You can deploy this model and start earning money today!

Festi/
festi-coder-full-2025-06

Name: festi-coder-full-2025-06
Availability: InStock

deepseek-ai/deepseek-coder-6.7b-instruct

finetune

apache-2.0

Views

No views yet

Festi Coder Full 2025-06

This is a fully fine-tuned version of deepseek-ai/deepseek-coder-6.7b-instruct, built by Festi to support advanced backend development on the Festi Framework. The model is trained on real-world Festi codebases and supports tasks like plugin generation, trait and service scaffolding, and backend automation.

Model Details

Model Description

Developed by: Festi
Model type: Causal Language Model (full fine-tune)
Base model: deepseek-ai/deepseek-coder-6.7b-instruct
Language(s): English, PHP (Festi syntax)
License: Apache-2.0
Fine-tuned with: Transformers (no LoRA)

Uses

Direct Use

This model is intended for developers working in the Festi ecosystem who want to:

Generate Festi plugins, services, CLI commands, and traits
Edit and extend existing Festi modules
Explain and document PHP code following Festi patterns

Out-of-Scope Use

Natural language chat or general NLP tasks
Use with non-Festi PHP frameworks (e.g., Laravel, Symfony)
Autonomous execution without human validation

Bias, Risks, and Limitations

This is a domain-specific model, not suitable for general-purpose programming. The code generated may contain syntactic or semantic issues and should be reviewed by experienced developers before use in production.

Recommendations

Validate model output before use
Use only in backend contexts aligned with Festi's architecture
Do not expose model output to end-users directly

How to Get Started with the Model

python

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

model_id = "Festi/festi-coder-full-2025-06"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

generator = pipeline("text-generation", model=model, tokenizer=tokenizer)

prompt = "<|user|>\nCreate a plugin to subscribe users via email.\n<|assistant|>\n"
output = generator(prompt, max_new_tokens=300)
print(output[0]["generated_text"])