LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Saiga Llama3 70B Sft M1 D5 Abliterated Gptq 4bit by IlyaGusev

 »  All LLMs  »  IlyaGusev  »  Saiga Llama3 70B Sft M1 D5 Abliterated Gptq 4bit   URL Share it on

  15   
  4-bit   4bit   Autotrain compatible   Conversational   Endpoints compatible   Gptq   Llama   Quantized   Region:us
Model Card on HF 🤗: https://huggingface.co/IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_gptq_4bit 

Saiga Llama3 70b Sft M1 D5 Abliterated Gptq 4bit Benchmarks

LLME Score: 0.19299
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Saiga Llama3 70B Sft M1 D5 Abliterated Gptq 4bit (IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_gptq_4bit)

Saiga Llama3 70B Sft M1 D5 Abliterated Gptq 4bit Parameters and Internals

LLM NameSaiga Llama3 70b Sft M1 D5 Abliterated Gptq 4bit
Repository 🤗https://huggingface.co/IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_gptq_4bit 
Base Model(s)  ...ft M1 D5 Abliterated Kto M1 D2   IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_kto_m1_d2
Model Size70b
Required VRAM39.8 GB
Updated2025-02-22
MaintainerIlyaGusev
Model Typellama
Model Files  39.8 GB
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureLlamaForCausalLM
Context Length8192
Model Max Length8192
Transformers Version4.41.2
Tokenizer ClassPreTrainedTokenizerFast
Padding Token<|begin_of_text|>
Vocabulary Size128256
Torch Data Typefloat16

Best Alternatives to Saiga Llama3 70B Sft M1 D5 Abliterated Gptq 4bit

Best Alternatives
Context / RAM
Downloads
Likes
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB94136
...B Instruct AutoRound GPTQ 4bit128K / 39.9 GB13511
...ama 3.1 70B Instruct Gptq 4bit128K / 39.9 GB254
Opus V1.2 70B Marlin32K / 36.4 GB80
MoMo 70B Lora 1.8.4 DPO GPTQ32K / 41.3 GB281
MoMo 70B Lora 1.8.6 DPO GPTQ32K / 41.3 GB271
...Midnight Miqu 70B V1.0 GPTQ32G31K / 40.7 GB10832
Midnight Miqu 70B V1.5 GPTQ32G31K / 40.7 GB1683
Tess 70B V1.6 Marlin31K / 36.3 GB71
Senku 70B GPTQ 4bit31K / 36.7 GB31
Note: green Score (e.g. "73.2") means that the model is better than IlyaGusev/saiga_llama3_70b_sft_m1_d5_abliterated_gptq_4bit.

Rank the Saiga Llama3 70B Sft M1 D5 Abliterated Gptq 4bit Capabilities

🆘 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! 🌟

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.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241227
  Support LLM Explorer