Cassandra 6.9B GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Cassandra 6.9B GPTQ   URL Share it on

  4-bit   Autotrain compatible   Finetuned   Gpt neox   Gptq   Quantized   Region:us   Safetensors

Cassandra 6.9B GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Cassandra 6.9B GPTQ (TheBloke/cassandra-6.9B-GPTQ)

Cassandra 6.9B GPTQ Parameters and Internals

Model Type 
text generation
Additional Notes 
Quantized to 4bit using AutoGPTQ for optimized inference accuracy and speed. Supports varying bit sizes for CPU+GPU inference.
Input Output 
Input Format:
NovelAI-style
Accepted Modalities:
text
Performance Tips:
Use '>" as a stop token in your UI
LLM NameCassandra 6.9B GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/cassandra-6.9B-GPTQ 
Model Size6.9b
Required VRAM4.7 GB
Updated2025-02-22
MaintainerTheBloke
Model Typegpt_neox
Model Files  4.7 GB
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureGPTNeoXForCausalLM
Licenseother
Context Length4096
Model Max Length4096
Transformers Version4.27.2
Vocabulary Size50277
Torch Data Typefloat16

Best Alternatives to Cassandra 6.9B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
... Int3 Step36000 GPTQ Wikitext22K / 3.4 GB760
...Int3 Step107000 GPTQ Wikitext22K / 3.4 GB760
...Int4 Step107000 GPTQ Wikitext22K / 4.2 GB760
... Int3 Step71000 GPTQ Wikitext22K / 3.4 GB780
...Int3 Step110000 GPTQ Wikitext22K / 3.4 GB780
...Int3 Step143000 GPTQ Wikitext22K / 3.4 GB770
... Int4 Step71000 GPTQ Wikitext22K / 4.2 GB780
...Int4 Step110000 GPTQ Wikitext22K / 4.2 GB780
...Int4 Step143000 GPTQ Wikitext22K / 4.2 GB780
...ythia 6.9B Int4 GPTQ Wikitext22K / 4.2 GB770
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/cassandra-6.9B-GPTQ.

Rank the Cassandra 6.9B 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