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

Merlinite 7B by ibm

 »  All LLMs  »  ibm  »  Merlinite 7B   URL Share it on

  10925   
  Arxiv:2403.01081   Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mistral-7...   En   Endpoints compatible   Ibm   Lab   Labrador   Labradorite   Merlinite   Mistral   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ibm/merlinite-7b 

Merlinite 7B Benchmarks

MMLU Pro: 22.98
GPQA: 6.26
MUSR: 13.88
BBH: 29.98
IFEval: 24.99 vs 88 (so35)-71.6%
ARC: 63.65 vs 96.7 (so35)-34.2%
HellaSwag: 84.52 vs 95.3 (gpt4)-11.3%
MMLU: 64.91 vs 88.3 (so35)-26.5%
TruthfulQA: 50.15 vs 59 (gpt4)-15%
WinoGrande: 79.72 vs 87.5 (gpt4)-8.9%
GSM8K: 41.09 vs 96.4 (so35)-57.4%
MATH Lvl 5: 2.49
LLME Score: 0.31343
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Merlinite 7B (ibm/merlinite-7b)

Merlinite 7B Parameters and Internals

Model Type 
text-generation
Additional Notes 
Merlinite-7b is a Mistral-7b-derivative model developed by IBM with a methodology called LAB.
Supported Languages 
en (Primarily English)
Training Details 
Methodology:
LAB (Large-scale Alignment for chatBots) using a taxonomy-driven data curation process and large-scale synthetic data generator.
LLM NameMerlinite 7B
Repository 🤗https://huggingface.co/ibm/merlinite-7b 
Base Model(s)  mistralai/Mistral-7B-v0.1   mistralai/Mistral-7B-v0.1
Model Size7b
Required VRAM14.4 GB
Updated2024-12-22
Maintaineribm
Model Typemistral
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
Supported Languagesen
Model ArchitectureMistralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.1
Tokenizer ClassLlamaTokenizer
Padding Token<|pad|>
Vocabulary Size32008
Torch Data Typebfloat16

Quantized Models of the Merlinite 7B

Model
Likes
Downloads
VRAM
Merlinite 7B GGUF51362 GB

Best Alternatives to Merlinite 7B

Best Alternatives
Context / RAM
Downloads
Likes
...Nemo Instruct 2407 Abliterated1000K / 24.5 GB26689
MegaBeam Mistral 7B 512K512K / 14.4 GB711346
SpydazWeb AI HumanAI RP512K / 14.4 GB261
SpydazWeb AI HumanAI 002512K / 14.4 GB191
...daz Web AI ChatML 512K Project512K / 14.5 GB120
MegaBeam Mistral 7B 300K282K / 14.4 GB328215
Hebrew Mistral 7B 200K256K / 30 GB319315
Astral 256K 7B V2250K / 14.4 GB190
Astral 256K 7B250K / 14.4 GB160
Boptruth Agatha 7B128K / 14.4 GB4750
Note: green Score (e.g. "73.2") means that the model is better than ibm/merlinite-7b.

Rank the Merlinite 7B 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? 40123 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 v20241217
  Support LLM Explorer