LLM EXPLORER 59,420 MODELS INDEXED

Opt 1.3B Gptq 4bit by iproskurina

By iproskurina · 7 downloads

Opt 1.3B Gptq 4bit is an open-source language model by iproskurina. Features: 1.3b LLM, VRAM: 1.1GB, Context: 2K, License: other, Quantized, LLM Explorer Score: 0.1.

  Arxiv:2210.17323   4bit   Autotrain compatible   Base model:facebook/opt-1.3b Base model:finetune:facebook/o...   Dataset:c4   En   Gptq   Opt   Pretrained   Quantized   Region:us   Safetensors

Opt 1.3B Gptq 4bit Parameters and Internals

Model Type 
opt, text-generation
Additional Notes 
Quantized by iproskurina using AutoGPTQ.
Supported Languages 
en (High)
LLM NameOpt 1.3B Gptq 4bit
Repository πŸ€—https://huggingface.co/iproskurina/opt-1.3b-gptq-4bit 
Model Nameopt-1.3b
Model Creatorfacebook
Base Model(s)  Opt 13B   facebook/opt-1.3b
Model Size1.3b
Required VRAM1.1 GB
Updated2024-09-23
Maintaineriproskurina
Model Typeopt
Model Files  1.1 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq|4bit
Model ArchitectureOPTForCausalLM
Licenseother
Context Length2048
Model Max Length2048
Transformers Version4.35.2
Tokenizer ClassGPT2Tokenizer
Padding Token<pad>
Vocabulary Size50272
Torch Data Typefloat16
Activation Functionrelu
Errorsreplace

Best Alternatives to Opt 1.3B Gptq 4bit

Best Alternatives
Context / RAM
Downloads
Likes
Opt 1.3B GPTQ 4bit G1282K / 1.1 GB110
LLmRa 1.3B V22K / 5.3 GB6640
Opt 1.3B2K / 2.6 GB121972185
Sparse0.5 OPT 1.32K / 2.6 GB8710
... Distilled PromptKD Dolly V1.02K / 2.6 GB70
New Galactica 1.3b Mcq2K / 2.6 GB50
... Galactica 1.3b DPO 0.1beta Ai2K / 2.6 GB41
New Galactica 1.3b Mcq Rag2K / 2.6 GB80
New Galactica 1.3b Mcq No Rag2K / 2.6 GB60
... Galactica 1.3b DPO 0.1beta Ai2K / 2.6 GB50
Note: green Score (e.g. "73.2") means that the model is better than iproskurina/opt-1.3b-gptq-4bit.