H2ogpt Mixtral 8x7b 32K AWQ by h2oai

 ยป  All LLMs  ยป  h2oai  ยป  H2ogpt Mixtral 8x7b 32K AWQ   URL Share it on

  4-bit   Autotrain compatible   Awq   Conversational   Endpoints compatible   Mixtral   Moe   Quantized   Region:us   Safetensors   Sharded   Tensorflow

H2ogpt Mixtral 8x7b 32K AWQ Benchmarks

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

H2ogpt Mixtral 8x7b 32K AWQ Parameters and Internals

LLM NameH2ogpt Mixtral 8x7b 32K AWQ
Repository ๐Ÿค—https://huggingface.co/h2oai/h2ogpt-mixtral-8x7b-32k-awq 
Model Size6.5b
Required VRAM24.7 GB
Updated2024-09-29
Maintainerh2oai
Model Typemixtral
Model Files  10.0 GB: 1-of-3   10.0 GB: 2-of-3   4.7 GB: 3-of-3
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureMixtralForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Vocabulary Size32000
Torch Data Typefloat16
H2ogpt Mixtral 8x7b 32K AWQ (h2oai/h2ogpt-mixtral-8x7b-32k-awq)

Best Alternatives to H2ogpt Mixtral 8x7b 32K AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Mixtral Instruct AWQ32K / 24.7 GB8439942
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB2048415
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB538757
Mixtral 8x7B Instruct V0.1 AWQ32K / 24.7 GB700
Dolphin 2.7 Mixtral 8x7b AWQ32K / 24.7 GB292520
...kaLM Mixtral 8x7B V0.2 DPO AWQ32K / 24.7 GB50
Karakuri Lm 8x7b Chat V0.1 AWQ32K / 24.7 GB230
Functionary Medium V2.4 AWQ32K / 24.7 GB193
Taiwan LLM 8x7B DPO AWQ32K / 24.7 GB51
... Hermes 2 Mixtral 8x7B DPO AWQ32K / 24.7 GB27521
Note: green Score (e.g. "73.2") means that the model is better than h2oai/h2ogpt-mixtral-8x7b-32k-awq.

Rank the H2ogpt Mixtral 8x7b 32K 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? 36371 in total.

Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Release v2024072803