LLM EXPLORER 59,516 MODELS INDEXED

Saiga Llama3 8B AWQ by alekosus

By alekosus · 22 downloads
HF Repo ↗ Copy URL

Saiga Llama3 8B AWQ is an open-source language model by alekosus. Features: 8b LLM, VRAM: 5.8GB, Context: 8K, License: llama3, Quantized, LLM Explorer Score: 0.12.

  4-bit   Autotrain compatible   Awq   Conversational   Endpoints compatible   Llama   Quantized   Region:us   Ru   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/alekosus/saiga_llama3_8b_awq 

Saiga Llama3 8B AWQ Parameters and Internals

LLM NameSaiga Llama3 8b AWQ
Repository 🤗https://huggingface.co/alekosus/saiga_llama3_8b_awq 
Base Model(s)  Saiga Llama3 8b   IlyaGusev/saiga_llama3_8b
Model Size8b
Required VRAM5.8 GB
Updated2024-08-06
Maintaineralekosus
Model Typellama
Model Files  4.7 GB: 1-of-2   1.1 GB: 2-of-2
Supported Languagesru
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureLlamaForCausalLM
Licensellama3
Context Length8192
Model Max Length8192
Transformers Version4.39.3
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|begin_of_text|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Saiga Llama3 8B AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...8B Instruct Gradient 1048K AWQ1024K / 5.8 GB80
...radient 1048K AWQ 4bit Smashed1024K / 5.8 GB71
...Instruct 262K AWQ 4bit Smashed256K / 5.8 GB54
...ta Llama 3 8B Instruct 64K AWQ64K / 5.8 GB60
... Instruct 8B 32K V0.1 4bit AWQ64K / 5.8 GB130
Llama 3 8B Instruct AWQ8K / 5.8 GB2545831
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB60
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB5630
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB70
Meta Llama 3 8B Instruct AWQ8K / 5.8 GB4015
Note: green Score (e.g. "73.2") means that the model is better than alekosus/saiga_llama3_8b_awq.