andreasjansson/wizardcoder-python-34b-v1-gguf:b357a162

Version

You're looking at a specific version of this model. Jump to the model overview.

andreasjansson /wizardcoder-python-34b-v1-gguf:b357a162

Input

prompt

*string

Shift + Return to add a new line

Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Send a email from andreas86@telia.se to myfriend@telia.se where you discuss the weather. In the body, describe the current weather in Stockholm as detailed as possible.

Respond with json that adheres to the following jsonschema:

{jsonschema}

### Response:Below is an instruction that describes a task. Write a response that appropriately completes the request.

### Instruction:
Send a email from andreas86@telia.se to myfriend@telia.se where you discuss the weather. In the body, describe the current weather in Stockholm as detailed as possible.

Respond with json that adheres to the following jsonschema:

{jsonschema}

### Response:

Prompt

grammar

string

Shift + Return to add a new line

Grammar in GBNF format. Use either grammar or jsonschema.

jsonschema

string

Shift + Return to add a new line

{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "type": "object",
  "properties": {
    "from": {
      "type": "string",
      "format": "email",
      "description": "The email address of the sender."
    },
    "to": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "email"
      },
      "description": "An array of email addresses to send the email to."
    },
    "cc": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "email"
      },
      "description": "An array of email addresses to be included in the CC field."
    },
    "bcc": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "email"
      },
      "description": "An array of email addresses to be included in the BCC field."
    },
    "subject": {
      "type": "string",
      "description": "The subject of the email."
    },
    "body": {
      "type": "string",
      "description": "The body text of the email."
    }
  },
  "required": ["from", "to", "subject", "body"],
  "additionalProperties": false
}{
  "$schema": "http://json-schema.org/draft-07/schema#",
  "type": "object",
  "properties": {
    "from": {
      "type": "string",
      "format": "email",
      "description": "The email address of the sender."
    },
    "to": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "email"
      },
      "description": "An array of email addresses to send the email to."
    },
    "cc": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "email"
      },
      "description": "An array of email addresses to be included in the CC field."
    },
    "bcc": {
      "type": "array",
      "items": {
        "type": "string",
        "format": "email"
      },
      "description": "An array of email addresses to be included in the BCC field."
    },
    "subject": {
      "type": "string",
      "description": "The subject of the email."
    },
    "body": {
      "type": "string",
      "description": "The body text of the email."
    }
  },
  "required": ["from", "to", "subject", "body"],
  "additionalProperties": false
}

JSON schema for the generated output. Use either grammar or jsonschema. You can use the jsonschema in the prompt by using the special string '{jsonschema}'

max_tokens

integer

Max number of tokens to return

Default: 500

temperature

number

Temperature

Default: 0.8

top_p

number

Top P

Default: 0.95

top_k

integer

Top K

Default: 10

frequency_penalty

number

(minimum: 0, maximum: 2)

Frequency penalty

Default: 0

presence_penalty

number

(minimum: 0, maximum: 2)

Presence

Default: 0

repeat_penalty

number

(minimum: 0, maximum: 2)

Repetition penalty

Default: 1.1

mirostat_mode

string

Mirostat sampling mode

Default: "Disabled"

mirostat_learning_rate

number

(minimum: 0, maximum: 1)

Mirostat learning rate, if mirostat_mode is not Disabled

Default: 0.1

mirostat_entropy

number

(minimum: 0, maximum: 10)

Mirostat target entropy

Default: 5

Run this model in Node.js with one line of code:

npx create-replicate --model=andreasjansson/wizardcoder-python-34b-v1-gguf

or set up a project from scratch

Install Replicate’s Node.js client library:

npm install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import and set up the client:

import Replicate from "replicate";

const replicate = new Replicate({
  auth: process.env.REPLICATE_API_TOKEN,
});

