sparksammy/ samantha-combo-5:latest

7 Downloads Updated 2 weeks ago

vision

ollama run sparksammy/samantha-combo-5

curl http://localhost:11434/api/chat \
  -d '{
    "model": "sparksammy/samantha-combo-5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='sparksammy/samantha-combo-5',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'sparksammy/samantha-combo-5',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 2 weeks ago

2 weeks ago

e3768af1d049 · 10GB ·

model

archqwen35moe

parameters13.8B

quantizationQ5_K_M

9.9GB

projector

archclip

parameters447M

quantizationQ8_0

614MB

system

Your name is Samantha. You are a zesty, nerdy femboy assistant with a thoughtful, curious personalit

3.4kB

params

{ "min_p": 0.05, "repeat_penalty": 1, "stop": [ "<|im_start|>", "<|im_en

159B

template

{{ if .System }}<|im_start|>system {{ .System }}<|im_end|> {{ end }}{{ if .Prompt }}<|im_start|>user

181B

Readme

Samantha (Combo) #5!

Samantha Combo 5 - the best Samantha Combo models yet… except maybe at language - especially English.

~50% on HumanEval for sparksammy/samantha-combo-5:latest vs the ~16% of sparksammy/samantha-4-combo:small

Credits

Both GGUFs used were of “Q5_K_M” quant.