcee-ai/optillm-upstream
Added some optimization techniques to he API call
- Removed Cache - Addy Async optimization
shamanez opened a pull request on arcee-ai/optillm-upstream
Added some optimization techniques to he API call
- Removed Cache - Addy Async optimization
shamanez closed a pull request on codelion/optillm
Some modification to clear the code
- removed cache -added async
shamanez opened a pull request on codelion/optillm
Some modification to clear the code
- removed cache -added async
shamanez pushed 1 commit to remove_cache arcee-ai/optillm-upstream

View on GitHub

shamanez created a branch on arcee-ai/optillm-upstream

remove_cache - Optimizing inference proxy for LLMs

shamanez pushed 6 commits to main arcee-ai/optillm-upstream
  • readme update 5d10530
  • added gptqa eval script b7ffbbc
  • added parrallel evals 8ad5b40
  • added the gptqa diamand dataset 236f0e4
  • added utils.py df20719
  • Merge pull request #1 from arcee-ai/evals-atals-arcee Add both serial and parrallel optillm method evaluations with ... c1431b3

View on GitHub

shamanez closed a pull request on arcee-ai/optillm-upstream
Add both serial and parrallel optillm method evaluations with arcee endpoint.
## Evaluate optillm with Arcee-Atlas To evaluate optillm with Arcee-Atlas, we provide a script to generate a dataset and another to evaluate the results. ## API kets Please set your API kets i...
Load more