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

Raccoon Small by rizla

 »  All LLMs  »  rizla  »  Raccoon Small   URL Share it on

  86   
  Autotrain compatible Base model:finetune:mistralai/... Base model:mistralai/mixtral-8...   Dpo   Endpoints compatible   Instruct   Mixtral   Moe   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/rizla/raccoon-small 

Raccoon Small Benchmarks

ARC: 74.4 vs 96.7 (so35)-23.1%
HellaSwag: 88.73 vs 95.3 (gpt4)-6.9%
MMLU: 64.55 vs 88.3 (so35)-26.9%
TruthfulQA: 76.74 vs 59 (gpt4)30.1%
WinoGrande: 87.37 vs 87.5 (gpt4)-0.1%
GSM8K: 56.86 vs 96.4 (so35)-41%
LLME Score: 0.18189
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Raccoon Small (rizla/raccoon-small)

Raccoon Small Parameters and Internals

Model Type 
language model
Additional Notes 
Made specifically as part of an experimental merging process using the mergekitty tool.
Training Details 
Methodology:
Merged using mergekitty tool; Based on GPT-4 architecture.
Model Architecture:
Combination of two 2expmixtrals into a singular model via merging.
LLM NameRaccoon Small
Repository 🤗https://huggingface.co/rizla/raccoon-small 
Base Model(s)  mistralai/Mixtral-8x7B-Instruct-v0.1   mistralai/Mixtral-8x7B-Instruct-v0.1
Model Size19.2b
Required VRAM38.4 GB
Updated2024-12-14
Maintainerrizla
Model Typemixtral
Instruction-BasedYes
Model Files  10.0 GB: 1-of-4   10.0 GB: 2-of-4   9.9 GB: 3-of-4   8.5 GB: 4-of-4
Model ArchitectureMixtralForCausalLM
Licensecc-by-nc-4.0
Context Length32768
Model Max Length32768
Transformers Version4.37.2
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to Raccoon Small

Best Alternatives
Context / RAM
Downloads
Likes
...oundary Solar Chat 2x10.7B MoE4K / 38 GB1231
SOLAR Math 2x10.7B V0.24K / 38.4 GB12153
...ixtral 8x22B Instruct V0.1 AWQ64K / 73.7 GB13610
... 8x22B Instruct V0.1 GPTQ 4bit64K / 74.1 GB1771
Note: green Score (e.g. "73.2") means that the model is better than rizla/raccoon-small.

Rank the Raccoon Small 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? 39237 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