Run andreasjansson/wizardcoder-python-34b-v1-gguf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "andreasjansson/wizardcoder-python-34b-v1-gguf:b357a162acd41ce53c04b14a25df0f1d476c2e39d465895d28cdba87944506c6",
  {
    input: {
      top_k: 10,
      top_p: 0.95,
      prompt: "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nSend a email from andreas86@telia.se to myfriend@telia.se where you discuss the weather. In the body, describe the current weather in Stockholm as detailed as possible.\n\nRespond with json that adheres to the following jsonschema:\n\n{jsonschema}\n\n### Response:",
      grammar: "",
      jsonschema: "{\n  \"$schema\": \"http://json-schema.org/draft-07/schema#\",\n  \"type\": \"object\",\n  \"properties\": {\n    \"from\": {\n      \"type\": \"string\",\n      \"format\": \"email\",\n      \"description\": \"The email address of the sender.\"\n    },\n    \"to\": {\n      \"type\": \"array\",\n      \"items\": {\n        \"type\": \"string\",\n        \"format\": \"email\"\n      },\n      \"description\": \"An array of email addresses to send the email to.\"\n    },\n    \"cc\": {\n      \"type\": \"array\",\n      \"items\": {\n        \"type\": \"string\",\n        \"format\": \"email\"\n      },\n      \"description\": \"An array of email addresses to be included in the CC field.\"\n    },\n    \"bcc\": {\n      \"type\": \"array\",\n      \"items\": {\n        \"type\": \"string\",\n        \"format\": \"email\"\n      },\n      \"description\": \"An array of email addresses to be included in the BCC field.\"\n    },\n    \"subject\": {\n      \"type\": \"string\",\n      \"description\": \"The subject of the email.\"\n    },\n    \"body\": {\n      \"type\": \"string\",\n      \"description\": \"The body text of the email.\"\n    }\n  },\n  \"required\": [\"from\", \"to\", \"subject\", \"body\"],\n  \"additionalProperties\": false\n}",
      max_tokens: 500,
      temperature: 0.8,
      mirostat_mode: "Disabled",
      repeat_penalty: 1.1,
      mirostat_entropy: 5,
      presence_penalty: 0,
      frequency_penalty: 0,
      mirostat_learning_rate: 0.1
    }
  }
);

console.log(output);

To learn more, take a look at the guide on getting started with Node.js.

Install Replicate’s Python client library:

pip install replicate

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Import the client:

import replicate

Run andreasjansson/wizardcoder-python-34b-v1-gguf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "andreasjansson/wizardcoder-python-34b-v1-gguf:b357a162acd41ce53c04b14a25df0f1d476c2e39d465895d28cdba87944506c6",
    input={
        "top_k": 10,
        "top_p": 0.95,
        "prompt": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nSend a email from andreas86@telia.se to myfriend@telia.se where you discuss the weather. In the body, describe the current weather in Stockholm as detailed as possible.\n\nRespond with json that adheres to the following jsonschema:\n\n{jsonschema}\n\n### Response:",
        "grammar": "",
        "jsonschema": "{\n  \"$schema\": \"http://json-schema.org/draft-07/schema#\",\n  \"type\": \"object\",\n  \"properties\": {\n    \"from\": {\n      \"type\": \"string\",\n      \"format\": \"email\",\n      \"description\": \"The email address of the sender.\"\n    },\n    \"to\": {\n      \"type\": \"array\",\n      \"items\": {\n        \"type\": \"string\",\n        \"format\": \"email\"\n      },\n      \"description\": \"An array of email addresses to send the email to.\"\n    },\n    \"cc\": {\n      \"type\": \"array\",\n      \"items\": {\n        \"type\": \"string\",\n        \"format\": \"email\"\n      },\n      \"description\": \"An array of email addresses to be included in the CC field.\"\n    },\n    \"bcc\": {\n      \"type\": \"array\",\n      \"items\": {\n        \"type\": \"string\",\n        \"format\": \"email\"\n      },\n      \"description\": \"An array of email addresses to be included in the BCC field.\"\n    },\n    \"subject\": {\n      \"type\": \"string\",\n      \"description\": \"The subject of the email.\"\n    },\n    \"body\": {\n      \"type\": \"string\",\n      \"description\": \"The body text of the email.\"\n    }\n  },\n  \"required\": [\"from\", \"to\", \"subject\", \"body\"],\n  \"additionalProperties\": false\n}",
        "max_tokens": 500,
        "temperature": 0.8,
        "mirostat_mode": "Disabled",
        "repeat_penalty": 1.1,
        "mirostat_entropy": 5,
        "presence_penalty": 0,
        "frequency_penalty": 0,
        "mirostat_learning_rate": 0.1
    }
)

