Deepseek Coder 6.7B Instruct Trt Int4 G64 Hf by juewang

 »  All LLMs  »  juewang  »  Deepseek Coder 6.7B Instruct Trt Int4 G64 Hf   URL Share it on

  8-bit   Autotrain compatible   Codegen   Conversational   Endpoints compatible   Instruct   Llama   Region:us   Safetensors

Deepseek Coder 6.7B Instruct Trt Int4 G64 Hf Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

Deepseek Coder 6.7B Instruct Trt Int4 G64 Hf Parameters and Internals

LLM NameDeepseek Coder 6.7B Instruct Trt Int4 G64 Hf
Repository 🤗https://huggingface.co/juewang/deepseek-coder-6.7b-instruct-trt-int4-g64-hf 
Model Size6.7b
Required VRAM4.2 GB
Updated2024-09-07
Maintainerjuewang
Model Typellama
Instruction-BasedYes
Model Files  4.2 GB
Generates CodeYes
Model ArchitectureLlamaForCausalLM
Context Length16384
Model Max Length16384
Transformers Version4.41.0.dev0
Tokenizer ClassLlamaTokenizer
Padding Token<|end▁of▁sentence|>
Vocabulary Size32256
Torch Data Typebfloat16
Deepseek Coder 6.7B Instruct Trt Int4 G64 Hf (juewang/deepseek-coder-6.7b-instruct-trt-int4-g64-hf)

Best Alternatives to Deepseek Coder 6.7B Instruct Trt Int4 G64 Hf

Best Alternatives
Context / RAM
Downloads
Likes
Speechless Coder Ds 6.7B16K / 13.5 GB6845
Code 290K 6.7B Instruct16K / 13.5 GB676
Datascience Coder 6.7B16K / 13.5 GB6683
Merge Code Gen16K / 13.6 GB50
...6.7B Instruct Trt Int8 G128 Hf16K / 7.2 GB70
NaturalSQL 6.7B V016K / 13.5 GB1036
SQL Sorcerer 6.7B V1.116K / 13.5 GB60
DeepYi Second16K / 12.6 GB130
SQL Sorcerer 6.7B V1.016K / 13.5 GB80
...rpreter DS 6.7B 8.0bpw H8 EXL216K / 6.9 GB122
Note: green Score (e.g. "73.2") means that the model is better than juewang/deepseek-coder-6.7b-instruct-trt-int4-g64-hf.

Rank the Deepseek Coder 6.7B Instruct Trt Int4 G64 Hf 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? 35693 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803