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

Llama2 70B OASST SFT V10 GGML by TheBloke

 »  All LLMs  »  TheBloke  »  Llama2 70B OASST SFT V10 GGML   URL Share it on

  8   
Base model:finetune:openassist... Base model:openassistant/llama... Dataset:argilla/databricks-dol...   Dataset:openassistant/oasst1 Dataset:rombodawg/losslessmega...   Dataset:shahules786/orca-best   En   Ggml   Llama   Quantized   Region:us   Sft
Model Card on HF 🤗: https://huggingface.co/TheBloke/Llama2-70B-OASST-SFT-v10-GGML 

Llama2 70B OASST SFT V10 GGML Benchmarks

LLME Score: 0.10222
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama2 70B OASST SFT V10 GGML (TheBloke/Llama2-70B-OASST-SFT-v10-GGML)
🌟 Advertise your project 🚀

Llama2 70B OASST SFT V10 GGML Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
Research, General AI applications
Limitations:
Potential for producing inaccurate, biased, or other objectionable responses., Testing primarily conducted in English., Limited testing in other languages.
Additional Notes 
Uses quantized formats (e.g., GGML) for varied inference settings.
Supported Languages 
English (full support), German (limited), Spanish (limited), French (limited), Italian (limited), Portuguese (limited), Polish (limited), Dutch (limited), Romanian (limited), Czech (limited), Swedish (limited)
Training Details 
Data Sources:
rombodawg/LosslessMegaCodeTrainingV2_1m_Evol_Uncensored, OpenAssistant/oasst1, shahules786/orca-best, argilla/databricks-dolly-15k-curated-multilingual
Methodology:
Fine-tuned in two stages: first on synthetic instructions/coding tasks, then on top human demonstrations.
Context Length:
4096
Model Architecture:
Causal decoder-only transformer
Responsible Ai Considerations 
Fairness:
Testing conducted primarily in English with limited testing in other languages. Limited coverage of all scenarios.
Mitigation Strategies:
Developers should perform safety testing tailored to specific use cases.
Input Output 
Input Format:
Uses OpenAI's chatml standard prompt format
Accepted Modalities:
text
Performance Tips:
For GPU offloading, consider VRAM capacity.
LLM NameLlama2 70B OASST SFT V10 GGML
Repository 🤗https://huggingface.co/TheBloke/Llama2-70B-OASST-SFT-v10-GGML 
Model NameLlama2 70B SFT v10
Model CreatorOpenAssistant
Base Model(s)  Llama2 70B Oasst Sft V10   OpenAssistant/llama2-70b-oasst-sft-v10
Model Size70b
Required VRAM29 GB
Updated2025-10-26
MaintainerTheBloke
Model Typellama
Model Files  29.0 GB   36.5 GB   33.4 GB   30.1 GB   38.8 GB   43.1 GB   41.7 GB   39.2 GB   47.4 GB   49.0 GB   47.7 GB
Supported Languagesen
GGML QuantizationYes
Quantization Typeggml
Model ArchitectureAutoModel
Licensellama2

Best Alternatives to Llama2 70B OASST SFT V10 GGML

Best Alternatives
Context / RAM
Downloads
Likes
Llama 2 70B Chat GGML0K / 28.6 GB21161
Synthia 70B V1.1 GGML0K / 28.6 GB64
...boros L2 70B 2.1 Creative GGML0K / 28.6 GB53
...iction.live Kimiko V2 70B GGML0K / 28.6 GB62
Lemur 70B Chat V1 GGML0K / 29 GB53
Model 007 70B GGML0K / 28.6 GB61
Nous Hermes Llama2 70B GGML0K / 29 GB312
Airoboros L2 70B 2.1 GGML0K / 28.6 GB102
Llama 2 70B Orca 200K GGML0K / 28.6 GB123
Genz 70B GGML0K / 28.6 GB93
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Llama2-70B-OASST-SFT-v10-GGML.

Rank the Llama2 70B 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? 51545 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 v20241124
  Support LLM Explorer