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

Cria Llama2 7B V1.3 GGML by davzoku

 »  All LLMs  »  davzoku  »  Cria Llama2 7B V1.3 GGML   URL Share it on

  725   
  Autotrain compatible   Codegen Dataset:mlabonne/codellama-2-2...   En   Ggml   Llama   Llama2   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/davzoku/cria-llama2-7b-v1.3-GGML 

Cria Llama2 7B V1.3 GGML Benchmarks

ARC: 52.73 vs 96.7 (so35)-45.5%
HellaSwag: 78.58 vs 95.3 (gpt4)-17.5%
MMLU: 48.3 vs 88.3 (so35)-45.3%
TruthfulQA: 45.58 vs 59 (gpt4)-22.7%
WinoGrande: 71.9 vs 87.5 (gpt4)-17.8%
GSM8K: 8.49 vs 96.4 (so35)-91.2%
LLME Score: 0.17145
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cria Llama2 7B V1.3 GGML (davzoku/cria-llama2-7b-v1.3-GGML)

Cria Llama2 7B V1.3 GGML Parameters and Internals

Model Type 
text generation, chatbot
Use Cases 
Areas:
chatbots, intelligent applications
Primary Use Cases:
chatbot system, model deployment
Training Details 
Data Sources:
mlabonne/CodeLlama-2-20k
Methodology:
Fine-tuned with QLoRA (4-bit precision)
Hardware Used:
T4 GPU, High RAM
Release Notes 
Version:
v1.3
Notes:
CRIA v1.3 released with multiple model variants
LLM NameCria Llama2 7B V1.3 GGML
Repository 🤗https://huggingface.co/davzoku/cria-llama2-7b-v1.3-GGML 
Base Model(s)  davzoku/cria-llama2-7b-v1.3   davzoku/cria-llama2-7b-v1.3
Model Size7b
Required VRAM3.8 GB
Updated2024-12-22
Maintainerdavzoku
Model Typellama
Model Files  3.8 GB
Supported Languagesen
GGML QuantizationYes
Quantization Typeggml
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.31.0
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Cria Llama2 7B V1.3 GGML

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 7B Java 16bit16K / 13.5 GB170
Codellama 7B Bnb 4bit16K / 3.9 GB33162
...lama 7B Tofuagent Contpretrain16K / 13.5 GB280
...ruct Solidity Bnb 4bit Smashed16K / 4.2 GB140
...B Instruct Hf Bnb 4bit Smashed16K / 4.2 GB210
CodeLlama 7B Python Onnx Fp1616K /  GB101
CodeLlama 7B Python 4bit MLX16K / 4 GB4714
...pMagic Coder 7B 8.0bpw H8 EXL216K / 6.9 GB51
CodelLama7B Inst DPO 7K Mlx16K / 4.2 GB82
...eLlama 7B Instruct Hf 4bit MLX16K / 4.2 GB121
Note: green Score (e.g. "73.2") means that the model is better than davzoku/cria-llama2-7b-v1.3-GGML.

Rank the Cria Llama2 7B V1.3 GGML 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? 40066 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 v20241217
  Support LLM Explorer