Text Generation
PEFT
Safetensors
English
lora
unsloth
lfm2
code
pull-request
model-inversion
conversational
Instructions to use Codingstark/LFM2.5-350M-PR-Origin with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use Codingstark/LFM2.5-350M-PR-Origin with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("LiquidAI/LFM2.5-350M") model = PeftModel.from_pretrained(base_model, "Codingstark/LFM2.5-350M-PR-Origin") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Studio
How to use Codingstark/LFM2.5-350M-PR-Origin 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 Codingstark/LFM2.5-350M-PR-Origin 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 Codingstark/LFM2.5-350M-PR-Origin to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for Codingstark/LFM2.5-350M-PR-Origin to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="Codingstark/LFM2.5-350M-PR-Origin", max_seq_length=2048, )
File size: 513 Bytes
e82ccf1 | 1 2 3 4 5 6 7 8 9 10 | {
"title": "Handle retry exhaustion",
"body": "Return the last error after all attempts are exhausted.",
"branch": "feature/retry-exhaustion",
"commit_messages": [
"Handle retry exhaustion"
],
"diff": "diff --git a/retry.py b/retry.py\n--- a/retry.py\n+++ b/retry.py\n@@ -8,4 +8,7 @@ def run(operation):\n+ last_error = None\n for _ in range(3):\n try:\n return operation()\n+ except Exception as error:\n+ last_error = error\n+ raise last_error"
}
|