Deepseek Coder 6.7B Instruct GGUF by second-state

 ยป  All LLMs  ยป  second-state  ยป  Deepseek Coder 6.7B Instruct GGUF   URL Share it on

  Autotrain compatible Base model:deepseek-ai/deepsee...   Codegen   Gguf   Instruct   License:other   Llama   Q2   Quantized   Region:us

Deepseek Coder 6.7B Instruct GGUF Benchmarks

Rank the Deepseek Coder 6.7B Instruct GGUF Capabilities

๐Ÿ†˜ 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! ๐ŸŒŸ

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  
Deepseek Coder 6.7B Instruct GGUF (second-state/Deepseek-Coder-6.7B-Instruct-GGUF)

Best Alternatives to Deepseek Coder 6.7B Instruct GGUF

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
...odeLlama 7B Instruct Onnx Fp1616K /  GB100
...6.7B Instruct 3.0bpw H6 EXL2 216K / 2.8 GB50
...6.7B Instruct 4.0bpw H6 EXL2 216K / 3.6 GB70
...eLlama 7B Instruct Hf 4bit MLX16K / 4.2 GB81
CodelLama7B Inst DPO 7K Mlx16K / 4.2 GB61
...6.7B Instruct 5.0bpw H6 EXL2 216K / 4.4 GB90
...6.7B Instruct 6.0bpw H6 EXL2 216K / 5.2 GB50
...6.7B Instruct 8.0bpw H8 EXL2 216K / 6.8 GB82
CodeLlama 7B Instruct Fp1616K / 13.5 GB458
...Llama 7B Instruct Bf16 Sharded16K / 13.5 GB421

Deepseek Coder 6.7B Instruct GGUF Parameters and Internals

LLM NameDeepseek Coder 6.7B Instruct GGUF
RepositoryOpen on ๐Ÿค— 
Model NameDeepseek Coder 6.7B Instruct
Model CreatorDeepSeek
Base Model(s)  Deepseek Coder 6.7B Instruct   deepseek-ai/deepseek-coder-6.7b-instruct
Model Size7b
Required VRAM2.5 GB
Updated2024-04-18
Maintainersecond-state
Model Typedeepseek
Instruction-BasedYes
Model Files  2.5 GB   3.6 GB   3.3 GB   3.0 GB   3.8 GB   4.1 GB   3.9 GB   4.7 GB   4.8 GB   4.7 GB   5.5 GB   7.2 GB
GGUF QuantizationYes
Quantization Typegguf|q2|q4_k|q5_k
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length16384
Model Max Length16384
Transformers Version4.34.1
Vocabulary Size32256
Initializer Range0.02
Torch Data Typebfloat16

What open-source LLMs or SLMs are you in search of? 35008 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024040901