LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Diff Codegen 350M V2 by CarperAI

 »  All LLMs  »  CarperAI  »  Diff Codegen 350M V2   URL Share it on

  14   

Diff Codegen 350M V2 is an open-source language model by CarperAI. Features: 350m LLM, VRAM: 0.8GB, License: mit, Code Generating, LLM Explorer Score: 0.06.

  Arxiv:2101.00027   Arxiv:2201.07311   Arxiv:2203.13474   Autotrain compatible   Code   Code-generation   Codegen   Diff model   En   Endpoints compatible   Pytorch   Region:us   The pile
Model Card on HF 🤗: https://huggingface.co/CarperAI/diff-codegen-350m-v2 

Diff Codegen 350M V2 Benchmarks

LLME Score: 0.0559
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Diff Codegen 350M V2 (CarperAI/diff-codegen-350m-v2)
🌟 Advertise your project 🚀

Diff Codegen 350M V2 Parameters and Internals

Model Type 
pytorch, causal-lm, code-generation
Use Cases 
Areas:
Research, Experimental Use
Applications:
Prototyping Code Generation Systems
Limitations:
Underrepresentation of programming languages with fewer than 100 stars, Short context length
Considerations:
Outputs should not be trusted as correct and secure. Use in a sandboxed environment.
Additional Notes 
This is an experimental research artifact and should be treated as such.
Training Details 
Data Sources:
The Pile, GitHub commits from BigQuery Public Dataset
Data Volume:
1.08 billion tokens
Methodology:
Fine-tuning technique used
Context Length:
2048
Hardware Used:
64 A100 GPUs
LLM NameDiff Codegen 350M V2
Repository 🤗https://huggingface.co/CarperAI/diff-codegen-350m-v2 
Model Size350m
Required VRAM0.8 GB
Updated2025-11-02
MaintainerCarperAI
Model Typecodegen
Model Files  0.8 GB
Supported Languagesen code
Generates CodeYes
Model ArchitectureCodeGenForCausalLM
Licensemit
Model Max Length2048
Transformers Version4.22.0.dev0
Tokenizer ClassGPT2Tokenizer
Vocabulary Size50295
Torch Data Typefloat16
Activation Functiongelu_new

Best Alternatives to Diff Codegen 350M V2

Best Alternatives
Context / RAM
Downloads
Likes
Ft Calculator0K / 0.6 GB50
...o Python 18K Alpaca Runpod.net0K / 0.7 GB11
...hs Finetuned Python 18K Alpaca0K / 0.8 GB50
...no Finetuned Python 18K Alpaca0K / 0.8 GB21
... Powershell Codegen 350M Multi0K / 1.4 GB111
Codegen 350M Mono Java Merged0K / 1.5 GB60
...en 350M Mono 18K Alpaca Python0K / 0.7 GB62
Nsql 350M0K / 1.5 GB52233
...om Functions Dataset Python V20K / 1.5 GB7942
Codegen 350M Mono0K /  GB1406
Note: green Score (e.g. "73.2") means that the model is better than CarperAI/diff-codegen-350m-v2.

Rank the Diff Codegen 350M V2 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

Instruction Following and Task Automation  
Factuality and Completeness of Knowledge  
Censorship and Alignment  
Data Analysis and Insight Generation  
Text Generation  
Text Summarization and Feature Extraction  
Code Generation  
Multi-Language Support and Translation  

What open-source LLMs or SLMs are you in search of? 52392 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer