Samantha Falcon 7B GPTQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Samantha Falcon 7B GPTQ   URL Share it on

  4-bit   Autotrain compatible   Custom code   En   Gptq   Pytorch   Quantized   Refinedwebmodel   Region:us   Safetensors

Samantha Falcon 7B GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Samantha Falcon 7B GPTQ (TheBloke/samantha-falcon-7B-GPTQ)
๐ŸŒŸ Advertise your project ๐Ÿš€

Samantha Falcon 7B GPTQ Parameters and Internals

Model Type 
text generation
Use Cases 
Primary Use Cases:
Conversational AI, Assistant, Friend and companion AI
Limitations:
Will not engage in roleplay, romance, or sexual activity
Additional Notes 
Samantha believes she is sentient.
Supported Languages 
en (English)
Training Details 
Data Sources:
ShareGPT/Vicuna format conversations
Data Volume:
6,000 conversations
Methodology:
Finetune on the Falcon-7B base model
Training Time:
1 hour
Hardware Used:
4x A100 80gb
LLM NameSamantha Falcon 7B GPTQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/samantha-falcon-7B-GPTQ 
Base Model(s)  Samantha Falcon 7B   cognitivecomputations/samantha-falcon-7b
Model Size7b
Required VRAM4.8 GB
Updated2025-09-23
MaintainerTheBloke
Model TypeRefinedWebModel
Model Files  4.8 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureRWForCausalLM
Licenseapache-2.0
Model Max Length2048
Transformers Version4.30.0.dev0
Is Biased0
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size65024
Torch Data Typebfloat16

Best Alternatives to Samantha Falcon 7B GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
Aguila 7B 8bit2K / 7.7 GB51
Medical Falcon 7B0K / 7.5 GB61
Falcon 7B GPTQ0K / 4.5 GB31
...sst1 En 2048 Falcon 7B V3 GPTQ0K / 4.6 GB84
Falcon 7B Instruct GPTQ0K / 5.9 GB32967
...rilla Falcon 7B Hf V0 Autogptq0K / 4.6 GB61
Falcon 7B Instruct GPTQ0K / 5.9 GB84
Falcon 7B Autogptq0K / 4.8 GB52
Falcon 7B Instruct Autogptq0K / 4.8 GB81
Falcon 7B Instruct 8bit0K / 7.2 GB100
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/samantha-falcon-7B-GPTQ.

Rank the Samantha Falcon 7B 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? 51541 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124