LLM EXPLORER 66,420 MODELS INDEXED

Deepseek Coder 7B Base V1.5 AWQ by ig1

By ig1 · 0 downloads
HF Repo ↗ Copy URL

Deepseek Coder 7B Base V1.5 AWQ is an open-source language model by ig1. Features: 7b LLM, VRAM: 4.8GB, Context: 4K, Quantized, Code Generating.

  4-bit   Autotrain compatible   Awq   Codegen   Endpoints compatible   Llama   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/ig1/deepseek-coder-7b-base-v1.5-awq 

Deepseek Coder 7B Base V1.5 AWQ Parameters and Internals

LLM NameDeepseek Coder 7B Base V1.5 AWQ
Repository 🤗https://huggingface.co/ig1/deepseek-coder-7b-base-v1.5-awq 
Base Model(s)  deepseek-ai/deepseek-coder-7b-base-v1.5   deepseek-ai/deepseek-coder-7b-base-v1.5
Model Size7b
Required VRAM4.8 GB
Updated2024-07-04
Maintainerig1
Model Typellama
Model Files  4.8 GB
AWQ QuantizationYes
Quantization Typeawq
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Context Length4096
Model Max Length4096
Transformers Version4.41.2
Tokenizer ClassLlamaTokenizer
Padding Token<｜end▁of▁sentence｜>
Vocabulary Size102400
Torch Data Typefloat16

Best Alternatives to Deepseek Coder 7B Base V1.5 AWQ

Best Alternatives
Context / RAM
Downloads
Likes
CodeLlama 7B Instruct AWQ16K / 3.9 GB2784
CodeLlama 7B AWQ16K / 3.9 GB756
CodeLlama 7B Python AWQ16K / 3.9 GB54
...Llama 7B Python Hf W4 G128 AWQ16K / 3.9 GB80
...ama 7B Instruct Hf W4 G128 AWQ16K / 3.9 GB60
Llama 2 Coder 7B AWQ4K / 3.9 GB83
CodeLlama 7B Java 16bit16K / 13.5 GB100
Codellama 7B Bnb 4bit16K / 3.9 GB36959
...ruct Solidity Bnb 4bit Smashed16K / 4.2 GB60
...lama 7B Tofuagent Contpretrain16K / 13.5 GB60
Note: green Score (e.g. "73.2") means that the model is better than ig1/deepseek-coder-7b-base-v1.5-awq.