NewJoin us for our inaugural conference, Forge 2026
DocsLog inGet started
Phind logo

Phind CodeLlama 34B Python v1

Ready
model path:accounts/fireworks/models/phind-code-llama-34b-python-v1
Deploy on demand

Phind CodeLlama 34B Python V1 is a fine-tuned version of the CodeLlama 34B Python LLM using an internal Phind dataset that achieved 69.5% pass@1 on HumanEval, beating GPT-4.

Phind CodeLlama 34B Python v1 API Features

On-demand Deployment

Docs

On-demand deployments allow you to use Phind CodeLlama 34B Python v1 on dedicated GPUs with Fireworks' high-performance serving stack with high reliability and no rate limits.

Metadata

State
Ready
Created on
2 MAR, 2024
Kind
Base model
Provider
Phind
Huggingface
Phind/Phind-CodeLlama-34B-Python-v1

Specifications

Calibrated
No
Mixture-of-Experts
No
Parameters
33.7B

Supporting Functionality

Fine-tuning
Not Supported
Serverless
Not Supported
Context Length
16.3k tokens
Function Calling
Not Supported
Embeddings
Not Supported
Rerankers
Not Supported
Supporting image input
Not Supported