From 552ebe6c37f1d1fb8446c2976a60ff11e4d8e54e Mon Sep 17 00:00:00 2001 From: Paul Date: Tue, 23 Jul 2024 16:24:38 +0000 Subject: [PATCH] Add llama 3.1 405b model --- schemas/fofr_ultrapixel.json | 550 +++++++++++ .../meta_meta-llama-3.1-405b-instruct.json | 926 ++++++++++++++++++ supported_models.json | 2 + 3 files changed, 1478 insertions(+) create mode 100644 schemas/fofr_ultrapixel.json create mode 100644 schemas/meta_meta-llama-3.1-405b-instruct.json diff --git a/schemas/fofr_ultrapixel.json b/schemas/fofr_ultrapixel.json new file mode 100644 index 0000000..ba4e5a1 --- /dev/null +++ b/schemas/fofr_ultrapixel.json @@ -0,0 +1,550 @@ +{ + "url": "https://replicate.com/fofr/ultrapixel", + "owner": "fofr", + "name": "ultrapixel", + "description": "Ultra high resolution images (up to 4096x4096) based on Stable Cascade", + "visibility": "public", + "github_url": "https://github.com/fofr/cog-ultrapixel", + "paper_url": null, + "license_url": "https://huggingface.co/stabilityai/stable-cascade/blob/main/LICENSE", + "run_count": 0, + "cover_image_url": "https://tjzk.replicate.delivery/models_models_cover_image/692efefd-f64d-44ec-9e74-8c7f87fdd7c3/UltraPixel_00001_.webp", + "default_example": { + "id": "xpfkt7a8y5rj60cgv64tbed3ac", + "model": "fofr/ultrapixel", + "version": "48934fc160c585169143f55dde57966cf466c08541bc937746ef91408a9dac7b", + "status": "succeeded", + "input": { + "width": 2048, + "height": 2048, + "prompt": "Spiderpunk woman, Cinematic 8k HDR, Anime Eyes, artwork by Ilya Kuvshinov", + "stage_b_cfg": 1.1, + "stage_c_cfg": 4, + "output_format": "webp", + "stage_b_steps": 10, + "stage_c_steps": 20, + "output_quality": 90, + "controlnet_weight": 1 + }, + "output": [ + "https://replicate.delivery/yhqm/iLYSujK5mhbBFFto73F2TkJ2rhxxQBCdxIpIWfoVrOFfk8KTA/UltraPixel_00001_.webp" + ], + "logs": "Random seed set to: 2980426308\nRunning workflow\ngot prompt\nExecuting node 16, title: UltraPixel Load, class type: UltraPixelLoad\nExecuting node 14, title: UltraPixel Process, class type: UltraPixelProcess\nLoading checkpoint shards: 0%| | 0/2 [00:00<|start_header_id|>system<|end_header_id|>\n\nYou are a helpful assistant.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nTina has one brother and one sister. How many sisters do Tina's siblings have?<|eot_id|><|start_header_id|>assistant<|end_header_id|>", + "error": null, + "metrics": { + "batch_size": 1.000229398266064, + "total_time": 2.86309, + "input_token_count": 26, + "tokens_per_second": 29.74134035953616, + "output_token_count": 84, + "predict_time_share": 2.8200430870056152, + "predict_time": 2.826425468, + "time_to_first_token": 0.112068943 + }, + "created_at": "2024-07-23T15:04:21.227000Z", + "started_at": "2024-07-23T15:04:21.263665Z", + "completed_at": "2024-07-23T15:04:24.090090Z", + "urls": { + "stream": "https://streaming-api.svc.sea.v.replicate.net/v1/streams/6zoqtc6qgpxby7xzauee36qv6bktfaxugelxfqs6ifgg6q4s77sa", + "get": "https://api.replicate.com/v1/predictions/zjq6szssxdrm20cgw0fsntgvbg", + "cancel": "https://api.replicate.com/v1/predictions/zjq6szssxdrm20cgw0fsntgvbg/cancel" + } + }, + "latest_version": { + "id": "e6cb7fc3ed90eae2c879c48deda8f49152391ad66349fe7694be24089c29f71c", + "created_at": "2024-07-23T15:24:35.230971+00:00", + "cog_version": "0.10.0-alpha17", + "openapi_schema": { + "info": { + "title": "Cog", + "version": "0.1.0" + }, + "paths": { + "/": { + "get": { + "summary": "Root", + "responses": { + "200": { + "content": { + "application/json": { + "schema": { + "title": "Response Root Get" + } + } + }, + "description": "Successful Response" + } + }, + "operationId": "root__get" + } + }, + "/ready": { + "get": { + "summary": "Ready", + "responses": { + "200": { + "content": { + "application/json": { + "schema": { + "title": "Response Ready Ready Get" + } + } + }, + "description": "Successful Response" + } + }, + "operationId": "ready_ready_get" + } + }, + "/shutdown": { + "post": { + "summary": "Start Shutdown", + "responses": { + "200": { + "content": { + "application/json": { + "schema": { + "title": "Response Start Shutdown Shutdown Post" + } + } + }, + "description": "Successful Response" + } + }, + "operationId": "start_shutdown_shutdown_post" + } + }, + "/trainings": { + "post": { + "summary": "Train", + "responses": { + "200": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/TrainingResponse" + } + } + }, + "description": "Successful Response" + }, + "422": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } + }, + "description": "Validation Error" + } + }, + "parameters": [ + { + "in": "header", + "name": "prefer", + "schema": { + "type": "string", + "title": "Prefer" + }, + "required": false + } + ], + "operationId": "train_trainings_post", + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/TrainingRequest" + } + } + } + } + } + }, + "/predictions": { + "post": { + "summary": "Predict", + "responses": { + "200": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/PredictionResponse" + } + } + }, + "description": "Successful Response" + }, + "422": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } + }, + "description": "Validation Error" + } + }, + "parameters": [ + { + "in": "header", + "name": "prefer", + "schema": { + "type": "string", + "title": "Prefer" + }, + "required": false + } + ], + "description": "Run a single prediction on the model", + "operationId": "predict_predictions_post", + "requestBody": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/PredictionRequest" + } + } + } + } + } + }, + "/health-check": { + "get": { + "summary": "Healthcheck", + "responses": { + "200": { + "content": { + "application/json": { + "schema": { + "title": "Response Healthcheck Health Check Get" + } + } + }, + "description": "Successful Response" + } + }, + "operationId": "healthcheck_health_check_get" + } + }, + "/trainings/{training_id}": { + "put": { + "summary": "Train Idempotent", + "responses": { + "200": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/PredictionResponse" + } + } + }, + "description": "Successful Response" + }, + "422": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } + }, + "description": "Validation Error" + } + }, + "parameters": [ + { + "in": "path", + "name": "training_id", + "schema": { + "type": "string", + "title": "Training ID" + }, + "required": true + }, + { + "in": "header", + "name": "prefer", + "schema": { + "type": "string", + "title": "Prefer" + }, + "required": false + } + ], + "operationId": "train_idempotent_trainings__training_id__put", + "requestBody": { + "content": { + "application/json": { + "schema": { + "allOf": [ + { + "$ref": "#/components/schemas/TrainingRequest" + } + ], + "title": "Training Request" + } + } + }, + "required": true + } + } + }, + "/predictions/{prediction_id}": { + "put": { + "summary": "Predict Idempotent", + "responses": { + "200": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/PredictionResponse" + } + } + }, + "description": "Successful Response" + }, + "422": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } + }, + "description": "Validation Error" + } + }, + "parameters": [ + { + "in": "path", + "name": "prediction_id", + "schema": { + "type": "string", + "title": "Prediction ID" + }, + "required": true + }, + { + "in": "header", + "name": "prefer", + "schema": { + "type": "string", + "title": "Prefer" + }, + "required": false + } + ], + "description": "Run a single prediction on the model (idempotent creation).", + "operationId": "predict_idempotent_predictions__prediction_id__put", + "requestBody": { + "content": { + "application/json": { + "schema": { + "allOf": [ + { + "$ref": "#/components/schemas/PredictionRequest" + } + ], + "title": "Prediction Request" + } + } + }, + "required": true + } + } + }, + "/trainings/{training_id}/cancel": { + "post": { + "summary": "Cancel Training", + "responses": { + "200": { + "content": { + "application/json": { + "schema": { + "title": "Response Cancel Training Trainings Training Id Cancel Post" + } + } + }, + "description": "Successful Response" + }, + "422": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } + }, + "description": "Validation Error" + } + }, + "parameters": [ + { + "in": "path", + "name": "training_id", + "schema": { + "type": "string", + "title": "Training ID" + }, + "required": true + } + ], + "operationId": "cancel_training_trainings__training_id__cancel_post" + } + }, + "/predictions/{prediction_id}/cancel": { + "post": { + "summary": "Cancel", + "responses": { + "200": { + "content": { + "application/json": { + "schema": { + "title": "Response Cancel Predictions Prediction Id Cancel Post" + } + } + }, + "description": "Successful Response" + }, + "422": { + "content": { + "application/json": { + "schema": { + "$ref": "#/components/schemas/HTTPValidationError" + } + } + }, + "description": "Validation Error" + } + }, + "parameters": [ + { + "in": "path", + "name": "prediction_id", + "schema": { + "type": "string", + "title": "Prediction ID" + }, + "required": true + } + ], + "description": "Cancel a running