From f44709ed924ee400f149822977aa245682c0d2a1 Mon Sep 17 00:00:00 2001 From: Paul Date: Tue, 5 Nov 2024 14:38:45 +0000 Subject: [PATCH] Remove mixtral --- .../mistralai_mixtral-8x7b-instruct-v0.1.json | 1094 ----------------- supported_models.json | 1 - 2 files changed, 1095 deletions(-) delete mode 100644 schemas/mistralai_mixtral-8x7b-instruct-v0.1.json diff --git a/schemas/mistralai_mixtral-8x7b-instruct-v0.1.json b/schemas/mistralai_mixtral-8x7b-instruct-v0.1.json deleted file mode 100644 index 691539e..0000000 --- a/schemas/mistralai_mixtral-8x7b-instruct-v0.1.json +++ /dev/null @@ -1,1094 +0,0 @@ -{ - "url": "https://replicate.com/mistralai/mixtral-8x7b-instruct-v0.1", - "owner": "mistralai", - "name": "mixtral-8x7b-instruct-v0.1", - "description": "The Mixtral-8x7B-instruct-v0.1 Large Language Model (LLM) is a pretrained generative Sparse Mixture of Experts tuned to be a helpful assistant.", - "visibility": "public", - "github_url": "https://github.com/nateraw/replicate-examples/tree/main/mixtral-vllm", - "paper_url": null, - "license_url": "https://choosealicense.com/licenses/apache-2.0/", - "run_count": 0, - "cover_image_url": "https://tjzk.replicate.delivery/models_models_cover_image/802d34fe-29b9-4079-ad16-b4333788e539/mixtral.png", - "default_example": { - "id": "7xg537tbifojej65lk46tfzevu", - "model": "mistralai/mixtral-8x7b-instruct-v0.1", - "version": "7b3212fbaf88310cfef07a061ce94224e82efc8403c26fc67e8f6c065de51f21", - "status": "succeeded", - "input": { - "top_k": 50, - "top_p": 0.9, - "prompt": "Write a bedtime story about neural networks I can read to my toddler", - "temperature": 0.6, - "max_new_tokens": 1024, - "prompt_template": "[INST] {prompt} [/INST] ", - "presence_penalty": 0, - "frequency_penalty": 0 - }, - "output": [ - "", - "", - "", - "🌙", - " Bed", - "time", - " Story", - ":", - " The", - " Dream", - "land", - " Ne", - "ural", - " Network", - " ", - "", - "", - "", - "🌙", - "\n", - "\n", - "Once", - " upon", - " a", - " time", - ",", - " in", - " a", - " land", - " called", - " Dream", - "land", - ",", - " there", - " was", - " a", - " magical", - " network", - " of", - " stars", - " called", - " the", - " Ne", - "ural", - " Network", - ".", - " The", - " Ne", - "ural", - " Network", - " was", - " special", - " because", - " it", - " was", - " made", - " up", - " of", - " many", - " tiny", - " stars", - " called", - " neur", - "ons", - ",", - " and", - " they", - " all", - " worked", - " together", - " to", - " help", - " the", - " people", - " of", - " Dream", - "land", - " have", - " sweet", - " dreams", - ".", - "\n", - "\n", - "Each", - " night", - ",", - " when", - " the", - " people", - " of", - " Dream", - "land", - " closed", - " their", - " eyes", - " to", - " sleep", - ",", - " they", - " would", - " send", - " their", - " dreams", - " up", - " into", - " the", - " sky", - ",", - " where", - " the", - " Ne", - "ural", - " Network", - " would", - " catch", - " them", - " and", - " transform", - " them", - " into", - " beautiful", - ",", - " peaceful", - " vis", - "ions", - ".", - "\n", - "\n", - "The", - " Ne", - "ural", - " Network", - " had", - " many", - " layers", - ",", - " just", - " like", - " a", - " cake", - ".", - " The", - " first", - " layer", - " was", - " called", - " the", - " Input", - " L", - "ayer", - ",", - " where", - " all", - " the", - " dreams", - " would", - " enter", - " and", - " be", - " greeted", - " by", - " the", - " friendly", - " neur", - "ons", - ".", - " The", - " Input", - " L", - "ayer", - " would", - " then", - " pass", - " the", - " dreams", - " along", - " to", - " the", - " next", - " layer", - ",", - " called", - " the", - " H", - "idden", - " L", - "ayer", - ".", - "\n", - "\n", - "The", - " H", - "idden", - " L", - "ayer", - " was", - " a", - " very", - " busy", - " place", - ",", - " where", - " the", - " neur", - "ons", - " would", - " take", - " the", - " dreams", - " and", - " make", - " them", - " even", - " more", - " beautiful", - ".", - " They", - " would", - " add", - " colors", - ",", - " shapes", - ",", - " and", - " happy", - " thoughts", - ",", - " making", - " sure", - " the", - " dreams", - " were", - " just", - " right", - " for", - " the", - " dream", - "ers", - ".", - "\n", - "\n", - "After", - " the", - " H", - "idden", - " L", - "ayer", - ",", - " the", - " dreams", - " would", - " go", - " to", - " the", - " Output", - " L", - "ayer", - ",", - " where", - " they", - " would", - " be", - " sent", - " back", - " down", - " to", - " the", - " people", - " of", - " Dream", - "land", - ".", - " The", - " Output", - " L", - "ayer", - " made", - " sure", - " that", - " the", - " dreams", - " were", - " perfect", - ",", - " with", - " just", - " the", - " right", - " amount", - " of", - " sweet", - "ness", - " and", - " wonder", - ".", - "\n", - "\n", - "One", - " night", - ",", - " a", - " little", - " girl", - " named", - " Lily", - " had", - " trouble", - " sleeping", - ".", - " She", - " couldn", - "'", - "t", - " stop", - " thinking", - " about", - " her", - " lost", - " t", - "ed", - "dy", - " bear", - ",", - " and", - " she", - " felt", - " sad", - " and", - " lonely", - ".", - " The", - " Ne", - "ural", - " Network", - " saw", - " Lily", - "'", - "s", - " sad", - "ness", - " and", - " knew", - " just", - " what", - " to", - " do", - ".", - "\n", - "\n", - "The", - " Input", - " L", - "ayer", - " welcomed", - " Lily", - "'", - "s", - " dream", - " and", - " passed", - " it", - " along", - " to", - " the", - " H", - "idden", - " L", - "ayer", - ".", - " The", - " neur", - "ons", - " in", - " the", - " H", - "idden", - " L", - "ayer", - " added", - " warm", - ",", - " co", - "zy", - " thoughts", - " and", - " images", - " of", - " t", - "ed", - "dy", - " bears", - " to", - " Lily", - "'", - "s", - " dream", - ".", - " They", - " made", - " sure", - " it", - " was", - " just", - " right", - " for", - " her", - ".", - "\n", - "\n", - "The", - " Output", - " L", - "ayer", - " then", - " sent", - " the", - " dream", - " back", - " down", - " to", - " Lily", - ",", - " and", - " she", - " found", - " herself", - " c", - "udd", - "ling", - " her", - " t", - "ed", - "dy", - " bear", - " in", - " a", - " soft", - ",", - " warm", - " bed", - ".", - " Lily", - " smiled", - " and", - " drift", - "ed", - " off", - " to", - " sleep", - ",", - " feeling", - " happy", - " and", - " safe", - ".", - "\n", - "\n", - "From", - " that", - " night", - " on", - ",", - " Lily", - " always", - " had", - " sweet", - " dreams", - ",", - " thanks", - " to", - " the", - " magical", - " Ne", - "ural", - " Network", - " in", - " Dream", - "land", - ".", - " And", - " every", - " night", - ",", - " the", - " Ne", - "ural", - " Network", - " would", - " help", - " the", - " people", - " of", - " Dream", - "land", - " have", - " the", - " most", - " wonderful", - " dreams", - ",", - " making", - " their", - " world", - " a", - " happ", - "ier", - ",", - " more", - " peaceful", - " place", - ".", - "\n", - "\n", - "And", - " as", - " the", - " sun", - " rose", - ",", - " the", - " Ne", - "ural", - " Network", - " would", - " rest", - ",", - " waiting", - " for", - " the", - " night", - " to", - " come", - " again", - ",", - " so", - " it", - " could", - " work", - " its", - " magic", - " once", - " more", - ".", - "\n", - "\n", - "", - "", - "", - "🌟", - " The", - " End", - " ", - "", - "", - "", - "🌟", - "\n", - "\n", - "Now", - " it", - "'", - "s", - " time", - " to", - " close", - " your", - " eyes", - " and", - " let", - " the", - " Ne", - "ural", - " Network", - " in", - " your", - " brain", - " help", - " you", - " have", - " sweet", - " dreams", - " too", - ".", - " Good", - "night", - "!", - " ", - "", - "", - "", - "😴", - "" - ], - "logs": "INFO 12-22 17:35:35 async_llm_engine.py:379] Received request 0: prompt: '[INST] Write a bedtime story about neural networks I can read to my toddler [/INST] ', sampling params: SamplingParams(n=1, best_of=1, presence_penalty=0.0, frequency_penalty=0.0, repetition_penalty=1.0, temperature=0.6, top_p=0.9, top_k=50, min_p=0.0, use_beam_search=False, length_penalty=1.0, early_stopping=False, stop=[''], stop_token_ids=[], ignore_eos=False, max_tokens=1024, logprobs=None, prompt_logprobs=None, skip_special_tokens=True, spaces_between_special_tokens=True), prompt token ids: None.