{
  "top_p": 0.9,
  "prompt": "Tina has one brother and one sister. How many sisters do Tina's siblings have?",
  "max_tokens": 1024,
  "min_tokens": 0,
  "temperature": 0.6,
  "system_prompt": "You are a helpful assistant.",
  "presence_penalty": 0,
  "frequency_penalty": 0
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

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

Run meta/meta-llama-3.1-405b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  top_p: 0.9,
  prompt: "Tina has one brother and one sister. How many sisters do Tina's siblings have?",
  max_tokens: 1024,
  min_tokens: 0,
  temperature: 0.6,
  system_prompt: "You are a helpful assistant.",
  presence_penalty: 0,
  frequency_penalty: 0
};

for await (const event of replicate.stream("meta/meta-llama-3.1-405b-instruct", { input })) {
  process.stdout.write(event.toString());
};

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

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run meta/meta-llama-3.1-405b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

# The meta/meta-llama-3.1-405b-instruct model can stream output as it's running.
for event in replicate.stream(
    "meta/meta-llama-3.1-405b-instruct",
    input={
        "top_p": 0.9,
        "prompt": "Tina has one brother and one sister. How many sisters do Tina's siblings have?",
        "max_tokens": 1024,
        "min_tokens": 0,
        "temperature": 0.6,
        "system_prompt": "You are a helpful assistant.",
        "presence_penalty": 0,
        "frequency_penalty": 0
    },
):
    print(str(event), end="")

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

Run meta/meta-llama-3.1-405b-instruct 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 $'{
    "input": {
      "top_p": 0.9,
      "prompt": "Tina has one brother and one sister. How many sisters do Tina\'s siblings have?",
      "max_tokens": 1024,
      "min_tokens": 0,
      "temperature": 0.6,
      "system_prompt": "You are a helpful assistant.",
      "presence_penalty": 0,
      "frequency_penalty": 0
    }
  }' \
  https://api.replicate.com/v1/models/meta/meta-llama-3.1-405b-instruct/predictions

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

Output

{
  "completed_at": "2024-07-23T15:04:24.090090Z",
  "created_at": "2024-07-23T15:04:21.227000Z",
  "data_removed": false,
  "error": null,
  "id": "zjq6szssxdrm20cgw0fsntgvbg",
  "input": {
    "top_p": 0.9,
    "prompt": "Tina has one brother and one sister. How many sisters do Tina's siblings have?",
    "max_tokens": 1024,
    "min_tokens": 0,
    "temperature": 0.6,
    "system_prompt": "You are a helpful assistant.",
    "presence_penalty": 0,
    "frequency_penalty": 0
  },
  "logs": "INFO 07-23 15:04:21 async_llm_engine.py:173] Added request 3cd670c9b87b469ea9721ddfbcc6b67a.\nINFO 07-23 15:04:21 metrics.py:396] Avg prompt throughput: 7.8 tokens/s, Avg generation throughput: 17.7 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.3%, CPU KV cache usage: 0.0%.\nINFO 07-23 15:04:24 async_llm_engine.py:140] Finished request 3cd670c9b87b469ea9721ddfbcc6b67a.\nGeneration took 1721746720.08sFormatted prompt: <|begin_of_text|><|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|>",
  "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
  },
  "output": [
    "T",
    "ina",
    " has",
    " one",
    " brother",
    " and",
    " one",
    " sister",
    ".",
    " From",
    " the",
    " brother",
    "'s",
    " perspective",
    ",",
    " he",
    " has",
    " one",
    " sister",
    ",",
    " Tina",
    ",",
    " and",
    " also",
    " the",
    " other",
    " sister",
    ".",
    " So",
    ",",
    " Tina",
    "'s",
    " brother",
    " has",
    " ",
    "2",
    " sisters",
    ".\n\n",
    "From",
    " the",
    " sister",
    "'s",
    " perspective",
    ",",
    " she",
    " also",
    " has",
    " one",
    " sister",
    ",",
    " Tina",
    ".",
    " \n\n",
    "So",
    ",",
    " Tina",
    "'s",
    " siblings",
    " have",
    " a",
    " total",
    " of",
    " ",
    "2",
    " sisters",
    " (",
    "from",
    " the",
    " brother",
    "'s",
    " perspective",
    ")",
    " and",
    " ",
    "1",
    " sister",
    " (",
    "from",
    " the",
    " sister",
    "'s",
    " perspective",
    ").",
    ""
  ],
  "started_at": "2024-07-23T15:04:21.263665Z",
  "status": "succeeded",
  "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"
  },
  "version": "hidden"
}

