Stheno V2 Delta AWQ by TheBloke

 ยป  All LLMs  ยป  TheBloke  ยป  Stheno V2 Delta AWQ   URL Share it on

  4-bit   Autotrain compatible   Awq Base model:quantized:sao10k/st... Base model:sao10k/stheno-v2-de...   En   Fp16   Llama   Quantized   Region:us   Safetensors

Stheno V2 Delta AWQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Stheno V2 Delta AWQ (TheBloke/Stheno-v2-Delta-AWQ)

Stheno V2 Delta AWQ Parameters and Internals

Model Type 
llama
Additional Notes 
- A v2 attempt but using the new DARE merging method. - Alright, I guess? Total Models used: < 5 Purely Experimental - Works well enough I think?
Supported Languages 
en (Native/Fluent)
LLM NameStheno V2 Delta AWQ
Repository ๐Ÿค—https://huggingface.co/TheBloke/Stheno-v2-Delta-AWQ 
Model NameStheno V2 Delta
Model CreatorSaofiq
Base Model(s)  Stheno V2 Delta Fp16   Sao10K/Stheno-v2-Delta-fp16
Model Size2b
Required VRAM7.2 GB
Updated2025-02-23
MaintainerTheBloke
Model Typellama
Model Files  7.2 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typefp16|awq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.35.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Stheno V2 Delta AWQ

Best Alternatives
Context / RAM
Downloads
Likes
...ents Llama3 4.0.37 DPO 480 AWQ8K / 5.8 GB790
...t Agents Llama3 4.0.34 DPO AWQ8K / 5.8 GB810
...t Agents Llama3 4.0.35 DPO AWQ8K / 5.8 GB810
...t Agents Llama3 4.0.23 DPO AWQ8K / 5.8 GB780
Llama3 AWQ Hermes 2 Theta8K / 5.8 GB800
Drug Profile Llama 3 AWQ8K / 5.8 GB110
...t Agents Llama3 4.0.22 DPO AWQ8K / 5.8 GB70
...ot Agents Llama3 4.0.5 SFT AWQ8K / 5.8 GB181
...ot Agents Llama3 4.0.2 SFT AWQ8K / 5.8 GB150
EPFL TA Meister AWQ 4bit8K / 5.8 GB120
Note: green Score (e.g. "73.2") means that the model is better than TheBloke/Stheno-v2-Delta-AWQ.

Rank the Stheno V2 Delta AWQ 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? 43515 in total.

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