Skip to content

[Workers AI] Adds the usage stats to all Text Gen models #19492

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Jan 28, 2025
Merged

[Workers AI] Adds the usage stats to all Text Gen models #19492

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
21 changes: 21 additions & 0 deletions src/content/workers-ai-models/deepseek-coder-6.7b-base-awq.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -353,6 +353,27 @@
"type": "string",
"description": "The generated text response from the model"
},
"usage": {
"type": "object",
"description": "Usage statistics for the inference request",
"properties": {
"prompt_tokens": {
"type": "number",
"description": "Total number of tokens in input",
"default": 0
},
"completion_tokens": {
"type": "number",
"description": "Total number of tokens in output",
"default": 0
},
"total_tokens": {
"type": "number",
"description": "Total number of input and output tokens",
"default": 0
}
}
},
"tool_calls": {
"type": "array",
"description": "An array of tool calls requests made during the response generation",
Expand Down
21 changes: 21 additions & 0 deletions src/content/workers-ai-models/deepseek-coder-6.7b-instruct-awq.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -353,6 +353,27 @@
"type": "string",
"description": "The generated text response from the model"
},
"usage": {
"type": "object",
"description": "Usage statistics for the inference request",
"properties": {
"prompt_tokens": {
"type": "number",
"description": "Total number of tokens in input",
"default": 0
},
"completion_tokens": {
"type": "number",
"description": "Total number of tokens in output",
"default": 0
},
"total_tokens": {
"type": "number",
"description": "Total number of input and output tokens",
"default": 0
}
}
},
"tool_calls": {
"type": "array",
"description": "An array of tool calls requests made during the response generation",
Expand Down
21 changes: 21 additions & 0 deletions src/content/workers-ai-models/deepseek-math-7b-instruct.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -357,6 +357,27 @@
"type": "string",
"description": "The generated text response from the model"
},
"usage": {
"type": "object",
"description": "Usage statistics for the inference request",
"properties": {
"prompt_tokens": {
"type": "number",
"description": "Total number of tokens in input",
"default": 0
},
"completion_tokens": {
"type": "number",
"description": "Total number of tokens in output",
"default": 0
},
"total_tokens": {
"type": "number",
"description": "Total number of input and output tokens",
"default": 0
}
}
},
"tool_calls": {
"type": "array",
"description": "An array of tool calls requests made during the response generation",
Expand Down
21 changes: 21 additions & 0 deletions src/content/workers-ai-models/discolm-german-7b-v1-awq.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -353,6 +353,27 @@
"type": "string",
"description": "The generated text response from the model"
},
"usage": {
"type": "object",
"description": "Usage statistics for the inference request",
"properties": {
"prompt_tokens": {
"type": "number",
"description": "Total number of tokens in input",
"default": 0
},
"completion_tokens": {
"type": "number",
"description": "Total number of tokens in output",
"default": 0
},
"total_tokens": {
"type": "number",
"description": "Total number of input and output tokens",
"default": 0
}
}
},
"tool_calls": {
"type": "array",
"description": "An array of tool calls requests made during the response generation",
Expand Down
21 changes: 21 additions & 0 deletions src/content/workers-ai-models/falcon-7b-instruct.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -353,6 +353,27 @@
"type": "string",
"description": "The generated text response from the model"
},
"usage": {
"type": "object",
"description": "Usage statistics for the inference request",
"properties": {
"prompt_tokens": {
"type": "number",
"description": "Total number of tokens in input",
"default": 0
},
"completion_tokens": {
"type": "number",
"description": "Total number of tokens in output",
"default": 0
},
"total_tokens": {
"type": "number",
"description": "Total number of input and output tokens",
"default": 0
}
}
},
"tool_calls": {
"type": "array",
"description": "An array of tool calls requests made during the response generation",
Expand Down
21 changes: 21 additions & 0 deletions src/content/workers-ai-models/gemma-2b-it-lora.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -353,6 +353,27 @@
"type": "string",
"description": "The generated text response from the model"
},
"usage": {
"type": "object",
"description": "Usage statistics for the inference request",
"properties": {
"prompt_tokens": {
"type": "number",
"description": "Total number of tokens in input",
"default": 0
},
"completion_tokens": {
"type": "number",
"description": "Total number of tokens in output",
"default": 0
},
"total_tokens": {
"type": "number",
"description": "Total number of input and output tokens",
"default": 0
}
}
},
"tool_calls": {
"type": "array",
"description": "An array of tool calls requests made during the response generation",
Expand Down
21 changes: 21 additions & 0 deletions src/content/workers-ai-models/gemma-7b-it-lora.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -353,6 +353,27 @@
"type": "string",
"description": "The generated text response from the model"
},
"usage": {
