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

Llama 2 13B Chat Hf Fp8 by FriendliAI

 »  All LLMs  »  FriendliAI  »  Llama 2 13B Chat Hf Fp8   URL Share it on

  15   
  Arxiv:2307.09288   8-bit   Autotrain compatible Base model:finetune:meta-llama... Base model:meta-llama/llama-2-...   Conversational   En   Facebook   Llama   Llama2   Meta   Pytorch   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/FriendliAI/Llama-2-13b-chat-hf-fp8 

Llama 2 13B Chat Hf Fp8 Benchmarks

LLME Score: 0.15043
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 13B Chat Hf Fp8 (FriendliAI/Llama-2-13b-chat-hf-fp8)
🌟 Advertise your project 🚀

Llama 2 13B Chat Hf Fp8 Parameters and Internals

Model Type 
llama, text-generation
Use Cases 
Areas:
commercial, research use
Applications:
assistant-like chat, natural language generation tasks
Primary Use Cases:
chat models
Limitations:
Use only in English, Must not violate applicable laws or regulations
Considerations:
Specific formatting needed for chat versions to get expected features and performance
Additional Notes 
The model is optimized for dialogue use cases and operates best under specific conditions and hardware.
Supported Languages 
en (high)
Training Details 
Data Sources:
publicly available online data
Data Volume:
2 trillion tokens
Methodology:
supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF)
Training Time:
January 2023 to July 2023
Hardware Used:
Meta's Research Super Cluster and production clusters, Third-party cloud compute
Model Architecture:
auto-regressive language model using an optimized transformer architecture
Safety Evaluation 
Methodologies:
internal evaluations library
Findings:
Llama-2-Chat models outperform open-source chat models on most benchmarks, performance is on par with some popular closed-source models like ChatGPT and PaLM
Risk Categories:
inaccuracy, bias
Ethical Considerations:
use responsibly with safety testing and tuning for specific applications
Responsible Ai Considerations 
Transparency:
Model details and evaluation results are provided publicly.
Accountability:
Meta is accountable for the model's outputs.
Mitigation Strategies:
Safety tests and responsible use guidelines are recommended for developers.
Input Output 
Input Format:
text only
Accepted Modalities:
text
Output Format:
text only
Performance Tips:
For chat use, follow specific input formatting guidelines including `INST`, `<BOS>`, and `<EOS>` tags.
LLM NameLlama 2 13B Chat Hf Fp8
Repository 🤗https://huggingface.co/FriendliAI/Llama-2-13b-chat-hf-fp8 
Model NameLlama 2 13B Chat
Model CreatorMeta Llama 2
Base Model(s)  Llama 2 13B Chat Hf   meta-llama/Llama-2-13b-chat-hf
Model Size13b
Required VRAM13.3 GB
Updated2025-08-20
MaintainerFriendliAI
Model Typellama
Model Files  13.3 GB
Supported Languagesen
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.39.1
Tokenizer ClassLlamaTokenizer
Padding Token</s>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the Llama 2 13B Chat Hf Fp8

Model
Likes
Downloads
VRAM
Llama 2 13B Chat Fp16733426 GB

Best Alternatives to Llama 2 13B Chat Hf Fp8

Best Alternatives
Context / RAM
Downloads
Likes
Luminaura RP 13B128K / 26 GB60
Yarn Llama 2 13B 128K128K / 26 GB42112
Agent Llama2 13B 80K80K / 26.4 GB50
Chat Llama2 13B 80K80K / 52.8 GB60
LongAlign 13B 64K64K / 26 GB1613
LongAlign 13B 64K64K / 26 GB1113
LongAlign 13B 64K Base64K / 26 GB163
LongAlign 13B 64K Base64K / 26 GB63
Openbuddy Llama2 13B V15p1 64K64K / 26.1 GB44
Openbuddy Llama2 13b64k V1564K / 26.1 GB72
Note: green Score (e.g. "73.2") means that the model is better than FriendliAI/Llama-2-13b-chat-hf-fp8.

Rank the Llama 2 13B Chat Hf Fp8 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? 50767 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