Text Generation
PEFT
Safetensors
English
Russian
qwen
qwen3.5
lora
unsloth
trl
sft
code
reasoning
bilingual
obsidian
graphite
conversational
Instructions to use OpenReasonAI/Graphite1.0-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- PEFT
How to use OpenReasonAI/Graphite1.0-4B with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3.5-4B-Base") model = PeftModel.from_pretrained(base_model, "OpenReasonAI/Graphite1.0-4B") - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Unsloth Studio new
How to use OpenReasonAI/Graphite1.0-4B 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 OpenReasonAI/Graphite1.0-4B 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 OpenReasonAI/Graphite1.0-4B to start chatting
Using HuggingFace Spaces for Unsloth
# No setup required # Open https://huggingface.co/spaces/unsloth/studio in your browser # Search for OpenReasonAI/Graphite1.0-4B to start chatting
Load model with FastModel
pip install unsloth from unsloth import FastModel model, tokenizer = FastModel.from_pretrained( model_name="OpenReasonAI/Graphite1.0-4B", max_seq_length=2048, )
Starred commited on
Training in progress, step 2256
Browse files
adapter_model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 84972248
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:56a3911c8195f07e7729206b22c78ea087b1f7bcd68b544aea4342793450bd94
|
| 3 |
size 84972248
|