Llama 2 7B Chat Nf4 Fp16 Upscaled by arnavgrg

 ยป  All LLMs  ยป  arnavgrg  ยป  Llama 2 7B Chat Nf4 Fp16 Upscaled   URL Share it on

  Autotrain compatible   Conversational   Endpoints compatible   Fp16   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Llama 2 7B Chat Nf4 Fp16 Upscaled Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Llama 2 7B Chat Nf4 Fp16 Upscaled (arnavgrg/llama-2-7b-chat-nf4-fp16-upscaled)

Llama 2 7B Chat Nf4 Fp16 Upscaled Parameters and Internals

Model Type 
text-generation-inference
Additional Notes 
The model is an upscaled fp16 variant of the original Llama-2-7b-chat and includes nf4 4-bit quantization via bitsandbytes. Note that the quantization operation is not lossless, impacting performance compared to the base model.
Input Output 
Accepted Modalities:
text
Performance Tips:
Use FP16 with transformers to load the model efficiently.
LLM NameLlama 2 7B Chat Nf4 Fp16 Upscaled
Repository ๐Ÿค—https://huggingface.co/arnavgrg/llama-2-7b-chat-nf4-fp16-upscaled 
Model Size7b
Required VRAM13.5 GB
Updated2025-02-15
Maintainerarnavgrg
Model Typellama
Model Files  4.9 GB: 1-of-3   5.0 GB: 2-of-3   3.6 GB: 3-of-3
Quantization Typefp16
Model ArchitectureLlamaForCausalLM
Licenseapache-2.0
Context Length4096
Model Max Length4096
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Llama 2 7B Chat Nf4 Fp16 Upscaled

Best Alternatives
Context / RAM
Downloads
Likes
Smaugv0.1 6.0bpw H6 EXL2195K / 26.4 GB124
Smaugv0.1 5.0bpw H6 EXL2195K / 22.3 GB103
Smaugv0.1 3.0bpw H6 EXL2195K / 13.9 GB91
Smaugv0.1 4.0bpw H6 EXL2195K / 18 GB81
Smaugv0.1 4.65bpw H6 EXL2195K / 20.8 GB81
Smaugv0.1 8.0bpw H8 EXL2195K / 34.9 GB81
Mistral 7B Openplatypus 1K32K / 29 GB15850
Mistral 7B OpenOrca 1K32K / 29 GB15853
Mistral 7B A U0.5 B2 Ver0.432K / 14.4 GB20280
Mistral 7B OP U1k Ver0.632K / 14.4 GB20290
Note: green Score (e.g. "73.2") means that the model is better than arnavgrg/llama-2-7b-chat-nf4-fp16-upscaled.

Rank the Llama 2 7B Chat Nf4 Fp16 Upscaled 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  

What open-source LLMs or SLMs are you in search of? 43137 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227