LLM EXPLORER 64,561 MODELS INDEXED

WizardLM2 2bit by KingNish

By KingNish · 155 downloads
HF Repo ↗ Copy URL

WizardLM2 2bit is an open-source language model by KingNish. Features: LLM, VRAM: 4.8GB, Context: 64K, MoE, Quantized, LLM Explorer Score: 0.12.

  Arxiv:2304.12244   Arxiv:2306.08568   Arxiv:2308.09583   2-bit   2bit   Autotrain compatible Base model:mistral-community/m... Base model:quantized:mistral-c...   Conversational   Endpoints compatible   Gguf   Mistral   Mixtral   Moe   Quantized   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/KingNish/WizardLM2-2bit 

WizardLM2 2bit Parameters and Internals

Model Type 
text-generation
LLM NameWizardLM2 2bit
Repository 🤗https://huggingface.co/KingNish/WizardLM2-2bit 
Model NameWizardLM-2-8x22B-GGUF
Base Model(s)  mistral-community/Mixtral-8x22B-v0.1   mistral-community/Mixtral-8x22B-v0.1
Required VRAM4.8 GB
Updated2024-12-10
MaintainerKingNish
Model Typemixtral
Model Files  11.8 GB: 1-of-5   12.3 GB: 2-of-5   11.2 GB: 3-of-5   12.0 GB: 4-of-5   4.8 GB: 5-of-5
GGUF QuantizationYes
Quantization Typegguf|2bit
Model ArchitectureMixtralForCausalLM
Context Length65536
Model Max Length65536
Transformers Version4.36.2
Tokenizer ClassLlamaTokenizer
Padding Token<unk>
Vocabulary Size32000
Torch Data Typebfloat16

Best Alternatives to WizardLM2 2bit

Best Alternatives
Context / RAM
Downloads
Likes
NebulaNet V2 4x7B MoE32K / 8.8 GB1314
Dolphin 2.7 Mixtral 8x7b GGUF32K / 15.6 GB11625
Cerebrum 1.0 8x7b GGUF32K / 17.3 GB181
...Hermes 2 Mixtral 8x7B SFT GGUF32K / 17.3 GB7884
...ixtral 8x7B Instruct V0.1 GGUF32K / 17.3 GB5075
...Hermes 2 Mixtral 8x7B DPO GGUF32K / 17.3 GB2772
...oE V0.1 DPO F16 4.0bpw H6 EXL2195K / 31.3 GB70
...oE V0.1 DPO F16 5.0bpw H6 EXL2195K / 38.8 GB60
...2 Mixtral 8x22b 6.0bpw H8 EXL264K / 105.8 GB21
WizardLM 2 8x22 EXL2 4.0bpw64K / 70.9 GB71
Note: green Score (e.g. "73.2") means that the model is better than KingNish/WizardLM2-2bit.