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

Fin Llama 33B Merged by bavest

 »  All LLMs  »  bavest  »  Fin Llama 33B Merged   URL Share it on

  1414   

Fin Llama 33B Merged is an open-source language model by bavest. Features: 33b LLM, VRAM: 65.2GB, Context: 2K, License: gpl, HF Score: 59.3, LLM Explorer Score: 0.11, Arc: 65, HellaSwag: 86.2, MMLU: 58.7, TruthfulQA: 49.8, WinoGrande: 80, GSM8K: 16.2.

Dataset:bavest/fin-llama-datas...   Deploy:azure   Endpoints compatible   Finance   Llama   Pytorch   Region:us   Sharded   Trading
Model Card on HF 🤗: https://huggingface.co/bavest/fin-llama-33b-merged 

Fin Llama 33B Merged Benchmarks

ARC: 65.02 vs 96.7 (so35)-32.8%
HellaSwag: 86.2 vs 95.3 (gpt4)-9.5%
MMLU: 58.73 vs 88.3 (so35)-33.5%
TruthfulQA: 49.75 vs 59 (gpt4)-15.7%
WinoGrande: 80.03 vs 87.5 (gpt4)-8.5%
GSM8K: 16.22 vs 96.4 (so35)-83.2%
LLME Score: 0.11088
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Fin Llama 33B Merged (bavest/fin-llama-33b-merged)
🌟 Advertise your project 🚀

Fin Llama 33B Merged Parameters and Internals

Model Type 
finance, llm, llama, trading
Use Cases 
Areas:
finance
Limitations:
4-bit inference is slow, Instabilities using 'fp16' compute type, Tokenizer.bos_token_id must be 1
Additional Notes 
Acknowledgement to Meta for LLaMA models, builds on several repos including Stanford Alpaca, QLoRA, Chinese-Guanaco, and LMSYS FastChat
Training Details 
Data Sources:
bavest/fin-llama-dataset
Methodology:
Based on QLoRA finetuning with 4-bit quantization
LLM NameFin Llama 33B Merged
Repository 🤗https://huggingface.co/bavest/fin-llama-33b-merged 
Model Size33b
Required VRAM65.2 GB
Updated2026-04-11
Maintainerbavest
Model Typellama
Model Files  9.8 GB: 1-of-7   10.0 GB: 2-of-7   9.9 GB: 3-of-7   9.9 GB: 4-of-7   9.9 GB: 5-of-7   10.0 GB: 6-of-7   5.7 GB: 7-of-7
Model ArchitectureLlamaForCausalLM
Licensegpl
Context Length2048
Model Max Length2048
Transformers Version4.29.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Quantized Models of the Fin Llama 33B Merged

Model
Likes
Downloads
VRAM
Fin Llama 33B GGUF330413 GB
Fin Llama 33B AWQ5917 GB
Fin Llama 33B GPTQ7716 GB

Best Alternatives to Fin Llama 33B Merged

Best Alternatives
Context / RAM
Downloads
Likes
...angled Llama 33M 32K Base V0.132K / 0.1 GB221
ReflectionCoder DS 33B16K / 67 GB97424
Deepseek Coder 33B Instruct16K / 66.5 GB10247566
Deepseek Wizard 33B Slerp16K / 35.3 GB100
ValidateAI 33B Slerp16K / 35.4 GB70
WhiteRabbitNeo 33B V116K / 67 GB97390
Chronos Divergence 33B16K / 65 GB3930
ValidateAI 3 33B Ties16K / 66.5 GB80
ValidateAI 2 33B AT16K / 66.5 GB50
...dy Deepseekcoder 33B V16.1 32K16K / 67.1 GB7680
Note: green Score (e.g. "73.2") means that the model is better than bavest/fin-llama-33b-merged.

Rank the Fin Llama 33B Merged 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? 52721 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