# The andreasjansson/wizardcoder-python-34b-v1-gguf model can stream output as it's running.
# The predict method returns an iterator, and you can iterate over that output.
for item in output:
    # https://replicate.com/andreasjansson/wizardcoder-python-34b-v1-gguf/api#output-schema
    print(item, end="")

To learn more, take a look at the guide on getting started with Python.

Set the REPLICATE_API_TOKEN environment variable:

export REPLICATE_API_TOKEN=<paste-your-token-here>

Find your API token in your account settings.

Run andreasjansson/wizardcoder-python-34b-v1-gguf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

curl -s -X POST \
  -H "Authorization: Bearer $REPLICATE_API_TOKEN" \
  -H "Content-Type: application/json" \
  -H "Prefer: wait" \
  -d $'{
    "version": "andreasjansson/wizardcoder-python-34b-v1-gguf:b357a162acd41ce53c04b14a25df0f1d476c2e39d465895d28cdba87944506c6",
    "input": {
      "top_k": 10,
      "top_p": 0.95,
      "prompt": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\\n\\n### Instruction:\\nSend a email from andreas86@telia.se to myfriend@telia.se where you discuss the weather. In the body, describe the current weather in Stockholm as detailed as possible.\\n\\nRespond with json that adheres to the following jsonschema:\\n\\n{jsonschema}\\n\\n### Response:",
      "grammar": "",
      "jsonschema": "{\\n  \\"$schema\\": \\"http://json-schema.org/draft-07/schema#\\",\\n  \\"type\\": \\"object\\",\\n  \\"properties\\": {\\n    \\"from\\": {\\n      \\"type\\": \\"string\\",\\n      \\"format\\": \\"email\\",\\n      \\"description\\": \\"The email address of the sender.\\"\\n    },\\n    \\"to\\": {\\n      \\"type\\": \\"array\\",\\n      \\"items\\": {\\n        \\"type\\": \\"string\\",\\n        \\"format\\": \\"email\\"\\n      },\\n      \\"description\\": \\"An array of email addresses to send the email to.\\"\\n    },\\n    \\"cc\\": {\\n      \\"type\\": \\"array\\",\\n      \\"items\\": {\\n        \\"type\\": \\"string\\",\\n        \\"format\\": \\"email\\"\\n      },\\n      \\"description\\": \\"An array of email addresses to be included in the CC field.\\"\\n    },\\n    \\"bcc\\": {\\n      \\"type\\": \\"array\\",\\n      \\"items\\": {\\n        \\"type\\": \\"string\\",\\n        \\"format\\": \\"email\\"\\n      },\\n      \\"description\\": \\"An array of email addresses to be included in the BCC field.\\"\\n    },\\n    \\"subject\\": {\\n      \\"type\\": \\"string\\",\\n      \\"description\\": \\"The subject of the email.\\"\\n    },\\n    \\"body\\": {\\n      \\"type\\": \\"string\\",\\n      \\"description\\": \\"The body text of the email.\\"\\n    }\\n  },\\n  \\"required\\": [\\"from\\", \\"to\\", \\"subject\\", \\"body\\"],\\n  \\"additionalProperties\\": false\\n}",
      "max_tokens": 500,
      "temperature": 0.8,
      "mirostat_mode": "Disabled",
      "repeat_penalty": 1.1,
      "mirostat_entropy": 5,
      "presence_penalty": 0,
      "frequency_penalty": 0,
      "mirostat_learning_rate": 0.1
    }
  }' \
  https://api.replicate.com/v1/predictions

To learn more, take a look at Replicate’s HTTP API reference docs.