\nINFO 12-22 17:35:35 llm_engine.py:649] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 0.0 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.0%, CPU KV cache usage: 0.0%\nINFO 12-22 17:35:40 llm_engine.py:649] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 36.4 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.0%, CPU KV cache usage: 0.0%\nINFO 12-22 17:35:45 llm_engine.py:649] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 36.0 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.0%, CPU KV cache usage: 0.0%\nINFO 12-22 17:35:50 llm_engine.py:649] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 35.9 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.1%, CPU KV cache usage: 0.0%\nINFO 12-22 17:35:51 async_llm_engine.py:111] Finished request 0.\ngeneration took 16.435s", - "error": null, - "metrics": { - "predict_time": 16.44726, - "total_time": 212.763218 - }, - "created_at": "2023-12-22T17:32:18.902523Z", - "started_at": "2023-12-22T17:35:35.218481Z", - "completed_at": "2023-12-22T17:35:51.665741Z", - "urls": { - "stream": "https://streaming-api.svc.us.c.replicate.net/v1/predictions/7xg537tbifojej65lk46tfzevu", - "get": "https://api.replicate.com/v1/predictions/7xg537tbifojej65lk46tfzevu", - "cancel": "https://api.replicate.com/v1/predictions/7xg537tbifojej65lk46tfzevu/cancel" - } - }, - "latest_version": { - "id": "5d78bcd7a992c4b793465bcdcf551dc2ab9668d12bb7aa714557a21c1e77041c", - "created_at": "2024-02-17T20:20:56.733439+00:00", - "cog_version": "0.9.0-beta10", - "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" - } - }, - "/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" - } - }, - "/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": { - "$ref": "#/components/schemas/PredictionRequest" - } - } - } - } - } - }, - "/health-check": { - "get": { - "summary": "Healthcheck", - "responses": { - "200": { - "content": { - "application/json": { - "schema": { - "title": "Response Healthcheck Health Check Get" - } - } - }, - "description": "Successful Response" - } - }, - "operationId": "healthcheck_health_check_get" - } - }, - "/predictions/{prediction_id}": { - "put": { - "summary": "Predict Idempotent", - "responses": { - "200": { - "content": { - "application/json": { - "schema": { - "$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 - } - } - }, - "/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", - "required": [ - "prompt" - ], - "properties": { - "top_k": { - "type": "integer", - "title": "Top K", - "default": 50, - "x-order": 4, - "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": 3, - "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", - "x-order": 0 - }, - "temperature": { - "type": "number", - "title": "Temperature", - "default": 0.6, - "x-order": 2, - "description": "The value used to modulate the next token probabilities." - }, - "max_new_tokens": { - "type": "integer", - "title": "Max New Tokens", - "default": 512, - "x-order": 1, - "description": "The maximum number of tokens the model should generate as output." - }, - "prompt_template": { - "type": "string", - "title": "Prompt Template", - "default": "[INST] {prompt} [/INST] ", - "x-order": 7, - "description": "The template used to format the prompt. The input prompt is inserted into the template using the `{prompt}` placeholder." - }, - "presence_penalty": { - "type": "number", - "title": "Presence Penalty", - "default": 0, - "x-order": 5, - "description": "Presence penalty" - }, - "frequency_penalty": { - "type": "number", - "title": "Frequency Penalty", - "default": 0, - "x-order": 6, - "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." - }, - "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" - } - } - }, - "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 a23bc21..e00a5b7 100644 --- a/supported_models.json +++ b/supported_models.json @@ -38,7 +38,6 @@ "meta/llama-2-70b-chat", "meta/llama-2-7b-chat", "meta/musicgen", - "mistralai/mixtral-8x7b-instruct-v0.1", "nateraw/audio-super-resolution", "nateraw/musicgen-songstarter-v0.2", "omniedgeio/face-swap",