Generated in

2.8 seconds

Input tokens

Output tokens

Tokens per second

29.74 tokens / second

Time to first token

0.1 seconds

Tweak it Share Report

Prediction

meta/meta-llama-3.1-405b-instruct

Official model

meta/meta-llama-3.1-405b-instruct

jzxx22twb9rm20cgw0przfgqzm

Status

Succeeded

Source

Web

Total duration

25.0s

Created

10 months ago by @meta

Input

{
  "top_p": 0.9,
  "prompt": "Invent a stack-based Turing-complete programming language with minimal syntax, write a PLY parser for it, a language runtime, and show some examples.",
  "max_tokens": 1024,
  "min_tokens": 0,
  "temperature": 0.6,
  "system_prompt": "You are an expert programmer, talking to another expert programmer. Be terse.",
  "presence_penalty": 0,
  "frequency_penalty": 0
}

Install Replicate’s Node.js client library:

npm install replicate

Import and set up the client:

import Replicate from "replicate";

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

Run meta/meta-llama-3.1-405b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const input = {
  top_p: 0.9,
  prompt: "Invent a stack-based Turing-complete programming language with minimal syntax, write a PLY parser for it, a language runtime, and show some examples.",
  max_tokens: 1024,
  min_tokens: 0,
  temperature: 0.6,
  system_prompt: "You are an expert programmer, talking to another expert programmer. Be terse.",
  presence_penalty: 0,
  frequency_penalty: 0
};

for await (const event of replicate.stream("meta/meta-llama-3.1-405b-instruct", { input })) {
  process.stdout.write(event.toString());
};

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

Install Replicate’s Python client library:

pip install replicate

Import the client:

import replicate

Run meta/meta-llama-3.1-405b-instruct using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

# The meta/meta-llama-3.1-405b-instruct model can stream output as it's running.
for event in replicate.stream(
    "meta/meta-llama-3.1-405b-instruct",
    input={
        "top_p": 0.9,
        "prompt": "Invent a stack-based Turing-complete programming language with minimal syntax, write a PLY parser for it, a language runtime, and show some examples.",
        "max_tokens": 1024,
        "min_tokens": 0,
        "temperature": 0.6,
        "system_prompt": "You are an expert programmer, talking to another expert programmer. Be terse.",
        "presence_penalty": 0,
        "frequency_penalty": 0
    },
):
    print(str(event), end="")

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

Run meta/meta-llama-3.1-405b-instruct 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 $'{
    "input": {
      "top_p": 0.9,
      "prompt": "Invent a stack-based Turing-complete programming language with minimal syntax, write a PLY parser for it, a language runtime, and show some examples.",
      "max_tokens": 1024,
      "min_tokens": 0,
      "temperature": 0.6,
      "system_prompt": "You are an expert programmer, talking to another expert programmer. Be terse.",
      "presence_penalty": 0,
      "frequency_penalty": 0
    }
  }' \
  https://api.replicate.com/v1/models/meta/meta-llama-3.1-405b-instruct/predictions

