LLM Explorer: A Curated Large Language Model Directory and Analytics  // 

Deepseek Llm 7B Base GPTQ by TheBloke

What open-source LLMs or SLMs are you in search of? 18732 in total.

 »  All LLMs  »  TheBloke  »  Deepseek Llm 7B Base GPTQ   URL Share it on

  4-bit   Autotrain compatible Base model:deepseek-ai/deepsee...   Gptq   License:other   Llama   Quantized   Region:us   Safetensors

Deepseek Llm 7B Base GPTQ Benchmarks

Rank the Deepseek Llm 7B Base 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  
Deepseek Llm 7B Base GPTQ (TheBloke/deepseek-llm-7B-base-GPTQ)

Best Alternatives to Deepseek Llm 7B Base GPTQ

Best Alternatives
HF Rank
Context/RAM
Downloads
Likes
Bagel DPO 7B V0.167.9532K / 14.4 GB225939
Internlm2 7B Llama66.9432K / 15.5 GB15995
Llama2 Init Mistral60.984K / 14.4 GB25510
A I 0xtom 7B Slerp60.4632K / 14.4 GB2580
AIRIC The Mistral59.9532K / 14.4 GB19413
Synatra RP Orca 2 7B V0.159.554K / 13.5 GB30576
Deepseek Llm 7B Chat59.274K / 13.9 GB713758
UltraQwen 7B59.1732K / 15.4 GB17712
...rnlm2 20B Llama 4.0bpw H6 EXL258.532K / 11 GB51
Mistral 7B Guanaco1k Ep258.1332K / 29 GB36423
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/deepseek-llm-7B-base-GPTQ.

Deepseek Llm 7B Base GPTQ Parameters and Internals

LLM NameDeepseek Llm 7B Base GPTQ
RepositoryOpen on 🤗 
Model NameDeepseek LLM 7B Base
Model CreatorDeepSeek
Base Model(s)  Deepseek Llm 7B Base   deepseek-ai/deepseek-llm-7b-base
Model Size7b
Required VRAM4.8 GB
Updated2024-02-21
MaintainerTheBloke
Model Typedeepseek
Model Files  4.8 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizerFast
Beginning of Sentence Token<|begin▁of▁sentence|>
End of Sentence Token<|end▁of▁sentence|>
Vocabulary Size102400
Initializer Range0.02
Torch Data Typebfloat16
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024022003