jlesbegu/evalllm2025

jlesbegu/ evalllm2025_v2:latest

26 Downloads Updated 10 months ago

finetuned : python -m mlx_lm.lora --train --model mistralai/Mistral-7B-Instruct-v0.3 --batch-size 4 --fine-tune-type dora --iters 1000 --num-layers 16

tools

ollama run jlesbegu/evalllm2025_v2

curl http://localhost:11434/api/chat \
  -d '{
    "model": "jlesbegu/evalllm2025_v2",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='jlesbegu/evalllm2025_v2',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'jlesbegu/evalllm2025_v2',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Details

Updated 10 months ago

10 months ago

392f0d324aec · 14GB ·

model

archllama

parameters7.25B

quantizationF16

14GB

template

{{- if .Messages }} {{- range $index, $_ := .Messages }} {{- if eq .Role "user" }} {{- if and (eq (l

801B

system

Tu es un expert du vocabulaire de l'armée française.

56B

params

{ "stop": [ "[INST]", "[/INST]" ] }

30B

Readme

finetuned with the command: python -m mlx_lm.lora --train --model mistralai/Mistral-7B-Instruct-v0.3 --batch-size 4 --fine-tune-type dora --iters 1000 --num-layers 16