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

CodeLlama 13B Oasst Sft V10 GGML by TheBloke

 »  All LLMs  »  TheBloke  »  CodeLlama 13B Oasst Sft V10 GGML   URL Share it on

  9   
Base model:finetune:openassist... Base model:openassistant/codel...   Codegen   Dataset:openassistant/oasst1   Dataset:shahules786/orca-best   En   Ggml   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/TheBloke/CodeLlama-13B-oasst-sft-v10-GGML 

CodeLlama 13B Oasst Sft V10 GGML Benchmarks

LLME Score: 0.12757
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
CodeLlama 13B Oasst Sft V10 GGML (TheBloke/CodeLlama-13B-oasst-sft-v10-GGML)

CodeLlama 13B Oasst Sft V10 GGML Parameters and Internals

Model Type 
Causal decoder-only transformer
Use Cases 
Limitations:
Potential for inaccurate, biased, or objectionable responses.
Considerations:
Perform safety testing and tuning before deploying.
Supported Languages 
English (High)
Training Details 
Data Sources:
orca-best, OpenAssistant/oasst1
Methodology:
Finetuning with special training methods, using ChatML as the prompt format.
Model Architecture:
Causal decoder-only transformer language model
Responsible Ai Considerations 
Fairness:
Testing conducted primarily in English, outputs may not be predictable in advance and can potentially be biased.
Accountability:
Developers are responsible for performing safety testing and tuning for specific applications.
Mitigation Strategies:
Developers should follow Meta's Responsible Use Guide.
Input Output 
Input Format:
ChatML format with system messages and conversation turns.
Accepted Modalities:
text
LLM NameCodeLlama 13B Oasst Sft V10 GGML
Repository 🤗https://huggingface.co/TheBloke/CodeLlama-13B-oasst-sft-v10-GGML 
Model NameCodeLlama 13B SFT v10
Model CreatorOpenAssistant
Base Model(s)  Codellama 13B Oasst Sft V10   OpenAssistant/codellama-13b-oasst-sft-v10
Model Size13b
Required VRAM5.7 GB
Updated2025-02-05
MaintainerTheBloke
Model Typellama
Model Files  5.7 GB   7.1 GB   6.5 GB   5.9 GB   7.3 GB   8.1 GB   8.1 GB   7.6 GB   8.9 GB   9.8 GB   9.4 GB   9.2 GB   10.8 GB   13.8 GB
Supported Languagesen
GGML QuantizationYes
Quantization Typeggml
Generates CodeYes
Model ArchitectureAutoModel
Licensellama2

Best Alternatives to CodeLlama 13B Oasst Sft V10 GGML

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 13B GGML0K / 5.7 GB1433
CodeLlama 13B Python GGML0K / 5.5 GB1818
CodeLlama 13B Instruct GGML0K / 5.7 GB719
Codellama 7B Instruct GGUF0K / 2.8 GB1000
Codellama 13B Instruct GGUF0K / 13.8 GB50
CodeLlama 13B Instruct GGUF0K / 5.4 GB5127119
CodeLlama 13B GGUF0K / 5.4 GB538860
CodeLlama 13B Python GGUF0K / 5.4 GB154133
...deLlama 13B Oasst Sft V10 GGUF0K / 5.4 GB97614
MAmmoTH Coder 13B GGUF0K / 5.4 GB1334
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/CodeLlama-13B-oasst-sft-v10-GGML.

Rank the CodeLlama 13B Oasst Sft V10 GGML 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? 42577 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.
Release v20241227
  Support LLM Explorer