gurubot/Hermes-4.3-36B-GGUF:Q4_K

gurubot/ Hermes-4.3-36B-GGUF:Q4_K_M

228 Downloads Updated 1 month ago

somewhat uncensored, and quite creative.

ollama run gurubot/Hermes-4.3-36B-GGUF:Q4_K_M

curl http://localhost:11434/api/chat \
  -d '{
    "model": "gurubot/Hermes-4.3-36B-GGUF:Q4_K_M",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='gurubot/Hermes-4.3-36B-GGUF:Q4_K_M',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'gurubot/Hermes-4.3-36B-GGUF:Q4_K_M',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 1 month ago

1 month ago

b01f7d5d597e · 22GB ·

model

archseed_oss

parameters36.2B

quantizationQ4_K_M

22GB

template

{{ if .System }}<seed:bos><|start_header_id|>system<|end_header_id|> {{ .System }}<|eot_id|>{{ end }

264B

params

{ "stop": [ "<|start_header_id|>", "<|end_header_id|>", "<|eot_id|>",

108B

Readme

Hermes 4.3 36B is a frontier, hybrid-mode reasoning model based on ByteDance Seed 36B base

It’s not technically “uncensored” but is quite malleable, fairly creative and fits on a single 24GB GPU

For full details see source: https://huggingface.co/NousResearch/Hermes-4.3-36B-GGUF