Output

{"bcc": [],"body": "Hello myfriend,\n\nIt is currently raining in Stockholm and the temperature is around 15 degrees Celsius. The wind is strong and the sky is overcast, but it won't last long as we are expecting sunny weather this weekend. It is a good day for a picnic or a walk in the park!\n\nRegards,\nAndreas","cc": [],"from": "andreas86@telia.se","subject": "Weather Update from Stockholm","to": ["myfriend@telia.se"]}

{
  "completed_at": "2023-09-22T22:11:51.234816Z",
  "created_at": "2023-09-22T22:11:42.978818Z",
  "data_removed": false,
  "error": null,
  "id": "rlnwn6dbidyjpx4qfiizgqcd2u",
  "input": {
    "top_k": 10,
    "top_p": 0.95,
    "prompt": "Below is an instruction that describes a task. Write a response that appropriately completes the request.\n\n### Instruction:\nSend a email from andreas86@telia.se to myfriend@telia.se where you discuss the weather. In the body, describe the current weather in Stockholm as detailed as possible.\n\nRespond with json that adheres to the following jsonschema:\n\n{jsonschema}\n\n### Response:",
    "grammar": "",
    "jsonschema": "{\n  \"$schema\": \"http://json-schema.org/draft-07/schema#\",\n  \"type\": \"object\",\n  \"properties\": {\n    \"from\": {\n      \"type\": \"string\",\n      \"format\": \"email\",\n      \"description\": \"The email address of the sender.\"\n    },\n    \"to\": {\n      \"type\": \"array\",\n      \"items\": {\n        \"type\": \"string\",\n        \"format\": \"email\"\n      },\n      \"description\": \"An array of email addresses to send the email to.\"\n    },\n    \"cc\": {\n      \"type\": \"array\",\n      \"items\": {\n        \"type\": \"string\",\n        \"format\": \"email\"\n      },\n      \"description\": \"An array of email addresses to be included in the CC field.\"\n    },\n    \"bcc\": {\n      \"type\": \"array\",\n      \"items\": {\n        \"type\": \"string\",\n        \"format\": \"email\"\n      },\n      \"description\": \"An array of email addresses to be included in the BCC field.\"\n    },\n    \"subject\": {\n      \"type\": \"string\",\n      \"description\": \"The subject of the email.\"\n    },\n    \"body\": {\n      \"type\": \"string\",\n      \"description\": \"The body text of the email.\"\n    }\n  },\n  \"required\": [\"from\", \"to\", \"subject\", \"body\"],\n  \"additionalProperties\": false\n}",
    "max_tokens": 500,
    "temperature": 0.8,
    "mirostat_mode": "Disabled",
    "repeat_penalty": 1.1,
    "mirostat_entropy": 5,
    "presence_penalty": 0,
    "frequency_penalty": 0,
    "mirostat_learning_rate": 0.1
  },
  "logs": "from_string grammar:\nspace ::= space_1\nspace_1 ::= [ ] |\nstring ::= [\"] string_5 [\"] space\nstring_3 ::= [^\"\\] | [\\] string_4\nstring_4 ::= [\"\\/bfnrt] | [u] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F]\nstring_5 ::= string_3 string_5 |\nbcc ::= [[] space bcc_10 []] space\nbcc_7 ::= string bcc_9\nbcc_8 ::= [,] space string\nbcc_9 ::= bcc_8 bcc_9 |\nbcc_10 ::= bcc_7 |\ncc ::= [[] space cc_15 []] space\ncc_12 ::= string cc_14\ncc_13 ::= [,] space string \ncc_14 ::= cc_13 cc_14 |\ncc_15 ::= cc_12 | \nto ::= [[] space to_20 []] space \nto_17 ::= string to_19\nto_18 ::= [,] space string\nto_19 ::= to_18 to_19 | \nto_20 ::= to_17 |\nroot ::= [{] space [\"] [b] [c] [c] [\"] space [:] space bcc [,] space [\"] [b] [o] [d] [y] [\"] space [:] space string [,] space [\"] [c] [c] [\"] space [:] space cc [,] space [\"] [f] [r] [o] [m] [\"] space [:] space string [,] space [\"] [s] [u] [b] [j] [e] [c] [t] [\"] space [:] space string [,] space [\"] [t] [o] [\"] space [:] space to [}] space\nPrompt:\nBelow is an instruction that describes a task. Write a response that appropriately completes the request.