arnavsinghvi11
arnavsinghvi11
Hi there, I had a question regarding working with the API Server from the [instructions](https://vllm.readthedocs.io/en/latest/getting_started/quickstart.html) here. I am running this after running the docker command # Pull the Docker image...
-updated DSPy init with vLLM support -added vLLM to hf_client -added docs for local model testing with HFModel, TGI, vLLM, and MLC -added model initialization validation for HFClientTGI within latest...
-support for finetuning OpenAI models with latest API -modified BootstrapFinetune to support OpenAI fine-tuning -modified BootstrapFinetune to support HFModel fine-tuning with HFClientTGI checkpoint integrations as well -added model initialization validation...
-adapters for general LMs (DavinciAdapter), chat LMs (TurboAdapter) and Llama models (LlamaAdapter)
-logging of total_tokens usage from OpenAI requests -thread-safe with Python logging library
merged changes with dspy still failing the # check correctness threaded test - where ref and cached are not equal
-added deepspeed within seq2seq training
-documentation for DSPy Assertions -example notebooks for the QuizGen and TweetGen tasks
integrated Databricks connectors for configuring LMs and RM in DSPy. LMs - adapted from OpenAI Client SDK in [Databricks Model Serving endpoints](https://docs.databricks.com/en/machine-learning/model-serving/score-model-serving-endpoints.html#language-OpenAI%C2%A0client) Supports chat, completions, and embeddings model formats. RM...
-replaces docs/ folder with hosted DSPy-docs website -includes documentation on making contributions to docs