fervent_mcclintock/Qwen2.5-RPG-15b-Test1

fervent_mcclintock/ Qwen2.5-RPG-15b-Test1

3 Downloads Updated 2 days ago

One of a few test models trained on character and worldbuilding. Need to learn some system prompt magic though. I have high hopes for this one. It sets great scenes and does pretty alright without agent control at managing a game.

tools

ollama run fervent_mcclintock/Qwen2.5-RPG-15b-Test1:Q4_0

curl http://localhost:11434/api/chat \
  -d '{
    "model": "fervent_mcclintock/Qwen2.5-RPG-15b-Test1:Q4_0",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='fervent_mcclintock/Qwen2.5-RPG-15b-Test1:Q4_0',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'fervent_mcclintock/Qwen2.5-RPG-15b-Test1:Q4_0',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

Name

8 models

Size

Context

Input

Qwen2.5-RPG-15b-Test1:Q4_0

8.5GB · 32K context window · Text · 2 days ago

Qwen2.5-RPG-15b-Test1:Q4_0

8.5GB

32K

Text

Qwen2.5-RPG-15b-Test1:Q4_K_S

8.6GB · 32K context window · Text · 2 days ago

Qwen2.5-RPG-15b-Test1:Q4_K_S

8.6GB

32K

Text

Qwen2.5-RPG-15b-Test1:Q4_K_M

9.0GB · 32K context window · Text · 2 days ago

Qwen2.5-RPG-15b-Test1:Q4_K_M

9.0GB

32K

Text

Qwen2.5-RPG-15b-Test1:Q5_0

10GB · 32K context window · Text · 2 days ago

Qwen2.5-RPG-15b-Test1:Q5_0

10GB

32K

Text

Qwen2.5-RPG-15b-Test1:Q5_K_S

10GB · 32K context window · Text · 2 days ago

Qwen2.5-RPG-15b-Test1:Q5_K_S

10GB

32K

Text

Qwen2.5-RPG-15b-Test1:Q5_K_M

11GB · 32K context window · Text · 2 days ago

Qwen2.5-RPG-15b-Test1:Q5_K_M

11GB

32K

Text

Qwen2.5-RPG-15b-Test1:Q6_K

12GB · 32K context window · Text · 2 days ago

Qwen2.5-RPG-15b-Test1:Q6_K

12GB

32K

Text

Qwen2.5-RPG-15b-Test1:Q8_0

16GB · 32K context window · Text · 2 days ago

Qwen2.5-RPG-15b-Test1:Q8_0

16GB

32K

Text

Readme

No readme