\n### Instruction:\nSend a email from andreas86@telia.se to myfriend@telia.se where you discuss the weather. In the body, describe the current weather in Stockholm as detailed as possible.\nRespond with json that adheres to the following jsonschema:\n{\n\"$schema\": \"http://json-schema.org/draft-07/schema#\",\n\"type\": \"object\",\n\"properties\": {\n\"from\": {\n\"type\": \"string\",\n\"format\": \"email\",\n\"description\": \"The email address of the sender.\"\n},\n\"to\": {\n\"type\": \"array\",\n\"items\": {\n\"type\": \"string\",\n\"format\": \"email\"\n},\n\"description\": \"An array of email addresses to send the email to.\"\n},\n\"cc\": {\n\"type\": \"array\",\n\"items\": {\n\"type\": \"string\",\n\"format\": \"email\"\n},\n\"description\": \"An array of email addresses to be included in the CC field.\"\n},\n\"bcc\": {\n\"type\": \"array\",\n\"items\": {\n\"type\": \"string\",\n\"format\": \"email\"\n},\n\"description\": \"An array of email addresses to be included in the BCC field.\"\n},\n\"subject\": {\n\"type\": \"string\",\n\"description\": \"The subject of the email.\"\n},\n\"body\": {\n\"type\": \"string\",\n\"description\": \"The body text of the email.\"\n}\n},\n\"required\": [\"from\", \"to\", \"subject\", \"body\"],\n\"additionalProperties\": false\n}\n### Response:\nLlama.generate: prefix-match hit\nllama_print_timings:        load time =   323.93 ms\nllama_print_timings:      sample time =  1143.80 ms /   131 runs   (    8.73 ms per token,   114.53 tokens per second)\nllama_print_timings: prompt eval time =   954.76 ms /   372 tokens (    2.57 ms per token,   389.63 tokens per second)\nllama_print_timings:        eval time =  5865.64 ms /   130 runs   (   45.12 ms per token,    22.16 tokens per second)\nllama_print_timings:       total time =  8286.14 ms",
  "metrics": {
    "predict_time": 8.301813,
    "total_time": 8.255998
  },
  "output": [
    "{\"",
    "b",
    "cc",
    "\":",
    " [],",
    "\"",
    "body",
    "\":",
    " \"",
    "Hello",
    " my",
    "friend",
    ",\\",
    "n",
    "\\",
    "n",
    "It",
    " is",
    " currently",
    " ra",
    "ining",
    " in",
    " Stockholm",
    " and",
    " the",
    " temperature",
    " is",
    " around",
    " ",
    "1",
    "5",
    " degrees",
    " Cel",
    "si",
    "us",
    ".",
    " The",
    " wind",
    " is",
    " strong",
    " and",
    " the",
    " sky",
    " is",
    " over",
    "cast",
    ",",
    " but",
    " it",
    " won",
    "'",
    "t",
    " last",
    " long",
    " as",
    " we",
    " are",
    " expecting",
    " sun",
    "ny",
    " weather",
    " this",
    " week",
    "end",
    ".",
    " It",
    " is",
    " a",
    " good",
    " day",
    " for",
    " a",
    " pic",
    "nic",
    " or",
    " a",
    " walk",
    " in",
    " the",
    " park",
    "!\\",
    "n",
    "\\",
    "n",
    "Reg",
    "ards",
    ",\\",
    "n",
    "And",
    "reas",
    "\",\"",
    "cc",
    "\":",
    " [],",
    "\"",
    "from",
    "\":",
    " \"",
    "and",
    "reas",
    "8",
    "6",
    "@",
    "t",
    "elia",
    ".",
    "se",
    "\",\"",
    "subject",
    "\":",
    " \"",
    "We",
    "ather",
    " Update",
    " from",
    " Stockholm",
    "\",\"",
    "to",
    "\":",
    " [\"",
    "my",
    "friend",
    "@",
    "t",
    "elia",
    ".",
    "se",
    "\"]",
    "}",
    " "
  ],
  "started_at": "2023-09-22T22:11:42.933003Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/rlnwn6dbidyjpx4qfiizgqcd2u",
    "cancel": "https://api.replicate.com/v1/predictions/rlnwn6dbidyjpx4qfiizgqcd2u/cancel"
  },
  "version": "b357a162acd41ce53c04b14a25df0f1d476c2e39d465895d28cdba87944506c6"
}