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

Output

**Language Definition** Name: `STK` * `push` instruction: `p` * `pop` instruction: `o` * `add` instruction: `+` * `sub` instruction: `-` * `mul` instruction: `*` * `div` instruction: `/` * `jump` instruction: `j` * `halt` instruction: `h` **PLY Parser** ```python import ply.lex as lex import ply.yacc as yacc # Lexer tokens = ['PUSH', 'POP', 'ADD', 'SUB', 'MUL', 'DIV', 'JUMP', 'HALT', 'NUMBER'] t_PUSH = r'p' t_POP = r'o' t_ADD = r'\+' t_SUB = r'-' t_MUL = r'\*' t_DIV = r'/' t_JUMP = r'j' t_HALT = r'h' t_NUMBER = r'\d+' # Parser def p_program(p): '''program : instruction_list''' p[0] = p[1] def p_instruction_list(p): '''instruction_list : instruction instruction_list | instruction''' if len(p) == 3: p[0] = [p[1]] + p[2] else: p[0] = [p[1]] def p_instruction(p): '''instruction : PUSH NUMBER | POP | ADD | SUB | MUL | DIV | JUMP NUMBER | HALT''' if len(p) == 3: p[0] = (p[1], int(p[2])) else: p[0] = (p[1],) # Build parser lexer = lex.lex() parser = yacc.yacc() ``` **Language Runtime** ```python class STKRuntime: def __init__(self, program): self.program = program self.pc = 0 self.stack = [] def run(self): while self.pc < len(self.program): op, *args = self.program[self.pc] self.pc += 1 if op == 'p': self.stack.append(args[0]) elif op == 'o': self.stack.pop() elif op == '+': b = self.stack.pop() a = self.stack.pop() self.stack.append(a + b) elif op == '-': b = self.stack.pop() a = self.stack.pop() self.stack.append(a - b) elif op == '*': b = self.stack.pop() a = self.stack.pop() self.stack.append(a * b) elif op == '/': b = self.stack.pop() a = self.stack.pop() self.stack.append(a // b) elif op == 'j': self.pc = args[0] elif op == 'h': break def get_result(self): return self.stack[-1] if self.stack else None # Example usage program = parser.parse('p 2 p 3 +') runtime = STKRuntime(program) runtime.run() print(runtime.get_result()) # Output: 5 ``` **More Examples** * Fibonacci sequence: `p 0 p 1 p 10 j 5 h 5 o o + p 1 j 3 h 3 o o p 1 + j 5` * Factorial: `p 5 p 1 j 3 h 3 o o * p 1 + j 3`

