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

RasGulla1 7B by AbacusResearch

 »  All LLMs  »  AbacusResearch  »  RasGulla1 7B   URL Share it on

  87   

RasGulla1 7B is an open-source language model by AbacusResearch. Features: 7b LLM, VRAM: 14.4GB, License: mit, Merged, HF Score: 73, LLM Explorer Score: 0.13, Arc: 69.7, HellaSwag: 87.4, MMLU: 64.9, TruthfulQA: 63.3, WinoGrande: 80.9, GSM8K: 71.7.

  Merged Model   Cities   Dataset:your dataset name   En   Endpoints compatible   Finetuned   Lora   Mistral   Region:us   Safetensors   Sharded   Tensorflow   Vendor-names   Zip-codes
Model Card on HF 🤗: https://huggingface.co/AbacusResearch/RasGulla1-7b 

RasGulla1 7B Benchmarks

ARC: 69.71 vs 96.7 (so35)-27.9%
HellaSwag: 87.4 vs 95.3 (gpt4)-8.3%
MMLU: 64.94 vs 88.3 (so35)-26.5%
TruthfulQA: 63.31 vs 59 (gpt4)7.3%
WinoGrande: 80.9 vs 87.5 (gpt4)-7.5%
GSM8K: 71.72 vs 96.4 (so35)-25.6%
LLME Score: 0.13175
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
RasGulla1 7B (AbacusResearch/RasGulla1-7b)
🌟 Advertise your project 🚀

RasGulla1 7B Parameters and Internals

Model Type 
Text Classification
Use Cases 
Areas:
Commercial Applications, Research
Applications:
Vendor Data Classification
Primary Use Cases:
Vendor identification by street and zip code
Additional Notes 
This model uses only Lora weights and is specialized in identifying vendors based on street names, zip codes, and cities.
LLM NameRasGulla1 7B
Repository 🤗https://huggingface.co/AbacusResearch/RasGulla1-7b 
Merged ModelYes
Model Size7b
Required VRAM14.4 GB
Updated2026-04-09
MaintainerAbacusResearch
Model Files  0.2 GB   2.0 GB: 1-of-8   2.0 GB: 2-of-8   1.9 GB: 3-of-8   1.7 GB: 4-of-8   1.9 GB: 5-of-8   2.0 GB: 6-of-8   1.9 GB: 7-of-8   1.0 GB: 8-of-8
Supported Languagesen
Model ArchitectureAutoModelForCausalLM
Licensemit
Is Biasednone
Tokenizer ClassLlamaTokenizer
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesup_proj|down_proj|v_proj|q_proj|k_proj|gate_proj|o_proj
LoRA Alpha16
LoRA Dropout0
R Param16

Best Alternatives to RasGulla1 7B

Best Alternatives
Context / RAM
Downloads
Likes
Mistral 7B V0.332K / 14.5 GB12535
Mistral 7B Instruct V0.332K / 14.5 GB395
...unoichi Lemon Royale V3 32K 7B32K / 14.5 GB25
Mistral 7B Instruct V0.332K / 14.5 GB5133
Mistralai Mistral 7B V0.332K / 14.5 GB133
...ralai Mistral 7B Instruct V0.332K / 14.5 GB73
Mistral 7B Instruct V0.332K / 14.5 GB50
Mistral 7B V0.232K / 14.5 GB5661
Full V4 Astromistral Final32K / 4.5 GB11
LlamaGuard 7B4K / 13.5 GB4073239
Note: green Score (e.g. "73.2") means that the model is better than AbacusResearch/RasGulla1-7b.

Rank the RasGulla1 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? 52758 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.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer