Blue Orchid 2x7b GPTQ by LoneStriker

 ยป  All LLMs  ยป  LoneStriker  ยป  Blue Orchid 2x7b GPTQ   URL Share it on

  4bit   Autotrain compatible   Endpoints compatible   Gptq   Mixtral   Moe   Quantized   Region:us   Safetensors

Blue Orchid 2x7b GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Blue Orchid 2x7b GPTQ (LoneStriker/Blue-Orchid-2x7b-GPTQ)

Blue Orchid 2x7b GPTQ Parameters and Internals

Model Type 
Roleplaying, Storywriting
Input Output 
Input Format:
{system prompt} {prompt}
Accepted Modalities:
text
Output Format:
Character response
Performance Tips:
The Alpaca prompt template should also work fine.
LLM NameBlue Orchid 2x7b GPTQ
Repository ๐Ÿค—https://huggingface.co/LoneStriker/Blue-Orchid-2x7b-GPTQ 
Required VRAM7.1 GB
Updated2025-02-22
MaintainerLoneStriker
Model Typemixtral
Model Files  7.1 GB
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length8192
Model Max Length8192
Transformers Version4.37.1
Tokenizer ClassLlamaTokenizer
Padding Token<s>
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Blue Orchid 2x7b GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...y Mixtral 22bx8 V21.1 65K Gptq64K /  GB50
LHK DPO V1 GPTQ 4bit32K / 7.8 GB51
...dy Mixtral 7bx8 V18.1 32K Gptq32K / 24.8 GB333
Mixtral 8x7B V0.1 Int8 GPTQ32K /  GB122
...oE V0.1 DPO F16 5.0bpw H6 EXL2195K / 38.8 GB100
...oE V0.1 DPO F16 4.0bpw H6 EXL2195K / 31.3 GB80
...2 Mixtral 8x22b 6.0bpw H8 EXL264K / 105.8 GB71
WizardLM 2 8x22 EXL2 4.0bpw64K / 70.9 GB81
...rdLM 2 8x22B Beige EXL2 5.0bpw64K / 88.4 GB170
...M 2 8x22B Beige 4.0bpw H6 EXL264K / 70.8 GB130
Note: green Score (e.g. "73.2") means that the model is better than LoneStriker/Blue-Orchid-2x7b-GPTQ.

Rank the Blue Orchid 2x7b 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? 43470 in total.

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