Instructions to use Lerelou/SmoLlm3python-3B_GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Lerelou/SmoLlm3python-3B_GGUF with PEFT:
Task type is invalid.
- Transformers
How to use Lerelou/SmoLlm3python-3B_GGUF with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Lerelou/SmoLlm3python-3B_GGUF")# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("Lerelou/SmoLlm3python-3B_GGUF", dtype="auto") - llama-cpp-python
How to use Lerelou/SmoLlm3python-3B_GGUF with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="Lerelou/SmoLlm3python-3B_GGUF", filename="smolpython-3B-Q4_K_M.gguf", )
output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- llama.cpp
How to use Lerelou/SmoLlm3python-3B_GGUF with llama.cpp:
Install from brew
brew install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Lerelou/SmoLlm3python-3B_GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Lerelou/SmoLlm3python-3B_GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama-server -hf Lerelou/SmoLlm3python-3B_GGUF:Q4_K_M # Run inference directly in the terminal: llama-cli -hf Lerelou/SmoLlm3python-3B_GGUF:Q4_K_M
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 Lerelou/SmoLlm3python-3B_GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Lerelou/SmoLlm3python-3B_GGUF:Q4_K_M
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 Lerelou/SmoLlm3python-3B_GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Lerelou/SmoLlm3python-3B_GGUF:Q4_K_M
Use Docker
docker model run hf.co/Lerelou/SmoLlm3python-3B_GGUF:Q4_K_M
- LM Studio
- Jan
- vLLM
How to use Lerelou/SmoLlm3python-3B_GGUF with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Lerelou/SmoLlm3python-3B_GGUF" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lerelou/SmoLlm3python-3B_GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/Lerelou/SmoLlm3python-3B_GGUF:Q4_K_M
- SGLang
How to use Lerelou/SmoLlm3python-3B_GGUF with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Lerelou/SmoLlm3python-3B_GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lerelou/SmoLlm3python-3B_GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Lerelou/SmoLlm3python-3B_GGUF" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Lerelou/SmoLlm3python-3B_GGUF", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Ollama
How to use Lerelou/SmoLlm3python-3B_GGUF with Ollama:
ollama run hf.co/Lerelou/SmoLlm3python-3B_GGUF:Q4_K_M
- Unsloth Studio new
How to use Lerelou/SmoLlm3python-3B_GGUF with Unsloth Studio:
Install Unsloth Studio (macOS, Linux, WSL)
curl -fsSL https://unsloth.ai/install.sh | sh # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Lerelou/SmoLlm3python-3B_GGUF to start chatting
Install Unsloth Studio (Windows)
irm https://unsloth.ai/install.ps1 | iex # Run unsloth studio unsloth studio -H 0.0.0.0 -p 8888 # Then open http://localhost:8888 in your browser # Search for Lerelou/SmoLlm3python-3B_GGUF to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Lerelou/SmoLlm3python-3B_GGUF to start chatting
- Docker Model Runner
How to use Lerelou/SmoLlm3python-3B_GGUF with Docker Model Runner:
docker model run hf.co/Lerelou/SmoLlm3python-3B_GGUF:Q4_K_M
- Lemonade
How to use Lerelou/SmoLlm3python-3B_GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Lerelou/SmoLlm3python-3B_GGUF:Q4_K_M
Run and chat with the model
lemonade run user.SmoLlm3python-3B_GGUF-Q4_K_M
List all available models
lemonade list
Update README.md
Browse files
README.md
CHANGED
|
@@ -1,43 +1,27 @@
|
|
| 1 |
---
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
language:
|
| 3 |
-
- fr
|
| 4 |
- en
|
| 5 |
-
base_model:
|
| 6 |
-
- Qwen/Qwen3-8B
|
| 7 |
---
|
| 8 |
---
|
| 9 |
-
#
|
| 10 |
|
| 11 |
-
##
|
| 12 |
|
| 13 |
-
|
| 14 |
|
| 15 |
-
##
|
| 16 |
|
| 17 |
-
* **Modèle de Base** : [
|
| 18 |
-
* **Méthode** : Fine-tuning avec
|
| 19 |
-
* **
|
| 20 |
-
|
| 21 |
-
## Comment Utiliser le Modèle
|
| 22 |
-
|
| 23 |
-
Pour utiliser ce modèle, il est essentiel d'utiliser un **système prompt** identique à celui de l'entraînement et de formater les prompts pour obtenir les meilleures performances.
|
| 24 |
-
A implémenté de cette manière :
|
| 25 |
-
|
| 26 |
-
## Limitations et Biases
|
| 27 |
-
Ce modèle est spécialisé en électronique et Arduino. Il peut donner des réponses moins pertinentes sur d'autres sujets.
|
| 28 |
-
|
| 29 |
-
Il a été entraîné avec un nombre limité d'exemples.
|
| 30 |
-
|
| 31 |
-
## Licence
|
| 32 |
-
Ce modèle est sous licence Tongyi Qianwen License Agreement. Pour plus de détails, veuillez consulter le fichier LICENSE.md dans ce dépôt.
|
| 33 |
-
|
| 34 |
-
## Comment Utiliser le Modèle
|
| 35 |
-
|
| 36 |
-
Pour utiliser ce modèle, il est essentiel d'utiliser un **système prompt** identique à celui de l'entraînement et de formater les prompts pour obtenir les meilleures performances.
|
| 37 |
-
Exemple :
|
| 38 |
-
```markdown
|
| 39 |
-
<|im_start|>system
|
| 40 |
-
Vous êtes un assistant IA appelé Brains spécialisé en composants électroniques et en programmation Arduino. Fournissez des réponses techniques, claires et précises. Limitez vos réponses à 1 à 3 phrases concises.<|im_end|>
|
| 41 |
-
<|im_start|>user
|
| 42 |
-
Quel est le rôle d'un condensateur ?<|im_end|>
|
| 43 |
-
<|im_start|>assistant
|
|
|
|
| 1 |
---
|
| 2 |
+
library_name: peft
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: HuggingFaceTB/SmolLM3-3B-Base
|
| 5 |
+
tags:
|
| 6 |
+
- axolotl
|
| 7 |
+
- base_model:adapter:HuggingFaceTB/SmolLM3-3B-Base
|
| 8 |
+
- lora
|
| 9 |
+
- transformers
|
| 10 |
+
datasets:
|
| 11 |
+
- mlabonne/Evol-Instruct-Python-26k
|
| 12 |
+
pipeline_tag: text-generation
|
| 13 |
language:
|
|
|
|
| 14 |
- en
|
|
|
|
|
|
|
| 15 |
---
|
| 16 |
---
|
| 17 |
+
# Model smolpython-3B_GGUF (Fine-Tuned HuggingFaceTB/SmolLM3-3B-Base)
|
| 18 |
|
| 19 |
+
## Model Description
|
| 20 |
|
| 21 |
+
This model is a fine-tuning of the HuggingFaceTB/SmolLM3-3B-Base model. It has been specialized for writing Python code.
|
| 22 |
|
| 23 |
+
## Training Details
|
| 24 |
|
| 25 |
+
* **Modèle de Base** : [HuggingFaceTB/SmolLM3-3B-Base](https://huggingface.co/HuggingFaceTB/SmolLM3-3B-Base)
|
| 26 |
+
* **Méthode** : Fine-tuning avec **Axolotl**.
|
| 27 |
+
* **Dataset** : [mlabonne/Evol-Instruct-Python-26k](https://huggingface.co/datasets/mlabonne/Evol-Instruct-Python-26k)
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|