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 7B Chat Hf Function Calling by Trelis

 »  All LLMs  »  Trelis  »  Llama 2 7B Chat Hf Function Calling   URL Share it on

  17   
  Arxiv:2307.09288   Autotrain compatible   En   Facebook   Function calling   Functions   Ggml   Gptq   Llama   Llama2   Meta   Pytorch   Quantized   Region:us   Sharded
Model Card on HF 🤗: https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling 

Llama 2 7B Chat Hf Function Calling Benchmarks

LLME Score: 0.10372
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 7B Chat Hf Function Calling (Trelis/Llama-2-7b-chat-hf-function-calling)
🌟 Advertise your project 🚀

Llama 2 7B Chat Hf Function Calling Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
commercial, research
Applications:
assistant-like chat, natural language generation tasks
Primary Use Cases:
dialogue applications, function calling using structured JSON
Limitations:
May produce inaccurate or biased responses, Evaluation primarily in English
Considerations:
Developers should perform safety testing and tuning tailored to specific applications of the model.
Additional Notes 
GPTQ-trained models offer fast and reliable performance with adapters.
Supported Languages 
English (Primary language for training and evaluation.)
Training Details 
Data Sources:
Publicly available online data, Publicly available instruction datasets
Data Volume:
2 trillion tokens
Methodology:
fine-tuning using GPTQ and reinforcement learning with human feedback (RLHF)
Context Length:
4000
Training Time:
January 2023 to July 2023
Hardware Used:
A100-80GB GPUs with TDP of 350-400W
Model Architecture:
Transformer
Safety Evaluation 
Methodologies:
Internal safety evaluations, Testing on TruthfulQA and Toxigen benchmarks
Findings:
Llama-2-Chat models produced 0 percent toxic generations in Toxigen evaluations
Risk Categories:
misinformation, bias
Ethical Considerations:
Developers should perform safety testing tailored to specific applications.
Responsible Ai Considerations 
Fairness:
Not specified
Transparency:
Model responses might not cover all scenarios in English.
Accountability:
Developers are responsible for safety testing and tuning.
Mitigation Strategies:
Fine-tuning with reinforcement learning and human feedback
Input Output 
Input Format:
Structured input with INST and JSON function call formats.
Accepted Modalities:
text
Output Format:
JSON object with function name and arguments.
Performance Tips:
Use GPU for fast and accurate inference.
Release Notes 
Version:
2
Date:
Recently released
Notes:
Includes function calling capabilities.
LLM NameLlama 2 7B Chat Hf Function Calling
Repository 🤗https://huggingface.co/Trelis/Llama-2-7b-chat-hf-function-calling 
Base Model(s)  ...7B Chat Hf Function Calling V3   Trelis/Llama-2-7b-chat-hf-function-calling-v3
Model Size7b
Required VRAM13.5 GB
Updated2025-08-19
MaintainerTrelis
Model Typellama
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   3.6 GB: 3-of-3
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Llama 2 7B Chat Hf Function Calling

Best Alternatives
Context / RAM
Downloads
Likes
Yarn Llama 2 7B 128K GPTQ128K / 3.9 GB117
Yarn Llama 2 7B 64K GPTQ64K / 3.9 GB71
... 7B 32K Instructions V4 Marlin32K / 4.1 GB80
Aixcoder 7B GPTQ32K / 4.5 GB51
Calm2 7B Chat GPTQ32K / 4.4 GB85
...Calm2 7B Chat GPTQ Calib Ja 1K32K / 4.4 GB85
Llama 2 7B 32K Instruct GPTQ32K / 3.9 GB927
Codebear 7B 4bit16K / 3.9 GB31
CodeLlama 7B Instruct GPTQ16K / 3.9 GB228046
...a 7B Instruct GPTQ Calib Ja 1K16K / 3.9 GB70
Note: green Score (e.g. "73.2") means that the model is better than Trelis/Llama-2-7b-chat-hf-function-calling.

Rank the Llama 2 7B Chat Hf Function Calling 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? 50751 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