moinnadeem/codellama-34b-instruct-vllm | Run with an API on Replicate

Input

prompt

*string

Shift + Return to add a new line

Write a Python function downloads a html page from the internet and extracts the text of the h1 elementsWrite a Python function downloads a html page from the internet and extracts the text of the h1 elements

Prompt to send to the model.

system_prompt

string

Shift + Return to add a new line

System prompt to send to the model. This is prepended to the prompt and helps guide system behavior.

Default: "You are a helpful assistant."

max_new_tokens

integer

(minimum: 1)

Maximum number of tokens to generate. A word is generally 2-3 tokens

Default: 128

min_new_tokens

integer

(minimum: -1)

Minimum number of tokens to generate. To disable, set to -1. A word is generally 2-3 tokens.

Default: -1

temperature

number

(minimum: 0.01, maximum: 5)

Adjusts randomness of outputs, greater than 1 is random and 0 is deterministic, 0.75 is a good starting value.

Default: 0.75

top_p

number

(minimum: 0, maximum: 1)

When decoding text, samples from the top p percentage of most likely tokens; lower to ignore less likely tokens

Default: 0.9

top_k

integer

(minimum: 0)

When decoding text, samples from the top k most likely tokens; lower to ignore less likely tokens

Default: 50

stop_sequences

string

Shift + Return to add a new line

A comma-separated list of sequences to stop generation at. For example, '<end>,<stop>' will stop generation at the first instance of 'end' or '<stop>'.

seed

integer

Random seed. Leave blank to randomize the seed

debug

boolean

provide debugging output in logs

Default: false

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

npx create-replicate --model=moinnadeem/codellama-34b-instruct-vllm

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 moinnadeem/codellama-34b-instruct-vllm using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "moinnadeem/codellama-34b-instruct-vllm:49f07fcebd9e71cc2c451fd5d0667602987aa77f8ed9c6d63b8ab8ef97739fe7",
  {
    input: {
      debug: false,
      top_k: 50,
      top_p: 0.9,
      prompt: "Write a Python function downloads a html page from the internet and extracts the text of the h1 elements",
      temperature: 0.75,
      system_prompt: "You are a helpful assistant.",
      max_new_tokens: 509,
      min_new_tokens: -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 moinnadeem/codellama-34b-instruct-vllm using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "moinnadeem/codellama-34b-instruct-vllm:49f07fcebd9e71cc2c451fd5d0667602987aa77f8ed9c6d63b8ab8ef97739fe7",
    input={
        "debug": False,
        "top_k": 50,
        "top_p": 0.9,
        "prompt": "Write a Python function downloads a html page from the internet and extracts the text of the h1 elements",
        "temperature": 0.75,
        "system_prompt": "You are a helpful assistant.",
        "max_new_tokens": 509,
        "min_new_tokens": -1
    }
)

