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

Mixtral 8x7B Instruct V0.1 AQLM 2Bit 1x16 Hf by ISTA-DASLab

 »  All LLMs  »  ISTA-DASLab  »  Mixtral 8x7B Instruct V0.1 AQLM 2Bit 1x16 Hf   URL Share it on

  69   
  Arxiv:2401.06118   2bit   Aqlm   Autotrain compatible   Conversational   Endpoints compatible   Instruct   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf 

Mixtral 8x7B Instruct V0.1 AQLM 2Bit 1x16 Hf Benchmarks

LLME Score: 0.1721
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Mixtral 8x7B Instruct V0.1 AQLM 2Bit 1x16 Hf (ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf)

Mixtral 8x7B Instruct V0.1 AQLM 2Bit 1x16 Hf Parameters and Internals

Model Type 
text generation
Additional Notes 
For quantization, 1 codebook of 16 bits was used.
LLM NameMixtral 8x7B Instruct V0.1 AQLM 2Bit 1x16 Hf
Repository 🤗https://huggingface.co/ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf 
Model Size6.5b
Required VRAM13.1 GB
Updated2025-02-05
MaintainerISTA-DASLab
Model Typemixtral
Instruction-BasedYes
Model Files  5.0 GB: 1-of-3   5.0 GB: 2-of-3   3.1 GB: 3-of-3
Quantization Type2bit
Model ArchitectureMixtralForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.38.0
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16

Best Alternatives to Mixtral 8x7B Instruct V0.1 AQLM 2Bit 1x16 Hf

Best Alternatives
Context / RAM
Downloads
Likes
Dolphin 2.7 Mixtral 8x7b AWQ32K / 24.7 GB636421
Mixtral Instruct AWQ32K / 24.7 GB437643
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB50
...utLM Mixtral 8x7B Instruct AWQ32K / 24.7 GB14162
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB36457
...xtral Instruct AWQ Clone Dec2332K / 24.7 GB80
...ixtral Instruct 8x7b Zloss AWQ32K / 24.7 GB102
...0.1 LimaRP ZLoss DARE TIES AWQ32K / 24.7 GB43
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB20715
...Instruct V0.1 LimaRP ZLoss AWQ32K / 24.7 GB71
Note: green Score (e.g. "73.2") means that the model is better than ISTA-DASLab/Mixtral-8x7B-Instruct-v0_1-AQLM-2Bit-1x16-hf.

Rank the Mixtral 8x7B Instruct V0.1 AQLM 2Bit 1x16 Hf 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? 42577 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