base on Inference code for Persimmon-8B Persimmon-8B User Guide ========== This repo contains inference code for [Persimmon-8B](https://www.adept.ai/blog/persimmon-8b), the new LLM from Adept. Downloading the Checkpoint -------- The model checkpoints are stored on our public OCI bucket and can be downloaded using `wget`. The base model is not fine-tuned and is released under an Apache 2.0 license. The chat model is fine-tuned and is released under a CC-BY-NC 4.0 license. Base: https://axtkn4xl5cip.objectstorage.us-phoenix-1.oci.customer-oci.com/n/axtkn4xl5cip/b/adept-public-data/o/8b_base_model_release.tar md5sum: cd0320cba9efad9ccd18e9ec4d16ae1b Chat: https://axtkn4xl5cip.objectstorage.us-phoenix-1.oci.customer-oci.com/n/axtkn4xl5cip/b/adept-public-data/o/8b_chat_model_release.tar md5sum: 663aeace07269c44e90f4e8bcd07f32a Untar the model into its own directory via `tar -xvf 8b_base_model_release.tar` or `tar -xvf 8b_chat_model_release.tar` The scripts are set up to expect the model folder to be placed within the code directory, but you can place it elsewhere and modify the scripts accordingly. Building Docker ----------- Build the docker that will include all the necessary dependencies (and then some!) using the included Dockerfile: ``` docker build -f docker/Dockerfile -t 'adeptdocker' . ``` Running Docker ---------- Ensure that the variable `MODEL_DIR` in `run_text_generation_server.sh` is set to the location of the model directory. By default it is set to `MODEL_DIR=8b_chat_model_release`, which is the default name for the chat model. (For the base model, change this line to `MODEL_DIR=8b_base_model_release`.) Running `sh docker_launch.sh` will start a model server that you can query via: ``` curl '<address of server>/api' -X 'PUT' -H 'Content-Type: application/json; charset=UTF-8' -d '{"prompts": ["human: Hello, how are you?\n\nadept:"], "tokens_to_generate": 128, "top_p": 0.9, "random_seed": 1234, "logprobs": false}' ``` Notes ----- * The chat model is fine-tuned to expect inputs of the form: `human: {prompt}\n\nadept:`[^1]. To ensure best performance from this model, please use this format! You can see an example of this in the curl command above. To automatically wrap single-turn input prompts with this structure, you can modify the definition of `megatron/text_generation/api.py::generate_and_post_process` so that the default value for the argument `process_prompts_for_chat` is set to `True`. * We are releasing the model with tensor parallelism of 1. In this configuration, the model requires an 80GB GPU to run naively. It should be possible to fit the model on a 40GB card by removing the unused embeddings and reducing the maximum sequence length (at the top of `run_text_generation_server.py`). Quantization to 8-bit or lower would make also it fit with plenty of room to spare. * We included the `.vocab` file so you can browse the vocabulary in plain text - this file is otherwise unused. Citation -------- If you use this model in your work, please use the following BibTeX citation: ```bibtex @misc{persimmon-8b, author = {Elsen, Erich and Odena, Augustus and Nye, Maxwell and Ta\c{s}\i{}rlar, Sa\u{g}nak and Dao, Tri and Hawthorne, Curtis and Moparthi, Deepak and Somani, Arushi}, title = {Releasing {Persimmon-8B}}, url = {https://www.adept.ai/blog/persimmon-8b}, year = {2023} } ``` [^1]: Subsequent inputs should have the form `human: {prompt}\n\nadept: {output}\n\nhuman: {follow_up}\n\nadept:` ", Assign "at most 3 tags" to the expected json: {"id":"666","tags":[]} "only from the tags list I provide: [{"id":77,"name":"3d"},{"id":89,"name":"agent"},{"id":17,"name":"ai"},{"id":54,"name":"algorithm"},{"id":24,"name":"api"},{"id":44,"name":"authentication"},{"id":3,"name":"aws"},{"id":27,"name":"backend"},{"id":60,"name":"benchmark"},{"id":72,"name":"best-practices"},{"id":39,"name":"bitcoin"},{"id":37,"name":"blockchain"},{"id":1,"name":"blog"},{"id":45,"name":"bundler"},{"id":58,"name":"cache"},{"id":21,"name":"chat"},{"id":49,"name":"cicd"},{"id":4,"name":"cli"},{"id":64,"name":"cloud-native"},{"id":48,"name":"cms"},{"id":61,"name":"compiler"},{"id":68,"name":"containerization"},{"id":92,"name":"crm"},{"id":34,"name":"data"},{"id":47,"name":"database"},{"id":8,"name":"declarative-gui "},{"id":9,"name":"deploy-tool"},{"id":53,"name":"desktop-app"},{"id":6,"name":"dev-exp-lib"},{"id":59,"name":"dev-tool"},{"id":13,"name":"ecommerce"},{"id":26,"name":"editor"},{"id":66,"name":"emulator"},{"id":62,"name":"filesystem"},{"id":80,"name":"finance"},{"id":15,"name":"firmware"},{"id":73,"name":"for-fun"},{"id":2,"name":"framework"},{"id":11,"name":"frontend"},{"id":22,"name":"game"},{"id":81,"name":"game-engine "},{"id":23,"name":"graphql"},{"id":84,"name":"gui"},{"id":91,"name":"http"},{"id":5,"name":"http-client"},{"id":51,"name":"iac"},{"id":30,"name":"ide"},{"id":78,"name":"iot"},{"id":40,"name":"json"},{"id":83,"name":"julian"},{"id":38,"name":"k8s"},{"id":31,"name":"language"},{"id":10,"name":"learning-resource"},{"id":33,"name":"lib"},{"id":41,"name":"linter"},{"id":28,"name":"lms"},{"id":16,"name":"logging"},{"id":76,"name":"low-code"},{"id":90,"name":"message-queue"},{"id":42,"name":"mobile-app"},{"id":18,"name":"monitoring"},{"id":36,"name":"networking"},{"id":7,"name":"node-version"},{"id":55,"name":"nosql"},{"id":57,"name":"observability"},{"id":46,"name":"orm"},{"id":52,"name":"os"},{"id":14,"name":"parser"},{"id":74,"name":"react"},{"id":82,"name":"real-time"},{"id":56,"name":"robot"},{"id":65,"name":"runtime"},{"id":32,"name":"sdk"},{"id":71,"name":"search"},{"id":63,"name":"secrets"},{"id":25,"name":"security"},{"id":85,"name":"server"},{"id":86,"name":"serverless"},{"id":70,"name":"storage"},{"id":75,"name":"system-design"},{"id":79,"name":"terminal"},{"id":29,"name":"testing"},{"id":12,"name":"ui"},{"id":50,"name":"ux"},{"id":88,"name":"video"},{"id":20,"name":"web-app"},{"id":35,"name":"web-server"},{"id":43,"name":"webassembly"},{"id":69,"name":"workflow"},{"id":87,"name":"yaml"}]" returns me the "expected json"