LLM EXPLORER 59,420 MODELS INDEXED

EGTLM Qwen1.5 1.8B Instruct by selmisskilig

By selmisskilig · 3 downloads
HF Repo ↗ Copy URL

EGTLM Qwen1.5 1.8B Instruct is an open-source language model by selmisskilig. Features: 1.8b LLM, VRAM: 3.7GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.12.

  Conversational   Endpoints compatible   Instruct   Pytorch   Qwen2   Region:us
Model Card on HF 🤗: https://huggingface.co/selmisskilig/EGTLM-Qwen1.5-1.8B-instruct 

EGTLM Qwen1.5 1.8B Instruct Parameters and Internals

Model Type 
text generation, embedding
Supported Languages 
Chinese (good)
Training Details 
Methodology:
Hybrid task with instruction shunting and hybrid loss; Bidirectional attention mechanism; uses carefully generated and filtered embedding data and open-source dialogue data.
Context Length:
32000
Model Architecture:
Hybrid Embedding and text generation task model with bidirectional attention mechanism
LLM NameEGTLM Qwen1.5 1.8B Instruct
Repository 🤗https://huggingface.co/selmisskilig/EGTLM-Qwen1.5-1.8B-instruct 
Model Size1.8b
Required VRAM3.7 GB
Updated2026-07-28
Maintainerselmisskilig
Model Typeqwen2
Instruction-BasedYes
Model Files  3.7 GB   0.0 GB
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to EGTLM Qwen1.5 1.8B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Neural Chat Mini V2.2 1.8B32K / 3.7 GB106
Orca 2.0 Tau 1.8B32K / 3.7 GB1210
Sailor 1.8B Chat32K / 3.7 GB426
Nusantara 1.8B Indo Chat8K / 3.7 GB640
Note: green Score (e.g. "73.2") means that the model is better than selmisskilig/EGTLM-Qwen1.5-1.8B-instruct.