Goliath 120B GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Goliath 120B GPTQ   URL Share it on

  4-bit   Autotrain compatible Base model:alpindale/goliath-1... Base model:quantized:alpindale...   Conversational   En   Gptq   Llama   Quantized   Region:us   Safetensors   Sharded   Tensorflow

Goliath 120B GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Goliath 120B GPTQ (TheBloke/goliath-120b-GPTQ)

Goliath 120B GPTQ Parameters and Internals

Model Type 
llama, conversational
Additional Notes 
Quantized by TheBloke. Multiple quantization parameters provided for optimal hardware compatibility.
Supported Languages 
en (high)
Training Details 
Data Sources:
Xwin-LM/Xwin-LM-70B-V0.1, Sao10K/Euryale-1.3-L2-70B
Methodology:
auto-regressive causal LM created by combining 2x finetuned Llama-2 70B
Input Output 
Input Format:
You are a helpful AI assistant. USER: {prompt} ASSISTANT:
Accepted Modalities:
text
Output Format:
text
LLM NameGoliath 120B GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/goliath-120b-GPTQ 
Model NameGoliath 120B
Model CreatorAlpin
Base Model(s)  Goliath 120B   alpindale/goliath-120b
Model Size120b
Required VRAM59.8 GB
Updated2025-03-14
MaintainerTheBloke
Model Typellama
Model Files  10.0 GB: 1-of-6   9.9 GB: 2-of-6   10.0 GB: 3-of-6   10.0 GB: 4-of-6   10.0 GB: 5-of-6   9.9 GB: 6-of-6
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.34.1
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Goliath 120B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...gLORA 120B Rope8 32K Fp16 GPTQ4K / 59.8 GB434
MegaDolphin 120B GPTQ4K / 61.1 GB304
Koishi 120B Qlora Gptq4K / 59.8 GB231
DiscoLM 120B GPTQ4K / 59.8 GB213
Miquella 120B 3.0bpw H6 EXL231K / 44.8 GB1410
Miquella 120B 8.0bpw H8 EXL231K / 118.1 GB123
Miquella 120B 4.0bpw H6 EXL231K / 59.4 GB112
...t 120B Cat A Llama EXL2 5.5bpw8K / 85.3 GB100
...t 120B Cat A Llama EXL2 4.5bpw8K / 70.3 GB81
...h LongLORA 120B Rope8 32K Fp164K / 235.4 GB237
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/goliath-120b-GPTQ.

Rank the Goliath 120B GPTQ 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? 45019 in total.

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