vanilj/phi-4-unsloth

vanilj/ phi-4-unsloth

6,858 Downloads Updated 1 year ago

The Phi 4 model with fixed tokenizer from Unsloth

ollama run vanilj/phi-4-unsloth

curl http://localhost:11434/api/chat \
  -d '{
    "model": "vanilj/phi-4-unsloth",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='vanilj/phi-4-unsloth',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'vanilj/phi-4-unsloth',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

8 models

Size

Context

Input

phi-4-unsloth:latest

8.9GB · 16K context window · Text · 1 year ago

phi-4-unsloth:latest

8.9GB

16K

Text

phi-4-unsloth:Q2_K_L

5.7GB · 16K context window · Text · 1 year ago

phi-4-unsloth:Q2_K_L

5.7GB

16K

Text

phi-4-unsloth:Q2_K

5.6GB · 16K context window · Text · 1 year ago

phi-4-unsloth:Q2_K

5.6GB

16K

Text

phi-4-unsloth:Q3_K_M

7.2GB · 16K context window · Text · 1 year ago

phi-4-unsloth:Q3_K_M

7.2GB

16K

Text

phi-4-unsloth:Q4_K_M

8.9GB · 16K context window · Text · 1 year ago

phi-4-unsloth:Q4_K_M

8.9GB

16K

Text

phi-4-unsloth:Q5_K_M

10GB · 16K context window · Text · 1 year ago

phi-4-unsloth:Q5_K_M

10GB

16K

Text

phi-4-unsloth:Q6_K

12GB · 16K context window · Text · 1 year ago

phi-4-unsloth:Q6_K

12GB

16K

Text

phi-4-unsloth:q8_0

16GB · 16K context window · Text · 1 year ago

phi-4-unsloth:q8_0

16GB

16K

Text

Readme

GGUF files: unsloth/phi-4-GGUF