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

Mistral7b V0.3 Alpaca Cleaned by avrecum

 »  All LLMs  »  avrecum  »  Mistral7b V0.3 Alpaca Cleaned   URL Share it on

  22   
  Autotrain compatible   Endpoints compatible   Gguf   Lora   Mistral   Quantized   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/avrecum/mistral7b-v0.3-alpaca-cleaned 

Mistral7b V0.3 Alpaca Cleaned Benchmarks

LLME Score: 0.17259
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
🌟 Advertise your project 🚀

Mistral7b V0.3 Alpaca Cleaned Parameters and Internals

Model Type 
text-generation
Additional Notes 
Model finetuned for 1 epoch using paged_adamw_8bit optimizer with specific training parameters: per_device_train_batch_size=10, gradient_accumulation_steps=4, warmup_steps=5, learning_rate=2e-4, weight_decay=0.01, lr_scheduler_type='linear', seed=3407.
Training Details 
Data Sources:
cleaned Stanford Alpaca dataset
Methodology:
LoRA
LLM NameMistral7b V0.3 Alpaca Cleaned
Repository 🤗https://huggingface.co/avrecum/mistral7b-v0.3-alpaca-cleaned 
Model Size7.2b
Required VRAM14.5 GB
Updated2025-06-09
Maintaineravrecum
Model Files  0.2 GB   14.5 GB   5.0 GB: 1-of-3   5.0 GB: 2-of-3   4.5 GB: 3-of-3
GGUF QuantizationYes
Quantization Typegguf
Model ArchitectureAutoModelForCausalLM
Licensemit
Model Max Length32768
Is Biasednone
Tokenizer ClassLlamaTokenizer
Padding Token[control_768]
PEFT TypeLORA
LoRA ModelYes
PEFT Target Modulesk_proj|q_proj|up_proj|v_proj|gate_proj|down_proj|o_proj
LoRA Alpha16
LoRA Dropout0
R Param16
Mistral7b V0.3 Alpaca Cleaned (avrecum/mistral7b-v0.3-alpaca-cleaned)

Best Alternatives to Mistral7b V0.3 Alpaca Cleaned

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral AI Llava 4bit0K / 14.4 GB5482
Mistralmeme0K / 14.4 GB570
My Mistral Seekh Qna0K / 28.9 GB290
Cosmic 20K / 14.4 GB101
Zephyr Tuning V10K / 14.4 GB17470
Spydaz Web AI 0250K / 14.4 GB440
Small Fut Final0K / 14.4 GB191
Big Fut Final0K / 14.4 GB101
Last Model Too Long Time0K / 14.4 GB81
DummySFT0K / 28.9 GB100
Note: green Score (e.g. "73.2") means that the model is better than avrecum/mistral7b-v0.3-alpaca-cleaned.

Rank the Mistral7b V0.3 Alpaca Cleaned 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? 48046 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