Llama 2 70B GGML by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Llama 2 70B GGML   URL Share it on

  Arxiv:2307.09288   En   Facebook   Ggml   Llama   Llama2   Meta   Pytorch   Quantized   Region:us

Llama 2 70B GGML Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Llama 2 70B GGML Parameters and Internals

Model Type
text generation
Use Cases
Areas:
Commercial, Research
Applications:
Assistant-like chat with tuned models, Natural language generation
Primary Use Cases:
Text generation for dialogue and other natural language tasks
Limitations:
Limited to English, Not suitable for use that violates applicable laws or regulations
Considerations:Formatting needs to be followed for chat versions, including specific tokens and whitespace.
Additional NotesFoundation model with potential for further fine-tuning, especially for dialogue use cases.
Supported Languages
en (English)
Training Details
Data Sources:
A new mix of publicly available online data
Data Volume:2 trillion tokens
Methodology:Pretrained and fine-tuned, using supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF)
Context Length:4000
Training Time:January 2023 to July 2023
Hardware Used:
Meta's Research Super Cluster and production clusters
Model Architecture:Optimized transformer architecture with Grouped-Query Attention (GQA) for improved inference scalability.
Safety Evaluation
Methodologies:
Internal evaluations using academic benchmarks
Findings:
May produce inaccurate, biased, or objectionable responses in certain scenarios
Risk Categories:
Misinformation, Bias
Ethical Considerations:The model carries risks with use; outputs cannot be predicted in advance.
Responsible Ai Considerations
Fairness:Uncertain; developers should perform safety testing and tuning tailored to their specific applications.
Transparency:The model's potential outputs cannot be predicted in advance.
Accountability:Meta is responsible for the initial deployment, but users must ensure safe application.
Mitigation Strategies:Perform safety testing and tuning tailored to specific applications.
Input Output
Input Format:text
Accepted Modalities:
text
Output Format:text
Performance Tips:Adhere to specified input formatting for chat models.
Release Notes
Version:70B
Date:2023-07-01
Notes:70 billion parameters for varied natural language generation tasks.
LLM NameLlama 2 70B GGML
Repository ๐Ÿค—https://huggingface.co/TheBloke/Llama-2-70B-GGML 
Model Size70b
Required VRAM28.6 GB
Updated2024-11-12
MaintainerTheBloke
Model Typellama
Model Files  28.6 GB   36.1 GB   33.0 GB   29.7 GB   38.9 GB   43.2 GB   41.4 GB   38.9 GB   47.5 GB   48.8 GB   47.5 GB
Supported Languagesen
GGML QuantizationYes
Quantization Typeggml
Model ArchitectureAutoModel
Licenseother
Llama 2 70B GGML (TheBloke/Llama-2-70B-GGML)

Best Alternatives to Llama 2 70B GGML

Best Alternatives
Context / RAM
Downloads
Likes
Llama 2 70B Chat GGML0K / 28.6 GB85161
Synthia 70B V1.1 GGML0K / 28.6 GB324
...iction.live Kimiko V2 70B GGML0K / 28.6 GB222
Lemur 70B Chat V1 GGML0K / 29 GB263
...boros L2 70B 2.1 Creative GGML0K / 28.6 GB23
Nous Hermes Llama2 70B GGML0K / 29 GB1712
Model 007 70B GGML0K / 28.6 GB121
Llama2 70B OASST SFT V10 GGML0K / 29 GB294
Llama 2 70B Orca 200K GGML0K / 28.6 GB243
Synthia 70B GGML0K / 28.6 GB282
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Llama-2-70B-GGML.

Rank the Llama 2 70B GGML Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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? 37901 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241110