Instructions to use patdev/k3-a40-bootstrap with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use patdev/k3-a40-bootstrap with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf patdev/k3-a40-bootstrap:BF16 # Run inference directly in the terminal: llama cli -hf patdev/k3-a40-bootstrap:BF16
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf patdev/k3-a40-bootstrap:BF16 # Run inference directly in the terminal: llama cli -hf patdev/k3-a40-bootstrap:BF16
Use pre-built binary
# Download pre-built binary from: # https://github.com/ggerganov/llama.cpp/releases # Start a local OpenAI-compatible server with a web UI: ./llama-server -hf patdev/k3-a40-bootstrap:BF16 # Run inference directly in the terminal: ./llama-cli -hf patdev/k3-a40-bootstrap:BF16
Build from source code
git clone https://github.com/ggerganov/llama.cpp.git cd llama.cpp cmake -B build cmake --build build -j --target llama-server llama-cli # Start a local OpenAI-compatible server with a web UI: ./build/bin/llama-server -hf patdev/k3-a40-bootstrap:BF16 # Run inference directly in the terminal: ./build/bin/llama-cli -hf patdev/k3-a40-bootstrap:BF16
Use Docker
docker model run hf.co/patdev/k3-a40-bootstrap:BF16
- LM Studio
- Jan
- Ollama
How to use patdev/k3-a40-bootstrap with Ollama:
ollama run hf.co/patdev/k3-a40-bootstrap:BF16
- Unsloth Desktop
- Docker Model Runner
How to use patdev/k3-a40-bootstrap with Docker Model Runner:
docker model run hf.co/patdev/k3-a40-bootstrap:BF16
- Lemonade
How to use patdev/k3-a40-bootstrap with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull patdev/k3-a40-bootstrap:BF16
Run and chat with the model
lemonade run user.k3-a40-bootstrap-BF16
List all available models
lemonade list
- Atomic Chat
banc adapte a l image publique vllm
Browse files- banc_ada_controle.py +3 -3
banc_ada_controle.py
CHANGED
|
@@ -26,6 +26,7 @@ Reperes, meme depot `NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4` :
|
|
| 26 |
RTX 6000 Ada, notre pod, ctx 1M, all : 238,5 | 911 @16
|
| 27 |
"""
|
| 28 |
import json
|
|
|
|
| 29 |
import re
|
| 30 |
import statistics
|
| 31 |
import subprocess
|
|
@@ -34,7 +35,7 @@ import time
|
|
| 34 |
import urllib.request
|
| 35 |
|
| 36 |
MODEL = "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4"
|
| 37 |
-
PY =
|
| 38 |
PORT = 8000
|
| 39 |
URL = "http://127.0.0.1:%d" % PORT
|
| 40 |
|
|
@@ -54,8 +55,7 @@ dire("=" * 78)
|
|
| 54 |
|
| 55 |
# Recette NVIDIA mot pour mot, contexte 131072 : la MEME que le job Blackwell.
|
| 56 |
# Toute divergence ici invaliderait le controle.
|
| 57 |
-
BASE = [
|
| 58 |
-
"--model", MODEL,
|
| 59 |
"--served-model-name", "ornith",
|
| 60 |
"--host", "127.0.0.1", "--port", str(PORT),
|
| 61 |
"--trust-remote-code",
|
|
|
|
| 26 |
RTX 6000 Ada, notre pod, ctx 1M, all : 238,5 | 911 @16
|
| 27 |
"""
|
| 28 |
import json
|
| 29 |
+
import sys
|
| 30 |
import re
|
| 31 |
import statistics
|
| 32 |
import subprocess
|
|
|
|
| 35 |
import urllib.request
|
| 36 |
|
| 37 |
MODEL = "nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-NVFP4"
|
| 38 |
+
PY = sys.executable # image publique : pas de /opt/venv
|
| 39 |
PORT = 8000
|
| 40 |
URL = "http://127.0.0.1:%d" % PORT
|
| 41 |
|
|
|
|
| 55 |
|
| 56 |
# Recette NVIDIA mot pour mot, contexte 131072 : la MEME que le job Blackwell.
|
| 57 |
# Toute divergence ici invaliderait le controle.
|
| 58 |
+
BASE = ["vllm", "serve", MODEL,
|
|
|
|
| 59 |
"--served-model-name", "ornith",
|
| 60 |
"--host", "127.0.0.1", "--port", str(PORT),
|
| 61 |
"--trust-remote-code",
|