Miquella 120B 4.0bpw H6 EXL2 by LoneStriker

 ยป  All LLMs  ยป  LoneStriker  ยป  Miquella 120B 4.0bpw H6 EXL2   URL Share it on

  Autotrain compatible   Endpoints compatible   Exl2   Llama   Merge   Mergekit   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Miquella 120B 4.0bpw H6 EXL2 Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Miquella 120B 4.0bpw H6 EXL2 (LoneStriker/miquella-120b-4.0bpw-h6-exl2)

Miquella 120B 4.0bpw H6 EXL2 Parameters and Internals

Model Type 
pre-trained language model
Additional Notes 
Model has been remade with fixed dequantization of miqu.
LLM NameMiquella 120B 4.0bpw H6 EXL2
Repository ๐Ÿค—https://huggingface.co/LoneStriker/miquella-120b-4.0bpw-h6-exl2 
Model Size120b
Required VRAM59.4 GB
Updated2024-12-26
MaintainerLoneStriker
Model Typellama
Model Files  8.5 GB: 1-of-7   8.5 GB: 2-of-7   8.5 GB: 3-of-7   8.5 GB: 4-of-7   8.6 GB: 5-of-7   8.6 GB: 6-of-7   8.2 GB: 7-of-7
Quantization Typeexl2
Model ArchitectureLlamaForCausalLM
Context Length32764
Model Max Length32764
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Miquella 120B 4.0bpw H6 EXL2

Best Alternatives
Context / RAM
Downloads
Likes
Miquella 120B 3.0bpw H6 EXL231K / 44.8 GB1010
Miquella 120B 8.0bpw H8 EXL231K / 118.1 GB113
...t 120B Cat A Llama EXL2 5.5bpw8K / 85.3 GB150
...t 120B Cat A Llama EXL2 4.5bpw8K / 70.3 GB81
...h LongLORA 120B Rope8 32K Fp164K / 235.4 GB207
...RA 120B Rope8 32K 6bpw H8 EXL24K / 88.7 GB101
...egaDolphin 120B 2.9bpw H6 EXL24K / 44.3 GB183
...gaDolphin 120B 2.65bpw H6 EXL24K / 40.5 GB192
...egaDolphin 120B 4.0bpw H6 EXL24K / 60.8 GB171
Goliath 120B 6.0bpw H6 EXL24K / 88.9 GB161
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/miquella-120b-4.0bpw-h6-exl2.

Rank the Miquella 120B 4.0bpw H6 EXL2 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? 40248 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217