phind-codellama:latest

85.4K 1 year ago

Code generation model based on Code Llama.

34b

1 year ago

566e1b629c44 · 19GB

model
llama
·
33.7B
·
Q4_0
license
LLAMA 2 COMMUNITY LICENSE AGREEMENT Llama 2 Version Release Date: July 18, 2023 "Agreement" means
system
You are an intelligent programming assistant.
params
{ "stop": [ "### System Prompt:", "### User Message:", "### Assistant:"
template
{{- if .System }} ### System Prompt {{ .System }} {{- end }} ### User Message {{ .Prompt }} ### As

Readme

Phind CodeLlama is a code generation model based on CodeLlama 34B fine-tuned for instruct use cases. There are two versions of the model: v1 and v2. v1 is based on CodeLlama 34B and CodeLlama-Python 34B. v2 is an iteration on v1, trained on an additional 1.5B tokens of high-quality programming-related data.

Usage

CLI

Open the terminal and run ollama run phind-codellama

API

Example

curl -X POST http://localhost:11434/api/generate -d '{
  "model": "phind-codellama",
  "prompt":"Implement a linked list in C++"
 }'

Memory requirements

  • 34b models generally require at least 32GB of RAM

References

Beating GPT-4 on HumanEval with a Fine-Tuned CodeLlama-34B

HuggingFace