kcaverly/phind-codellama-34b-v2-gguf – Run with an API on Replicate

kcaverly / phind-codellama-34b-v2-gguf

A quantized 34B parameter language model from Phind for code completion

Cold

Public
230 runs
L40S
GitHub
Paper
License

Run with an API

Playground API Examples README Versions

Input

prompt

*string

Shift + Return to add a new line

please create a rust enum called prediction status, with three variants starting, in progress and completed. Please only include valid rust code, do not include any commentary or explanations.please create a rust enum called prediction status, with three variants starting, in progress and completed. Please only include valid rust code, do not include any commentary or explanations.

Instruction for model

system_prompt

string

Shift + Return to add a new line

You are an intelligent programming assistant.You are an intelligent programming assistant.

System prompt for the model, helps guides model behaviour.

Default: "You are an intelligent programming assistant."

prompt_template

string

Shift + Return to add a new line

### System Prompt
{system_prompt}
### User Message
{prompt}
### Assistant
### System Prompt
{system_prompt}
### User Message
{prompt}
### Assistant

Template to pass to model. Override if you are providing multi-turn instructions.

Default: "### System Prompt\n{system_prompt}\n### User Message\n{prompt}\n### Assistant\n"

max_new_tokens

integer

Maximum new tokens to generate.

Default: -1

top_p

number

This parameter controls how many of the highest-probability words are selected to be included in the generated text

Default: 0.75

top_k

integer

This is the number of probable next words, to create a pool of words to choose from

Default: 40

temperature

number

This parameter used to control the 'warmth' or responsiveness of an AI model based on the LLaMA architecture. It adjusts how likely the model is to generate new, unexpected information versus sticking closely to what it has been trained on. A higher value for this parameter can lead to more creative and diverse responses, while a lower value results in safer, more conservative answers that are closer to those found in its training data. This parameter is particularly useful when fine-tuning models for specific tasks where you want to balance between generating novel insights and maintaining accuracy and coherence.

Default: 0.01

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

npx create-replicate --model=kcaverly/phind-codellama-34b-v2-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 kcaverly/phind-codellama-34b-v2-gguf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

const output = await replicate.run(
  "kcaverly/phind-codellama-34b-v2-gguf:5cc313d1a99986f6b903926cd493e07bfbcf8f0fd1417a234aa2ba9ba01a3e61",
  {
    input: {
      top_k: 40,
      top_p: 0.75,
      prompt: "please create a rust enum called prediction status, with three variants starting, in progress and completed. Please only include valid rust code, do not include any commentary or explanations.",
      temperature: 0.01,
      system_prompt: "You are an intelligent programming assistant.",
      max_new_tokens: -1,
      prompt_template: "### System Prompt\n{system_prompt}\n### User Message\n{prompt}\n### Assistant\n"
    }
  }
);
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 kcaverly/phind-codellama-34b-v2-gguf using Replicate’s API. Check out the model's schema for an overview of inputs and outputs.

output = replicate.run(
    "kcaverly/phind-codellama-34b-v2-gguf:5cc313d1a99986f6b903926cd493e07bfbcf8f0fd1417a234aa2ba9ba01a3e61",
    input={
        "top_k": 40,
        "top_p": 0.75,
        "prompt": "please create a rust enum called prediction status, with three variants starting, in progress and completed. Please only include valid rust code, do not include any commentary or explanations.",
        "temperature": 0.01,
        "system_prompt": "You are an intelligent programming assistant.",
        "max_new_tokens": -1,
        "prompt_template": "### System Prompt\n{system_prompt}\n### User Message\n{prompt}\n### Assistant\n"
    }
)

# The kcaverly/phind-codellama-34b-v2-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/kcaverly/phind-codellama-34b-v2-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 kcaverly/phind-codellama-34b-v2-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": "5cc313d1a99986f6b903926cd493e07bfbcf8f0fd1417a234aa2ba9ba01a3e61",
    "input": {
      "top_k": 40,
      "top_p": 0.75,
      "prompt": "please create a rust enum called prediction status, with three variants starting, in progress and completed. Please only include valid rust code, do not include any commentary or explanations.",
      "temperature": 0.01,
      "system_prompt": "You are an intelligent programming assistant.",
      "max_new_tokens": -1,
      "prompt_template": "### System Prompt\\n{system_prompt}\\n### User Message\\n{prompt}\\n### Assistant\\n"
    }
  }' \
  https://api.replicate.com/v1/predictions

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

Output

```rust pub enum PredictionStatus { Starting, InProgress, Completed, } ```

{
  "completed_at": "2023-12-13T19:00:38.806529Z",
  "created_at": "2023-12-13T18:55:55.525599Z",
  "data_removed": false,
  "error": null,
  "id": "r2kem53bnyisyzjbzt3ix7snue",
  "input": {
    "top_k": 40,
    "top_p": 0.75,
    "prompt": "please create a rust enum called prediction status, with three variants starting, in progress and completed. Please only include valid rust code, do not include any commentary or explanations.",
    "temperature": 0.01,
    "system_prompt": "You are an intelligent programming assistant.",
    "max_new_tokens": -1,
    "prompt_template": "### System Prompt\n{system_prompt}\n### User Message\n{prompt}\n### Assistant\n"
  },
  "logs": "llama_print_timings:        load time =     268.65 ms\nllama_print_timings:      sample time =       4.06 ms /    28 runs   (    0.15 ms per token,  6891.46 tokens per second)\nllama_print_timings: prompt eval time =     268.55 ms /    63 tokens (    4.26 ms per token,   234.59 tokens per second)\nllama_print_timings:        eval time =    1159.85 ms /    27 runs   (   42.96 ms per token,    23.28 tokens per second)\nllama_print_timings:       total time =    1478.76 ms",
  "metrics": {
    "predict_time": 1.494993,
    "total_time": 283.28093
  },
  "output": [
    "```",
    "rust",
    "\n",
    "pub",
    " enum",
    " Pred",
    "iction",
    "Status",
    " {",
    "\n",
    "   ",
    " Starting",
    ",",
    "\n",
    "   ",
    " In",
    "Progress",
    ",",
    "\n",
    "   ",
    " Comple",
    "ted",
    ",",
    "\n",
    "}",
    "\n",
    "```",
    ""
  ],
  "started_at": "2023-12-13T19:00:37.311536Z",
  "status": "succeeded",
  "urls": {
    "stream": "https://streaming-api.svc.us.c.replicate.net/v1/predictions/r2kem53bnyisyzjbzt3ix7snue",
    "get": "https://api.replicate.com/v1/predictions/r2kem53bnyisyzjbzt3ix7snue",
    "cancel": "https://api.replicate.com/v1/predictions/r2kem53bnyisyzjbzt3ix7snue/cancel"
  },
  "version": "5cc313d1a99986f6b903926cd493e07bfbcf8f0fd1417a234aa2ba9ba01a3e61"
}

Generated in

1.5 seconds

Tweak it Report

Run time and cost

This model costs approximately $0.18 to run on Replicate, or 5 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 L40S GPU hardware. Predictions typically complete within 4 minutes. The predict time for this model varies significantly based on the inputs.

Readme

TheBloke’s quantized version of Phind’s CodeLlama 33B V2 Instruct model in GGUF format. The full model card can be found here.

Specifically, this is the phind-codellama-34b-v2.Q5_K_M.gguf model, with a 4096 context window.