"type": "object",
"description": "Usage statistics for the inference request",
"properties": {
"prompt_tokens": {
"type": "number",
"description": "Total number of tokens in input",
"default": 0
},
"completion_tokens": {
"type": "number",
"description": "Total number of tokens in output",
"default": 0
},
"total_tokens": {
"type": "number",
"description": "Total number of input and output tokens",
"default": 0
}
}
},
"tool_calls": {
"type": "array",
"description": "An array of tool calls requests made during the response generation",
Expand Down
21 changes: 21 additions & 0 deletions src/content/workers-ai-models/gemma-7b-it.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -373,6 +373,27 @@
"type": "string",
"description": "The generated text response from the model"
},
"usage": {
"type": "object",
"description": "Usage statistics for the inference request",
"properties": {
"prompt_tokens": {
"type": "number",
"description": "Total number of tokens in input",
"default": 0
},
"completion_tokens": {
"type": "number",
"description": "Total number of tokens in output",
"default": 0
},
"total_tokens": {
"type": "number",
"description": "Total number of input and output tokens",
"default": 0
}
}
},
"tool_calls": {
"type": "array",
"description": "An array of tool calls requests made during the response generation",
Expand Down
21 changes: 21 additions & 0 deletions src/content/workers-ai-models/hermes-2-pro-mistral-7b.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -357,6 +357,27 @@
"type": "string",
"description": "The generated text response from the model"
},
"usage": {
"type": "object",
"description": "Usage statistics for the inference request",
"properties": {
"prompt_tokens": {
"type": "number",
"description": "Total number of tokens in input",
"default": 0
},
"completion_tokens": {
"type": "number",
"description": "Total number of tokens in output",
"default": 0
},
"total_tokens": {
"type": "number",
"description": "Total number of input and output tokens",
"default": 0
}
}
},
"tool_calls": {
"type": "array",
"description": "An array of tool calls requests made during the response generation",
Expand Down
21 changes: 21 additions & 0 deletions src/content/workers-ai-models/llama-2-13b-chat-awq.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -353,6 +353,27 @@
"type": "string",
"description": "The generated text response from the model"
},
"usage": {
"type": "object",
"description": "Usage statistics for the inference request",
"properties": {
"prompt_tokens": {
"type": "number",
"description": "Total number of tokens in input",
"default": 0
},
"completion_tokens": {
"type": "number",
"description": "Total number of tokens in output",
"default": 0
},
"total_tokens": {
"type": "number",
"description": "Total number of input and output tokens",
"default": 0
}
}
},
"tool_calls": {
"type": "array",
"description": "An array of tool calls requests made during the response generation",
Expand Down
21 changes: 21 additions & 0 deletions src/content/workers-ai-models/llama-2-7b-chat-fp16.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -357,6 +357,27 @@
"type": "string",
"description": "The generated text response from the model"
},
"usage": {
"type": "object",
"description": "Usage statistics for the inference request",
"properties": {
"prompt_tokens": {
"type": "number",
"description": "Total number of tokens in input",
"default": 0
},
"completion_tokens": {
"type": "number",
"description": "Total number of tokens in output",
"default": 0
},
"total_tokens": {
"type": "number",
"description": "Total number of input and output tokens",
"default": 0
}
}
},
"tool_calls": {
"type": "array",
"description": "An array of tool calls requests made during the response generation",
Expand Down
21 changes: 21 additions & 0 deletions src/content/workers-ai-models/llama-2-7b-chat-hf-lora.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -353,6 +353,27 @@
"type": "string",
"description": "The generated text response from the model"
},
"usage": {
"type": "object",
"description": "Usage statistics for the inference request",
"properties": {
"prompt_tokens": {
"type": "number",
"description": "Total number of tokens in input",
"default": 0
},
"completion_tokens": {
"type": "number",
"description": "Total number of tokens in output",
"default": 0
},
"total_tokens": {
"type": "number",
"description": "Total number of input and output tokens",
"default": 0
}
}
},
"tool_calls": {
"type": "array",
"description": "An array of tool calls requests made during the response generation",
Expand Down
21 changes: 21 additions & 0 deletions src/content/workers-ai-models/llama-2-7b-chat-int8.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -344,6 +344,27 @@
"type": "string",
"description": "The generated text response from the model"
},
"usage": {
"type": "object",
"description": "Usage statistics for the inference request",
"properties": {
"prompt_tokens": {
"type": "number",
"description": "Total number of tokens in input",
"default": 0
},
"completion_tokens": {
"type": "number",
"description": "Total number of tokens in output",
"default": 0
},
"total_tokens": {
"type": "number",
"description": "Total number of input and output tokens",
"default": 0
}
}
},
"tool_calls": {
"type": "array",
"description": "An array of tool calls requests made during the response generation",
Expand Down
Loading