Saiga2 70B Lora GPTQ by Komposter43

 ยป  All LLMs  ยป  Komposter43  ยป  Saiga2 70B Lora GPTQ   URL Share it on

  4-bit   Autotrain compatible Base model:ilyagusev/saiga2 70... Base model:quantized:ilyagusev...   Gptq   Llama   Lora   Quantized   Region:us   Ru   Safetensors

Saiga2 70b Lora GPTQ Benchmarks

nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Saiga2 70B Lora GPTQ (Komposter43/saiga2_70b_lora-GPTQ)

Saiga2 70B Lora GPTQ Parameters and Internals

Model Type 
llama
Supported Languages 
ru (unknown)
LLM NameSaiga2 70b Lora GPTQ
Repository ๐Ÿค—https://huggingface.co/Komposter43/saiga2_70b_lora-GPTQ 
Model NameSaiga2 70B GPTQ
Model CreatorIlyaGusev
Base Model(s)  Saiga2 70b Lora   IlyaGusev/saiga2_70b_lora
Model Size70b
Required VRAM36.7 GB
Updated2024-12-22
MaintainerKomposter43
Model Typellama
Model Files  36.7 GB
Supported Languagesru
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureLlamaForCausalLM
Licensellama2
Context Length4096
Model Max Length4096
Transformers Version4.33.2
Tokenizer ClassLlamaTokenizer
Beginning of Sentence Token<s>
End of Sentence Token</s>
Unk Token<unk>
Vocabulary Size32000
LoRA ModelYes
Torch Data Typefloat16

Best Alternatives to Saiga2 70B Lora GPTQ

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB22905
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB522
...ama 3.1 70B Instruct Gptq 4bit128K / 39.9 GB3544
Opus V1.2 70B Marlin32K / 36.4 GB140
MoMo 70B Lora 1.8.6 DPO GPTQ32K / 41.3 GB291
MoMo 70B Lora 1.8.4 DPO GPTQ32K / 41.3 GB281
Midnight Miqu 70B V1.5 GPTQ32G31K / 40.7 GB2353
Tess 70B V1.6 Marlin31K / 36.3 GB71
...Midnight Miqu 70B V1.0 GPTQ32G31K / 40.7 GB92
Senku 70B GPTQ 4bit31K / 36.7 GB81
Note: green Score (e.g. "73.2") means that the model is better than Komposter43/saiga2_70b_lora-GPTQ.

Rank the Saiga2 70B Lora 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? 40123 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241217