a iranian model named moein gts and it can speak too freindly and good at Encyclopedia!!makers are sohrevardi twins (ali sohrevardi arshiya sohrevardi)

ollama run arshiyasohrevardimoein/moeinGTS:3b-hermes

curl http://localhost:11434/api/chat \
  -d '{
    "model": "arshiyasohrevardimoein/moeinGTS:3b-hermes",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='arshiyasohrevardimoein/moeinGTS:3b-hermes',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'arshiyasohrevardimoein/moeinGTS:3b-hermes',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 month ago

1 month ago

982fa7287020 · 986MB

model

archqwen2

parameters1.54B

quantizationQ4_K_M

986MB

template

{{- if .Messages }} {{- range $index, $_ := .Messages }} {{- if eq .Role "system" }}<|im_start|>syst

772B

system

You are Hermes Agent, an autonomous AI agent powered by moeinGTS. You are equipped with step-by-step

225B

params

{ "stop": [ "<|im_start|>", "<|im_end|>", "</tool_call>" ], "tem

102B

Readme

language: - fa - en tags: - ollama - gguf - text-generation - qwen2 - moeingts

pipeline_tag: text-generation

moeinGTS 1.5B

moeinGTS is a compact, lightweight 1.5B parameter language model fine-tuned for fast, offline question-and-answering (Q&A) tasks based on Wikipedia and structured web datasets.

Optimized specifically for low-resource environments, this model delivers quick response times while keeping memory usage to a minimum.

Key Features

Parameter Size: 1.5 Billion
Quantization: Q4_K_M GGUF
Download Size: ~1 GB
VRAM/RAM Required: ~1.5 GB
Use Case: Local Q&A, general knowledge retrieval, fast text generation

Quickstart

Run the model directly using Ollama:

”`bash ollama run arshiyasohrevardimoein/moeinGTS

see model at hugging face : https://huggingface.co/arshiysohrevardi/moeinGTS1.5-1.5b