Llama3 7B Lora 4bit AWQ by nmnth

 ยป  All LLMs  ยป  nmnth  ยป  Llama3 7B Lora 4bit AWQ   URL Share it on

  4-bit   4bit   Autotrain compatible   Awq   Endpoints compatible   Llama   Lora   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Rank the Llama3 7B Lora 4bit AWQ 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  
Llama3 7B Lora 4bit AWQ (nmnth/llama3_7b_lora_4bit_awq)

Best Alternatives to Llama3 7B Lora 4bit AWQ

Best Alternatives
HF Rank
Titanbagel64.2132K / 14.4 GB18010
Smaugv0.1 AWQ60.1195K / 19.3 GB21
Smaugv0.1 3.0bpw H6 EXL260.1195K / 13.9 GB21
Smaugv0.1 4.0bpw H6 EXL260.1195K / 18 GB21
Smaugv0.1 4.65bpw H6 EXL260.1195K / 20.8 GB21
Smaugv0.1 5.0bpw H6 EXL260.1195K / 22.3 GB23
Smaugv0.1 6.0bpw H6 EXL260.1195K / 26.4 GB24
Smaugv0.1 8.0bpw H8 EXL260.1195K / 34.9 GB21
...p 0.05 Max Grad1.0 Grad Accu1660.132K / 14.4 GB90
...p 0.05 Max Grad1.0 Grad Accu1660.132K / 14.4 GB80
Note: green Score (e.g. "73.2") means that the model is better than nmnth/llama3_7b_lora_4bit_awq.

Llama3 7B Lora 4bit AWQ Parameters and Internals

LLM NameLlama3 7b Lora 4bit AWQ
RepositoryOpen on ๐Ÿค— 
Model Size7b
Required VRAM5.8 GB
Model Typellama
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
AWQ QuantizationYes
Quantization Typeawq|4bit
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.41.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|reserved_special_token_250|>
Vocabulary Size128256
LoRA ModelYes
Initializer Range0.02
Torch Data Typefloat16

What open-source LLMs or SLMs are you in search of? 34944 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024042801