# The moinnadeem/codellama-34b-instruct-vllm 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/moinnadeem/codellama-34b-instruct-vllm/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 moinnadeem/codellama-34b-instruct-vllm 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": "moinnadeem/codellama-34b-instruct-vllm:49f07fcebd9e71cc2c451fd5d0667602987aa77f8ed9c6d63b8ab8ef97739fe7",
    "input": {
      "debug": false,
      "top_k": 50,
      "top_p": 0.9,
      "prompt": "Write a Python function downloads a html page from the internet and extracts the text of the h1 elements",
      "temperature": 0.75,
      "system_prompt": "You are a helpful assistant.",
      "max_new_tokens": 509,
      "min_new_tokens": -1
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

``` import requests from bs4 import BeautifulSoup def download_h1_text(url): response = requests.get(url) soup = BeautifulSoup(response.content, 'html.parser') h1_elements = soup.find_all('h1') text = [element.text for element in h1_elements] return text ```

{
  "completed_at": "2023-09-28T06:32:03.676481Z",
  "created_at": "2023-09-28T06:29:49.483630Z",
  "data_removed": false,
  "error": null,
  "id": "dlmoz6lb6vjarv2ydqiecszm2e",
  "input": {
    "debug": false,
    "top_k": 50,
    "top_p": 0.9,
    "prompt": "Write a Python function downloads a html page from the internet and extracts the text of the h1 elements",
    "temperature": 0.75,
    "system_prompt": "You are a helpful assistant.",
    "max_new_tokens": 509,
    "min_new_tokens": -1
  },
  "logs": "Your formatted prompt is:\n[INST] <<SYS>>\nYou are a helpful assistant.\n<</SYS>>\nWrite a Python function downloads a html page from the internet and extracts the text of the h1 elements [/INST]\nINFO 09-28 06:31:59 async_llm_engine.py:328] Received request 0: prompt: '[INST] <<SYS>>\\nYou are a helpful assistant.\\n<</SYS>>\\n\\nWrite a Python function downloads a html page from the internet and extracts the text of the h1 elements [/INST]', sampling params: SamplingParams(n=1, best_of=1, presence_penalty=0.0, frequency_penalty=1.0, temperature=0.75, top_p=0.9, top_k=50, use_beam_search=False, length_penalty=1.0, early_stopping=False, stop=['</s>'], ignore_eos=False, max_tokens=509, logprobs=None), prompt token ids: None.\nINFO 09-28 06:31:59 llm_engine.py:613] 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: 0.3%, CPU KV cache usage: 0.0%\nINFO 09-28 06:32:03 async_llm_engine.py:100] Finished request 0.\nGenerated text:  ```\nimport requests\nfrom bs4 import BeautifulSoup\ndef download_h1_text(url):\nresponse = requests.get(url)\nsoup = BeautifulSoup(response.content, 'html.parser')\nh1_elements = soup.find_all('h1')\ntext = [element.text for element in h1_elements]\nreturn text\n```\nhostname: model-c97256d5-c3f3ad7eed055505-gpu-a100-7b6bbcfb6c-hkfd7",
  "metrics": {
    "predict_time": 4.290875,
    "total_time": 134.192851
  },
  "output": [
    "",
    " ```",
    "\n",
    "import",
    " requests",
    "\n",
    "from",
    " bs",
    "4",
    " import",
    " Beautiful",
    "S",
    "oup",
    "\n",
    "\n",
    "def",
    " download",
    "_",
    "h",
    "1",
    "_",
    "text",
    "(",
    "url",
    "):",
    "\n",
    "   ",
    " response",
    " =",
    " requests",
    ".",
    "get",
    "(",
    "url",
    ")",
    "\n",
    "   ",
    " soup",
    " =",
    " Beautiful",
    "S",
    "oup",
    "(",
    "response",
    ".",
    "content",
    ",",
    " '",
    "html",
    ".",
    "parser",
    "')",
    "\n",
    "   ",
    " h",
    "1",
    "_",
    "elements",
    " =",
    " soup",
    ".",
    "find",
    "_",
    "all",
    "('",
    "h",
    "1",
    "')",
    "\n",
    "   ",
    " text",
    " =",
    " [",
    "element",
    ".",
    "text",
    " for",
    " element",
    " in",
    " h",
    "1",
    "_",
    "elements",
    "]",
    "\n",
    "   ",
    " return",
    " text",
    "\n",
    "```",
    ""
  ],
  "started_at": "2023-09-28T06:31:59.385606Z",
  "status": "succeeded",
  "urls": {
    "get": "https://api.replicate.com/v1/predictions/dlmoz6lb6vjarv2ydqiecszm2e",
    "cancel": "https://api.replicate.com/v1/predictions/dlmoz6lb6vjarv2ydqiecszm2e/cancel"
  },
  "version": "c97256d55db03f10b73fd058087165a47821eb2f776c851901da46293e952153"
}

Generated in

4.3 seconds

Tweak it Report View full prediction

This output was created using a different version of the model, moinnadeem/codellama-34b-instruct-vllm:c97256d5.

Run time and cost

This model costs approximately $0.027 to run on Replicate, or 37 runs per $1, but this varies depending on your inputs. It is also open source and you can run it on your own computer with Docker.

This model runs on Nvidia A100 (80GB) GPU hardware. Predictions typically complete within 19 seconds. The predict time for this model varies significantly based on the inputs.

Readme

This model doesn't have a readme.