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

Caigun Lora Model 34B V3 by APMIC

 »  All LLMs  »  APMIC  »  Caigun Lora Model 34B V3   URL Share it on

  802   

Caigun Lora Model 34B V3 is an open-source language model by APMIC. Features: 34b LLM, VRAM: 68.7GB, Context: 4K, License: cc-by-nc-nd-4.0, HF Score: 70.3, LLM Explorer Score: 0.13, Arc: 66.9, HellaSwag: 84.8, MMLU: 75.4, TruthfulQA: 56.5, WinoGrande: 83.6, GSM8K: 54.5.

  Endpoints compatible   Llama   Lora   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/APMIC/caigun-lora-model-34B-v3 

Caigun Lora Model 34B V3 Benchmarks

ARC: 66.89 vs 96.7 (so35)-30.8%
HellaSwag: 84.77 vs 95.3 (gpt4)-11%
MMLU: 75.41 vs 88.3 (so35)-14.6%
TruthfulQA: 56.47 vs 59 (gpt4)-4.3%
WinoGrande: 83.58 vs 87.5 (gpt4)-4.5%
GSM8K: 54.51 vs 96.4 (so35)-43.5%
LLME Score: 0.13067
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Caigun Lora Model 34B V3 (APMIC/caigun-lora-model-34B-v3)
🌟 Advertise your project 🚀

Caigun Lora Model 34B V3 Parameters and Internals

Use Cases 
Considerations:
It's important to consider ethical implications related to the use of our model.
Training Details 
Data Sources:
Orca style dataset
Model Architecture:
LLaMA architecture
Release Notes 
Version:
1.0
Date:
2023-12-21
Notes:
Finetuned on fake news detection.
Version:
2.0
Notes:
Finetuned on Orca style dataset.
Version:
3.0
Notes:
Utilized new optimizer.
LLM NameCaigun Lora Model 34B V3
Repository 🤗https://huggingface.co/APMIC/caigun-lora-model-34B-v3 
Model Size34b
Required VRAM68.7 GB
Updated2026-02-03
MaintainerAPMIC
Model Typellama
Model Files  7.8 GB: 1-of-9   7.8 GB: 2-of-9   7.8 GB: 3-of-9   7.8 GB: 4-of-9   7.8 GB: 5-of-9   7.8 GB: 6-of-9   7.8 GB: 7-of-9   7.8 GB: 8-of-9   6.3 GB: 9-of-9
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-nd-4.0
Context Length4096
Model Max Length4096
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size64000
LoRA ModelYes
Torch Data Typefloat16

Best Alternatives to Caigun Lora Model 34B V3

Best Alternatives
Context / RAM
Downloads
Likes
Bagel Hermes 34B Slerp195K / 68.9 GB85241
34B Beta195K / 69.2 GB786864
Yi 34B 200K195K / 68.9 GB9763320
Smaug 34B V0.1195K / 69.2 GB826064
Casual Magnum 34B195K / 68.8 GB51
Bagel 34B V0.2195K / 68.7 GB275241
Yi 34B 200K AEZAKMI V2195K / 69.2 GB187212
Smaug 34B V0.1 ExPO195K / 69.2 GB78000
Bagel DPO 34B V0.5195K / 68.7 GB805517
Faro Yi 34B195K / 69.2 GB81986
Note: green Score (e.g. "73.2") means that the model is better than APMIC/caigun-lora-model-34B-v3.

Rank the Caigun Lora Model 34B V3 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? 52473 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