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

Gpt4 Alpaca Lora Mlp 65B GPTQ by TheBloke

 »  All LLMs  »  TheBloke  »  Gpt4 Alpaca Lora Mlp 65B GPTQ   URL Share it on

  5   
  4-bit   Autotrain compatible Dataset:c-s-ale/alpaca-gpt4-da...   Endpoints compatible   Gptq   Llama   Lora   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/TheBloke/gpt4-alpaca-lora_mlp-65B-GPTQ 

Gpt4 Alpaca Lora Mlp 65B GPTQ Benchmarks

ARC: 65.02 vs 96.7 (so35)-32.8%
HellaSwag: 86.13 vs 95.3 (gpt4)-9.6%
MMLU: 62.73 vs 88.3 (so35)-29%
TruthfulQA: 59.16 vs 59 (gpt4)0.3%
WinoGrande: 80.66 vs 87.5 (gpt4)-7.8%
GSM8K: 28.28 vs 96.4 (so35)-70.7%
LLME Score: 0.10162
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Gpt4 Alpaca Lora Mlp 65B GPTQ (TheBloke/gpt4-alpaca-lora_mlp-65B-GPTQ)
🌟 Advertise your project 🚀

Gpt4 Alpaca Lora Mlp 65B GPTQ Parameters and Internals

Model Type 
text2text-generation
Use Cases 
Areas:
research, commercial applications
Additional Notes 
Merged LoRA weights with original Llama 65B model, quantized to 4bit using GPTQ.
Training Details 
Data Sources:
alpaca_data_gpt4
Methodology:
Fine-tuning using LoRA
Context Length:
512
Hardware Used:
8xA100(80G)
Model Architecture:
LoRA [MLP]
Input Output 
Accepted Modalities:
text
Performance Tips:
Limit responses to <1500 tokens to avoid VRAM overflow.
LLM NameGpt4 Alpaca Lora Mlp 65B GPTQ
Repository 🤗https://huggingface.co/TheBloke/gpt4-alpaca-lora_mlp-65B-GPTQ 
Base Model(s)  Gpt4 Alpaca Lora Mlp 65B HF   TheBloke/gpt4-alpaca-lora_mlp-65B-HF
Model Size65b
Required VRAM33.5 GB
Updated2025-09-15
MaintainerTheBloke
Model Typellama
Model Files  33.5 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.28.1
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
LoRA ModelYes
Torch Data Typefloat16

Best Alternatives to Gpt4 Alpaca Lora Mlp 65B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...en Instruct Human Mix 65B GPTQ2K / 33.5 GB110
Guanaco 65B GPTQ2K / 33.5 GB1732263
Airoboros 65B Gpt4 1.4 GPTQ2K / 33.5 GB413
Airoboros 65B Gpt4 1.3 GPTQ2K / 33.5 GB43
Airoboros 65B Gpt4 1.2 GPTQ2K / 33.5 GB511
Dromedary 65B Lora GPTQ2K / 33.5 GB46
Airoboros 65B GPT4 2.0 GPTQ2K / 33.5 GB73
Airoboros 65B GPT4 M2.0 GPTQ2K / 33.5 GB82
...stage Llama1 65B Instruct GPTQ2K / 34.7 GB63
...Research Oasst1 Llama 65B GPTQ2K / 33.5 GB75
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/gpt4-alpaca-lora_mlp-65B-GPTQ.

Rank the Gpt4 Alpaca Lora Mlp 65B GPTQ 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? 51387 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