prediction", + "operationId": "cancel_predictions__prediction_id__cancel_post" + } + } + }, + "openapi": "3.0.2", + "components": { + "schemas": { + "Input": { + "type": "object", + "title": "Input", + "properties": { + "top_k": { + "type": "integer", + "title": "Top K", + "default": 50, + "x-order": 6, + "description": "The number of highest probability tokens to consider for generating the output. If > 0, only keep the top k tokens with highest probability (top-k filtering)." + }, + "top_p": { + "type": "number", + "title": "Top P", + "default": 0.9, + "x-order": 5, + "description": "A probability threshold for generating the output. If < 1.0, only keep the top tokens with cumulative probability >= top_p (nucleus filtering). Nucleus filtering is described in Holtzman et al. (http://arxiv.org/abs/1904.09751)." + }, + "prompt": { + "type": "string", + "title": "Prompt", + "default": "", + "x-order": 0, + "description": "Prompt" + }, + "max_tokens": { + "type": "integer", + "title": "Max Tokens", + "default": 512, + "x-order": 3, + "description": "The maximum number of tokens the model should generate as output." + }, + "min_tokens": { + "type": "integer", + "title": "Min Tokens", + "default": 0, + "x-order": 2, + "description": "The minimum number of tokens the model should generate as output." + }, + "temperature": { + "type": "number", + "title": "Temperature", + "default": 0.6, + "x-order": 4, + "description": "The value used to modulate the next token probabilities." + }, + "system_prompt": { + "type": "string", + "title": "System Prompt", + "default": "You are a helpful assistant.", + "x-order": 1, + "description": "System prompt to send to the model. This is prepended to the prompt and helps guide system behavior. Ignored for non-chat models." + }, + "stop_sequences": { + "type": "string", + "title": "Stop Sequences", + "x-order": 9, + "description": "A comma-separated list of sequences to stop generation at. For example, ',' will stop generation at the first instance of 'end' or ''." + }, + "presence_penalty": { + "type": "number", + "title": "Presence Penalty", + "default": 0, + "x-order": 7, + "description": "Presence penalty" + }, + "frequency_penalty": { + "type": "number", + "title": "Frequency Penalty", + "default": 0, + "x-order": 8, + "description": "Frequency penalty" + } + } + }, + "Output": { + "type": "array", + "items": { + "type": "string" + }, + "title": "Output", + "x-cog-array-type": "iterator", + "x-cog-array-display": "concatenate" + }, + "Status": { + "enum": [ + "starting", + "processing", + "succeeded", + "canceled", + "failed" + ], + "type": "string", + "title": "Status", + "description": "An enumeration." + }, + "WebhookEvent": { + "enum": [ + "start", + "output", + "logs", + "completed" + ], + "type": "string", + "title": "WebhookEvent", + "description": "An enumeration." + }, + "TrainingInput": { + "type": "object", + "title": "TrainingInput", + "required": [ + "hf_model_id" + ], + "properties": { + "hf_token": { + "type": "string", + "title": "Hf Token", + "format": "password", + "x-order": 2, + "description": "\n Hugging Face API token. \n Get your token at https://huggingface.co/settings/tokens\n ", + "x-cog-secret": true + }, + "hf_model_id": { + "type": "string", + "title": "Hf Model Id", + "x-order": 0, + "description": "\n Hugging Face model identifier \n (e.g. NousResearch/Hermes-2-Theta-Llama-3-8B).\n " + }, + "hf_model_sha": { + "type": "string", + "title": "Hf Model Sha", + "x-order": 1, + "description": "\n The version of the model.\n If unspecified, the latest version is used.\n " + }, + "allow_patterns": { + "type": "string", + "title": "Allow Patterns", + "x-order": 3, + "description": "\n Patterns constituting the allowlist. \n If provided, item paths must match at least one pattern from the allowlist. \n (e.g. \"*.safetensors\").\n " + }, + "ignore_patterns": { + "type": "string", + "title": "Ignore Patterns", + "default": "*.gguf", + "x-order": 4, + "description": "\n Patterns constituting the denylist. \n If provided, item paths must not match any patterns from the denylist. \n (e.g. \"*.gguf\").\n " + }, + "prompt_template": { + "type": "string", + "title": "Prompt Template", + "x-order": 5, + "description": "Prompt template. This is a Jinja2 template that overrides the HuggingFace tokenizer configuration. If this is set to None and nothing is configured on HuggingFace, no formatting is applied. To override HuggingFace configuration, set it to the string `{{messages[0]['content']}}`." + } + } + }, + "TrainingOutput": { + "type": "object", + "title": "TrainingOutput", + "required": [ + "weights" + ], + "properties": { + "weights": { + "type": "string", + "title": "Weights", + "format": "uri" + } + } + }, + "TrainingRequest": { + "type": "object", + "title": "TrainingRequest", + "properties": { + "id": { + "type": "string", + "title": "Id" + }, + "input": { + "$ref": "#/components/schemas/TrainingInput" + }, + "webhook": { + "type": "string", + "title": "Webhook", + "format": "uri", + "maxLength": 65536, + "minLength": 1 + }, + "created_at": { + "type": "string", + "title": "Created At", + "format": "date-time" + }, + "output_file_prefix": { + "type": "string", + "title": "Output File Prefix" + }, + "webhook_events_filter": { + "type": "array", + "items": { + "$ref": "#/components/schemas/WebhookEvent" + }, + "default": [ + "start", + "output", + "logs", + "completed" + ] + } + } + }, + "ValidationError": { + "type": "object", + "title": "ValidationError", + "required": [ + "loc", + "msg", + "type" + ], + "properties": { + "loc": { + "type": "array", + "items": { + "anyOf": [ + { + "type": "string" + }, + { + "type": "integer" + } + ] + }, + "title": "Location" + }, + "msg": { + "type": "string", + "title": "Message" + }, + "type": { + "type": "string", + "title": "Error Type" + } + } + }, + "TrainingResponse": { + "type": "object", + "title": "TrainingResponse", + "properties": { + "id": { + "type": "string", + "title": "Id" + }, + "logs": { + "type": "string", + "title": "Logs", + "default": "" + }, + "error": { + "type": "string", + "title": "Error" + }, + "input": { + "$ref": "#/components/schemas/TrainingInput" + }, + "output": { + "$ref": "#/components/schemas/TrainingOutput" + }, + "status": { + "$ref": "#/components/schemas/Status" + }, + "metrics": { + "type": "object", + "title": "Metrics" + }, + "version": { + "type": "string", + "title": "Version" + }, + "created_at": { + "type": "string", + "title": "Created At", + "format": "date-time" + }, + "started_at": { + "type": "string", + "title": "Started At", + "format": "date-time" + }, + "completed_at": { + "type": "string", + "title": "Completed At", + "format": "date-time" + } + } + }, + "PredictionRequest": { + "type": "object", + "title": "PredictionRequest", + "properties": { + "id": { + "type": "string", + "title": "Id" + }, + "input": { + "$ref": "#/components/schemas/Input" + }, + "webhook": { + "type": "string", + "title": "Webhook", + "format": "uri", + "maxLength": 65536, + "minLength": 1 + }, + "created_at": { + "type": "string", + "title": "Created At", + "format": "date-time" + }, + "output_file_prefix": { + "type": "string", + "title": "Output File Prefix" + }, + "webhook_events_filter": { + "type": "array", + "items": { + "$ref": "#/components/schemas/WebhookEvent" + }, + "default": [ + "start", + "output", + "logs", + "completed" + ] + } + } + }, + "PredictionResponse": { + "type": "object", + "title": "PredictionResponse", + "properties": { + "id": { + "type": "string", + "title": "Id" + }, + "logs": { + "type": "string", + "title": "Logs", + "default": "" + }, + "error": { + "type": "string", + "title": "Error" + }, + "input": { + "$ref": "#/components/schemas/Input" + }, + "output": { + "$ref": "#/components/schemas/Output" + }, + "status": { + "$ref": "#/components/schemas/Status" + }, + "metrics": { + "type": "object", + "title": "Metrics" + }, + "version": { + "type": "string", + "title": "Version" + }, + "created_at": { + "type": "string", + "title": "Created At", + "format": "date-time" + }, + "started_at": { + "type": "string", + "title": "Started At", + "format": "date-time" + }, + "completed_at": { + "type": "string", + "title": "Completed At", + "format": "date-time" + } + } + }, + "HTTPValidationError": { + "type": "object", + "title": "HTTPValidationError", + "properties": { + "detail": { + "type": "array", + "items": { + "$ref": "#/components/schemas/ValidationError" + }, + "title": "Detail" + } + } + } + } + } + } + } +} \ No newline at end of file diff --git a/supported_models.json b/supported_models.json index 5e5e6ca..8a55af5 100644 --- a/supported_models.json +++ b/supported_models.json @@ -20,6 +20,7 @@ "fofr/latent-consistency-model", "fofr/sd3-with-chaos", "fofr/style-transfer", + "fofr/ultrapixel", "lucataco/hunyuandit-v1.1", "lucataco/llama-3-vision-alpha", "lucataco/magnet", @@ -30,6 +31,7 @@ "lucataco/sdxl-clip-interrogator", "lucataco/xtts-v2", "luosiallen/latent-consistency-model", + "meta/meta-llama-3.1-405b-instruct", "meta/llama-2-70b-chat", "meta/llama-2-7b-chat", "meta/musicgen",