{
  "completed_at": "2024-07-23T15:20:12.568195Z",
  "created_at": "2024-07-23T15:19:47.546000Z",
  "data_removed": false,
  "error": null,
  "id": "jzxx22twb9rm20cgw0przfgqzm",
  "input": {
    "top_p": 0.9,
    "prompt": "Invent a stack-based Turing-complete programming language with minimal syntax, write a PLY parser for it, a language runtime, and show some examples.",
    "max_tokens": 1024,
    "min_tokens": 0,
    "temperature": 0.6,
    "system_prompt": "You are an expert programmer, talking to another expert programmer. Be terse.",
    "presence_penalty": 0,
    "frequency_penalty": 0
  },
  "logs": "INFO 07-23 15:19:47 async_llm_engine.py:173] Added request 997e070bd8ea42f798e91bc890de6c56.\nINFO 07-23 15:19:47 metrics.py:396] Avg prompt throughput: 0.2 tokens/s, Avg generation throughput: 0.3 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 0.3%, CPU KV cache usage: 0.0%.\nINFO 07-23 15:19:52 metrics.py:396] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 30.1 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 1.0%, CPU KV cache usage: 0.0%.\nINFO 07-23 15:19:57 metrics.py:396] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 30.1 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 1.7%, CPU KV cache usage: 0.0%.\nINFO 07-23 15:20:02 metrics.py:396] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 30.1 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 2.4%, CPU KV cache usage: 0.0%.\nINFO 07-23 15:20:07 metrics.py:396] Avg prompt throughput: 0.0 tokens/s, Avg generation throughput: 30.1 tokens/s, Running: 1 reqs, Swapped: 0 reqs, Pending: 0 reqs, GPU KV cache usage: 3.1%, CPU KV cache usage: 0.0%.\nINFO 07-23 15:20:12 async_llm_engine.py:140] Finished request 997e070bd8ea42f798e91bc890de6c56.\nGeneration took 1721745335.56sFormatted prompt: <|begin_of_text|><|start_header_id|>system<|end_header_id|>\n\nYou are an expert programmer, talking to another expert programmer. Be terse.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nInvent a stack-based Turing-complete programming language with minimal syntax, write a PLY parser for it, a language runtime, and show some examples.<|eot_id|><|start_header_id|>assistant<|end_header_id|>",
  "metrics": {
    "batch_size": 2.000051610448683,
    "total_time": 25.022195,
    "input_token_count": 45,
    "tokens_per_second": 30.060659635637204,
    "output_token_count": 751,
    "predict_time_share": 12.490856170654297,
    "predict_time": 24.985711232,
    "time_to_first_token": 0.112341854
  },
  "output": [
    "**",
    "Language",
    " Definition",
    "**\n\n",
    "Name",
    ":",
    " `",
    "ST",
    "K",
    "`\n\n",
    "*",
    " `",
    "push",
    "`",
    " instruction",
    ":",
    " `",
    "p",
    "`\n",
    "*",
    " `",
    "pop",
    "`",
    " instruction",
    ":",
    " `",
    "o",
    "`\n",
    "*",
    " `",
    "add",
    "`",
    " instruction",
    ":",
    " `",
    "+",
    "`\n",
    "*",
    " `",
    "sub",
    "`",
    " instruction",
    ":",
    " `-",
    "`\n",
    "*",
    " `",
    "mul",
    "`",
    " instruction",
    ":",
    " `",
    "*",
    "`\n",
    "*",
    " `",
    "div",
    "`",
    " instruction",
    ":",
    " `/",
    "`\n",
    "*",
    " `",
    "jump",
    "`",
    " instruction",
    ":",
    " `",
    "j",
    "`\n",
    "*",
    " `",
    "halt",
    "`",
    " instruction",
    ":",
    " `",
    "h",
    "`\n\n",
    "**",
    "PLY",
    " Parser",
    "**\n\n",
    "```",
    "python",
    "\n",
    "import",
    " ply",
    ".lex",
    " as",
    " lex",
    "\n",
    "import",
    " ply",
    ".y",
    "acc",
    " as",
    " yacc",
    "\n\n",
    "#",
    " Lexer",
    "\n",
    "tokens",
    " =",
    " ['",
    "P",
    "USH",
    "',",
    " '",
    "POP",
    "',",
    " '",
    "ADD",
    "',",
    " '",
    "SUB",
    "',",
    " '",
    "M",
    "UL",
    "',",
    " '",
    "DIV",
    "',",
    " '",
    "J",
    "UMP",
