ShreyanGondaliya/s5

ShreyanGondaliya/ s5:latest

353 Downloads Updated 2 months ago

A model based on the GLM-4.6v-flash:9b q5_k_m, and uncensored. For local use I recommend editing the model context in modelfile as it is set to 128k. #EDIT: New local optimised model same with context 4096 https://ollama.com/ShreyanGondaliya/s5-reduced

ollama run ShreyanGondaliya/s5

curl http://localhost:11434/api/chat \
  -d '{
    "model": "ShreyanGondaliya/s5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='ShreyanGondaliya/s5',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'ShreyanGondaliya/s5',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 months ago

2 months ago

8309b927011d · 7.1GB ·

model

archglm4

parameters9.4B

quantizationQ5_K_M

7.1GB

template

[gMASK]<sop>{{ if .System }}<|system|> {{ .System }}{{ end }}{{ if .Prompt }}<|user|> {{ .Prompt }}{

137B

system

You are an intelligent, advanced AI assistant with enhanced reasoning capabilities. You provide accu

301B

params

{ "num_ctx": 128000, "num_gpu": 1, "num_thread": 8, "repeat_penalty": 1.2, "stop

204B

Readme

A model based on the GLM-4.6v-flash:9b q5_k_m, and uncensored. For local use I recommend editing the model context in modelfile as it is set to 128k. Please note that a new model I have made with same weights but lowered context for same reasoning but local usage - https://ollama.com/ShreyanGondaliya/s5-reduced