Juneup/internlm2.5_7b

Juneup/ internlm2.5_7b_distill

25 Downloads Updated 11 months ago

internlm2.5_7b_distill is a distill model of internlm2.5-7b-chat, trained with a 9k CoT dataset. "psy" refers to the model with psychological system prompt while "_orpo" refers to the model further trained with orpo on safety issues

ollama run Juneup/internlm2.5_7b_distill:orpo_q4_k_m

curl http://localhost:11434/api/chat \
  -d '{
    "model": "Juneup/internlm2.5_7b_distill:orpo_q4_k_m",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='Juneup/internlm2.5_7b_distill:orpo_q4_k_m',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'Juneup/internlm2.5_7b_distill:orpo_q4_k_m',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Models

View all →

Name

4 models

Size

Context

Input

internlm2.5_7b_distill:orpo_q4_k_m

4.7GB · 32K context window · Text · 11 months ago

internlm2.5_7b_distill:orpo_q4_k_m

4.7GB

32K

Text

internlm2.5_7b_distill:orpo_q8_0

8.2GB · 32K context window · Text · 11 months ago

internlm2.5_7b_distill:orpo_q8_0

8.2GB

32K

Text

internlm2.5_7b_distill:q4_k_m

4.7GB · 32K context window · Text · 11 months ago

internlm2.5_7b_distill:q4_k_m

4.7GB

32K

Text

internlm2.5_7b_distill:q8_0

8.2GB · 32K context window · Text · 11 months ago

internlm2.5_7b_distill:q8_0

8.2GB

32K

Text

Readme

No readme