    "',",
    " '",
    "HAL",
    "T",
    "',",
    " '",
    "NUMBER",
    "']\n\n",
    "t",
    "_PUSH",
    " =",
    " r",
    "'",
    "p",
    "'\n",
    "t",
    "_POP",
    " =",
    " r",
    "'o",
    "'\n",
    "t",
    "_ADD",
    " =",
    " r",
    "'\\",
    "+",
    "'\n",
    "t",
    "_SUB",
    " =",
    " r",
    "'-",
    "'\n",
    "t",
    "_MUL",
    " =",
    " r",
    "'\\",
    "*",
    "'\n",
    "t",
    "_DIV",
    " =",
    " r",
    "'/",
    "'\n",
    "t",
    "_JUMP",
    " =",
    " r",
    "'",
    "j",
    "'\n",
    "t",
    "_H",
    "ALT",
    " =",
    " r",
    "'h",
    "'\n",
    "t",
    "_NUMBER",
    " =",
    " r",
    "'\\",
    "d",
    "+",
    "'\n\n",
    "#",
    " Parser",
    "\n",
    "def",
    " p",
    "_program",
    "(p",
    "):\n",
    "   ",
    " '''",
    "program",
    " :",
    " instruction",
    "_list",
    "'''\n",
    "   ",
    " p",
    "[",
    "0",
    "]",
    " =",
    " p",
    "[",
    "1",
    "]\n\n",
    "def",
    " p",
    "_instruction",
    "_list",
    "(p",
    "):\n",
    "   ",
    " '''",
    "instruction",
    "_list",
    " :",
    " instruction",
    " instruction",
    "_list",
    "\n",
    "                      ",
    " |",
    " instruction",
    "'''\n",
    "   ",
    " if",
    " len",
    "(p",
    ")",
    " ==",
    " ",
    "3",
    ":\n",
    "       ",
    " p",
    "[",
    "0",
    "]",
    " =",
    " [",
    "p",
    "[",
    "1",
    "]]",
    " +",
    " p",
    "[",
    "2",
    "]\n",
    "   ",
    " else",
    ":\n",
    "       ",
    " p",
    "[",
    "0",
    "]",
    " =",
    " [",
    "p",
    "[",
    "1",
    "]]\n\n",
    "def",
    " p",
    "_instruction",
    "(p",
    "):\n",
    "   ",
    " '''",
    "instruction",
    " :",
    " PUSH",
    " NUMBER",
    "\n",
    "                  ",
    " |",
    " POP",
    "\n",
    "                  ",
    " |",
    " ADD",
    "\n",
    "                  ",
    " |",
    " SUB",
    "\n",
    "                  ",
    " |",
    " M",
    "UL",
    "\n",
    "                  ",
    " |",
    " DIV",
    "\n",
    "                  ",
    " |",
    " J",
    "UMP",
    " NUMBER",
    "\n",
    "                  ",
    " |",
    " HAL",
    "T",
    "'''\n",
    "   ",
    " if",
    " len",
    "(p",
    ")",
    " ==",
    " ",
    "3",
    ":\n",
    "       ",
    " p",
    "[",
    "0",
    "]",
    " =",
    " (",
    "p",
    "[",
    "1",
    "],",
    " int",
    "(p",
    "[",
    "2",
    "]))\n",
    "   ",
    " else",
    ":\n",
    "       ",
    " p",
    "[",
    "0",
    "]",
    " =",
    " (",
    "p",
    "[",
    "1",
    "],",
    ")\n\n",
    "#",
    " Build",
    " parser",
    "\n",
    "lexer",
    " =",
    " lex",
    ".lex",
    "()\n",
    "parser",
    " =",
    " yacc",
    ".y",
    "acc",
    "()\n",
    "``",
    "`\n\n",
    "**",
    "Language",
    " Runtime",
    "**\n\n",
    "```",
    "python",
    "\n",
    "class",
    " ST",
    "K",
    "Runtime",
    ":\n",
    "   ",
    " def",
    " __",
    "init",
    "__(",
    "self",
    ",",
    " program",
    "):\n",
    "       ",
    " self",
    ".program",
    " =",
    " program",
    "\n",
    "       ",
    " self",
    ".pc",
    " =",
    " ",
    "0",
    "\n",
    "       ",
    " self",
    ".stack",
    " =",
    " []\n\n",
    "   ",
    " def",
    " run",
    "(self",
    "):\n",
    "       ",
    " while",
    " self",
    ".pc",
    " <",
    " len",
    "(self",
    ".program",
    "):\n",
    "           ",
    " op",
    ",",
    " *",
    "args",
    " =",
    " self",
    ".program",
    "[self",
    ".pc",
    "]\n",
    "           ",
    " self",
    ".pc",
    " +=",
    " ",
    "1",
    "\n",
    "           ",
    " if",
    " op",
    " ==",
    " '",
    "p",
    "':\n",
    "               ",
    " self",
    ".stack",
    ".append",
    "(args",
    "[",
    "0",
    "])\n",