Generated in

8.3 seconds

Tweak it Report View full prediction

from_string grammar:
space ::= space_1
space_1 ::= [ ] |
string ::= ["] string_5 ["] space
string_3 ::= [^"\] | [\] string_4
string_4 ::= ["\/bfnrt] | [u] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F] [0-9a-fA-F]
string_5 ::= string_3 string_5 |
bcc ::= [[] space bcc_10 []] space
bcc_7 ::= string bcc_9
bcc_8 ::= [,] space string
bcc_9 ::= bcc_8 bcc_9 |
bcc_10 ::= bcc_7 |
cc ::= [[] space cc_15 []] space
cc_12 ::= string cc_14
cc_13 ::= [,] space string 
cc_14 ::= cc_13 cc_14 |
cc_15 ::= cc_12 | 
to ::= [[] space to_20 []] space 
to_17 ::= string to_19
to_18 ::= [,] space string
to_19 ::= to_18 to_19 | 
to_20 ::= to_17 |
root ::= [{] space ["] [b] [c] [c] ["] space [:] space bcc [,] space ["] [b] [o] [d] [y] ["] space [:] space string [,] space ["] [c] [c] ["] space [:] space cc [,] space ["] [f] [r] [o] [m] ["] space [:] space string [,] space ["] [s] [u] [b] [j] [e] [c] [t] ["] space [:] space string [,] space ["] [t] [o] ["] space [:] space to [}] space
Prompt:
Below is an instruction that describes a task. Write a response that appropriately completes the request.
### Instruction:
Send a email from andreas86@telia.se to myfriend@telia.se where you discuss the weather. In the body, describe the current weather in Stockholm as detailed as possible.
Respond with json that adheres to the following jsonschema:
{
"$schema": "http://json-schema.org/draft-07/schema#",
"type": "object",
"properties": {
"from": {
"type": "string",
"format": "email",
"description": "The email address of the sender."
},
"to": {
"type": "array",
"items": {
"type": "string",
"format": "email"
},
"description": "An array of email addresses to send the email to."
},
"cc": {
"type": "array",
"items": {
"type": "string",
"format": "email"
},
"description": "An array of email addresses to be included in the CC field."
},
"bcc": {
"type": "array",
"items": {
"type": "string",
"format": "email"
},
"description": "An array of email addresses to be included in the BCC field."
},
"subject": {
"type": "string",
"description": "The subject of the email."
},
"body": {
"type": "string",
"description": "The body text of the email."
}
},
"required": ["from", "to", "subject", "body"],
"additionalProperties": false
}
### Response:
Llama.generate: prefix-match hit
llama_print_timings:        load time =   323.93 ms
llama_print_timings:      sample time =  1143.80 ms /   131 runs   (    8.73 ms per token,   114.53 tokens per second)
llama_print_timings: prompt eval time =   954.76 ms /   372 tokens (    2.57 ms per token,   389.63 tokens per second)
llama_print_timings:        eval time =  5865.64 ms /   130 runs   (   45.12 ms per token,    22.16 tokens per second)
llama_print_timings:       total time =  8286.14 ms