LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Goliath LongLORA 120B Rope8 32K 6bpw H8 EXL2 by grimulkan

 »  All LLMs  »  grimulkan  »  Goliath LongLORA 120B Rope8 32K 6bpw H8 EXL2   URL Share it on

  10   
  Autotrain compatible   Endpoints compatible   Exl2   Fp16   Llama   Quantized   Region:us   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/grimulkan/Goliath-longLORA-120b-rope8-32k-6bpw_h8_exl2 

Goliath LongLORA 120B Rope8 32K 6bpw H8 EXL2 Benchmarks

LLME Score: 0.16899
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Goliath LongLORA 120B Rope8 32K 6bpw H8 EXL2 (grimulkan/Goliath-longLORA-120b-rope8-32k-6bpw_h8_exl2)

Goliath LongLORA 120B Rope8 32K 6bpw H8 EXL2 Parameters and Internals

Additional Notes 
This is an EXL2 6-bit quantization.
LLM NameGoliath LongLORA 120B Rope8 32K 6bpw H8 EXL2
Repository 🤗https://huggingface.co/grimulkan/Goliath-longLORA-120b-rope8-32k-6bpw_h8_exl2 
Model Size120b
Required VRAM88.7 GB
Updated2024-12-26
Maintainergrimulkan
Model Typellama
Model Files  4.3 GB: 1-of-22   4.2 GB: 2-of-22   4.3 GB: 3-of-22   4.3 GB: 4-of-22   4.2 GB: 5-of-22   4.3 GB: 6-of-22   4.2 GB: 7-of-22   4.1 GB: 8-of-22   4.2 GB: 9-of-22   4.1 GB: 10-of-22   4.1 GB: 11-of-22   4.2 GB: 12-of-22   4.3 GB: 13-of-22   4.2 GB: 14-of-22   4.2 GB: 15-of-22   4.2 GB: 16-of-22   4.2 GB: 17-of-22   4.1 GB: 18-of-22   4.2 GB: 19-of-22   4.2 GB: 20-of-22   4.3 GB: 21-of-22   0.3 GB: 22-of-22
Quantization Typefp16|exl2
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Goliath LongLORA 120B Rope8 32K 6bpw H8 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
Miquella 120B 4.0bpw H6 EXL231K / 59.4 GB112
...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
...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 grimulkan/Goliath-longLORA-120b-rope8-32k-6bpw_h8_exl2.

Rank the Goliath LongLORA 120B Rope8 32K 6bpw H8 EXL2 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? 40248 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217
  Support LLM Explorer