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

Cognitivecomputations Dolphincoder Starcoder2 7B Bnb 4bit Smashed by PrunaAI

 »  All LLMs  »  PrunaAI  »  Cognitivecomputations Dolphincoder Starcoder2 7B Bnb 4bit Smashed   URL Share it on

  19   
  4-bit   4bit   Autotrain compatible Base model:cognitivecomputatio... Base model:quantized:cognitive...   Bitsandbytes   Conversational   Endpoints compatible   Pruna-ai   Quantized   Region:us   Safetensors   Starcoder2
Model Card on HF 🤗: https://huggingface.co/PrunaAI/cognitivecomputations-dolphincoder-starcoder2-7b-bnb-4bit-smashed 

Cognitivecomputations Dolphincoder Starcoder2 7B Bnb 4bit Smashed Benchmarks

LLME Score: 0.20076
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cognitivecomputations Dolphincoder Starcoder2 7B Bnb 4bit Smashed (PrunaAI/cognitivecomputations-dolphincoder-starcoder2-7b-bnb-4bit-smashed)

Cognitivecomputations Dolphincoder Starcoder2 7B Bnb 4bit Smashed Parameters and Internals

Model Type 
compressed model
Additional Notes 
The model is initially slower and consumes more memory on the first run due to CUDA overheads.
Training Details 
Data Sources:
WikiText
Methodology:
Compressed with llm-int8
Input Output 
Input Format:
PT tensors with tokenizer
Accepted Modalities:
text
Output Format:
Decoded text from tokenizer
Performance Tips:
Run efficiency tests directly in use-case conditions to maximize performance.
LLM NameCognitivecomputations Dolphincoder Starcoder2 7B Bnb 4bit Smashed
Repository 🤗https://huggingface.co/PrunaAI/cognitivecomputations-dolphincoder-starcoder2-7b-bnb-4bit-smashed 
Base Model(s)  Dolphincoder Starcoder2 7B   cognitivecomputations/dolphincoder-starcoder2-7b
Model Size7b
Required VRAM4.4 GB
Updated2025-01-20
MaintainerPrunaAI
Model Typestarcoder2
Model Files  4.4 GB
Quantization Type4bit
Model ArchitectureStarcoder2ForCausalLM
Context Length16384
Model Max Length16384
Transformers Version4.40.0
Tokenizer ClassGPT2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size49154
Torch Data Typefloat16
Activation Functiongelu

Best Alternatives to Cognitivecomputations Dolphincoder Starcoder2 7B Bnb 4bit Smashed

Best Alternatives
Context / RAM
Downloads
Likes
Starcoder2 7B 4bit16K / 4.4 GB151
Starcoder2 7B16K / 14.4 GB7423165
Starcoder2 7B AWQ16K / 4.5 GB101
StarCoder2 7B GGUF16K / 2.7 GB397812
Dolphincoder Starcoder2 7B16K / 14.9 GB2011
Starcoder2 7B Int4 Ov16K / 3.8 GB150
Jmg Starcoder2 7B 100K16K / 14.4 GB200
Speechless Starcoder2 7B16K / 14.4 GB1325
Starcoder2 7B Instruct16K / 14.4 GB1272
Starcoder2 7B Instruct GPTQ16K / 4.5 GB91
Note: green Score (e.g. "73.2") means that the model is better than PrunaAI/cognitivecomputations-dolphincoder-starcoder2-7b-bnb-4bit-smashed.

Rank the Cognitivecomputations Dolphincoder Starcoder2 7B Bnb 4bit Smashed 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? 41636 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 v20241227
  Support LLM Explorer