    "           ",
    " elif",
    " op",
    " ==",
    " '",
    "o",
    "':\n",
    "               ",
    " self",
    ".stack",
    ".pop",
    "()\n",
    "           ",
    " elif",
    " op",
    " ==",
    " '+",
    "':\n",
    "               ",
    " b",
    " =",
    " self",
    ".stack",
    ".pop",
    "()\n",
    "               ",
    " a",
    " =",
    " self",
    ".stack",
    ".pop",
    "()\n",
    "               ",
    " self",
    ".stack",
    ".append",
    "(a",
    " +",
    " b",
    ")\n",
    "           ",
    " elif",
    " op",
    " ==",
    " '-",
    "':\n",
    "               ",
    " b",
    " =",
    " self",
    ".stack",
    ".pop",
    "()\n",
    "               ",
    " a",
    " =",
    " self",
    ".stack",
    ".pop",
    "()\n",
    "               ",
    " self",
    ".stack",
    ".append",
    "(a",
    " -",
    " b",
    ")\n",
    "           ",
    " elif",
    " op",
    " ==",
    " '*",
    "':\n",
    "               ",
    " b",
    " =",
    " self",
    ".stack",
    ".pop",
    "()\n",
    "               ",
    " a",
    " =",
    " self",
    ".stack",
    ".pop",
    "()\n",
    "               ",
    " self",
    ".stack",
    ".append",
    "(a",
    " *",
    " b",
    ")\n",
    "           ",
    " elif",
    " op",
    " ==",
    " '/",
    "':\n",
    "               ",
    " b",
    " =",
    " self",
    ".stack",
    ".pop",
    "()\n",
    "               ",
    " a",
    " =",
    " self",
    ".stack",
    ".pop",
    "()\n",
    "               ",
    " self",
    ".stack",
    ".append",
    "(a",
    " //",
    " b",
    ")\n",
    "           ",
    " elif",
    " op",
    " ==",
    " '",
    "j",
    "':\n",
    "               ",
    " self",
    ".pc",
    " =",
    " args",
    "[",
    "0",
    "]\n",
    "           ",
    " elif",
    " op",
    " ==",
    " '",
    "h",
    "':\n",
    "               ",
    " break",
    "\n\n",
    "   ",
    " def",
    " get",
    "_result",
    "(self",
    "):\n",
    "       ",
    " return",
    " self",
    ".stack",
    "[-",
    "1",
    "]",
    " if",
    " self",
    ".stack",
    " else",
    " None",
    "\n\n",
    "#",
    " Example",
    " usage",
    "\n",
    "program",
    " =",
    " parser",
    ".parse",
    "('",
    "p",
    " ",
    "2",
    " p",
    " ",
    "3",
    " +",
    "')\n",
    "runtime",
    " =",
    " ST",
    "K",
    "Runtime",
    "(program",
    ")\n",
    "runtime",
    ".run",
    "()\n",
    "print",
    "(runtime",
    ".get",
    "_result",
    "())",
    " ",
    " #",
    " Output",
    ":",
    " ",
    "5",
    "\n",
    "``",
    "`\n\n",
    "**",
    "More",
    " Examples",
    "**\n\n",
    "*",
    " Fibonacci",
    " sequence",
    ":",
    " `",
    "p",
    " ",
    "0",
    " p",
    " ",
    "1",
    " p",
    " ",
    "10",
    " j",
    " ",
    "5",
    " h",
    " ",
    "5",
    " o",
    " o",
    " +",
    " p",
    " ",
    "1",
    " j",
    " ",
    "3",
    " h",
    " ",
    "3",
    " o",
    " o",
    " p",
    " ",
    "1",
    " +",
    " j",
    " ",
    "5",
    "`\n",
    "*",
    " Factor",
    "ial",
    ":",
    " `",
    "p",
    " ",
    "5",
    " p",
    " ",
    "1",
    " j",
    " ",
    "3",
    " h",
    " ",
    "3",
    " o",
    " o",
    " *",
    " p",
    " ",
    "1",
    " +",
    " j",
    " ",
    "3",
    "`",
    ""
  ],
  "started_at": "2024-07-23T15:19:47.582483Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.sea.v.replicate.net/v1/streams/oo3jqmezolvmqhrq4nxquskhrt5ob6hugjjheyrhbuldkejk3rpq",
    "get": "https://api.replicate.com/v1/predictions/jzxx22twb9rm20cgw0przfgqzm",
    "cancel": "https://api.replicate.com/v1/predictions/jzxx22twb9rm20cgw0przfgqzm/cancel"
  },
  "version": "hidden"
}

Generated in

25.0 seconds

Input tokens

Output tokens

750

Tokens per second

30.06 tokens / second

Time to first token

0.1 seconds

Tweak it Share Report