XLAM 7B R by Salesforce

 ยป  All LLMs  ยป  Salesforce  ยป  XLAM 7B R   URL Share it on

  Arxiv:2402.15506   Arxiv:2406.18518   Arxiv:2409.03215   Arxiv:2503.22673   Autotrain compatible   Conversational Dataset:salesforce/xlam-functi...   En   Endpoints compatible   Function-calling   Instruct   Llm agent   Mistral   Pytorch   Region:us   Safetensors   Sharded   Tensorflow   Tool-use
Model Card on HF ๐Ÿค—: https://huggingface.co/Salesforce/xLAM-7b-r 

XLAM 7B R Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
XLAM 7B R (Salesforce/xLAM-7b-r)

XLAM 7B R Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research
Additional Notes 
The model is exclusively released for research purposes and is expected to have enhanced versions available commercially in the future.
Supported Languages 
en (Proficient)
Input Output 
Input Format:
Specific prompt structures for function calling.
Accepted Modalities:
text
Output Format:
JSON with function call specifications.
Performance Tips:
Use provided prompt format for optimal function-calling performance.
LLM NameXLAM 7B R
Repository ๐Ÿค—https://huggingface.co/Salesforce/xLAM-7b-r 
Model Size7b
Required VRAM14.4 GB
Updated2025-05-14
MaintainerSalesforce
Model Typemistral
Instruction-BasedYes
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.42.3
Tokenizer ClassLlamaTokenizer
Padding Token[PAD]
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to XLAM 7B R

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB215715
SpydazWeb AI HumanAI RP512K / 14.4 GB51
SpydazWeb AI HumanAI 002512K / 14.4 GB181
...daz Web AI ChatML 512K Project512K / 14.5 GB120
... Summarize 64K QLoRANET Merged128K / 4.1 GB160
...1 Summarize 64K LoRANET Merged128K / 14.4 GB50
Mistral 7B Instruct V0.232K / 14.4 GB33160952630
Mistral 7B Instruct V0.132K / 14.4 GB5207211677
Mixtral AI CyberCoder32K / 14.3 GB00
...ity Instruct 7M Gen Mistral 7B32K / 14.4 GB11435
Note: green Score (e.g. "73.2") means that the model is better than Salesforce/xLAM-7b-r.

Rank the XLAM 7B R 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? 47368 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227