Instructions to use Arittro2/grpo-checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Arittro2/grpo-checkpoints with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("unsloth/gemma-3-4b-it")
model = PeftModel.from_pretrained(base_model, "Arittro2/grpo-checkpoints")

Transformers

How to use Arittro2/grpo-checkpoints with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Arittro2/grpo-checkpoints")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Arittro2/grpo-checkpoints", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Arittro2/grpo-checkpoints with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Arittro2/grpo-checkpoints"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Arittro2/grpo-checkpoints",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Arittro2/grpo-checkpoints

SGLang

How to use Arittro2/grpo-checkpoints 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 "Arittro2/grpo-checkpoints" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Arittro2/grpo-checkpoints",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "Arittro2/grpo-checkpoints" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Arittro2/grpo-checkpoints",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Unsloth Desktop
Docker Model Runner
How to use Arittro2/grpo-checkpoints with Docker Model Runner:
```
docker model run hf.co/Arittro2/grpo-checkpoints
```

Arittro2 commited on Dec 4, 2025

Commit

cf98863

verified ·

1 Parent(s): e275b78

Upload folder using huggingface_hub

Browse files

Files changed (8) hide show

README.md +1 -1
adapter_config.json +4 -9
adapter_model.safetensors +1 -1
optimizer.pt +2 -2
rng_state.pth +1 -1
scheduler.pt +1 -1
trainer_state.json +0 -0
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -207,4 +207,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 [More Information Needed]
 ### Framework versions
-- PEFT 0.18.0

 [More Information Needed]
 ### Framework versions
+- PEFT 0.16.0

adapter_config.json CHANGED Viewed

@@ -1,7 +1,5 @@
 {
-  "alora_invocation_tokens": null,
   "alpha_pattern": {},
-  "arrow_config": null,
   "auto_mapping": {
     "base_model_class": "Gemma3ForConditionalGeneration",
     "parent_library": "transformers.models.gemma3.modeling_gemma3",
@@ -10,7 +8,6 @@
   "base_model_name_or_path": "unsloth/gemma-3-4b-it",
   "bias": "none",
   "corda_config": null,
-  "ensure_weight_tying": false,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
@@ -27,21 +24,19 @@
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
-  "peft_version": "0.18.0",
   "qalora_group_size": 16,
   "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "down_proj",
     "v_proj",
-    "gate_proj",
     "k_proj",
-    "o_proj",
     "up_proj",
-    "q_proj"
   ],
-  "target_parameters": null,
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,

 {
   "alpha_pattern": {},
   "auto_mapping": {
     "base_model_class": "Gemma3ForConditionalGeneration",
     "parent_library": "transformers.models.gemma3.modeling_gemma3",
   "base_model_name_or_path": "unsloth/gemma-3-4b-it",
   "bias": "none",
   "corda_config": null,
   "eva_config": null,
   "exclude_modules": null,
   "fan_in_fan_out": false,
   "megatron_core": "megatron.core",
   "modules_to_save": null,
   "peft_type": "LORA",
   "qalora_group_size": 16,
   "r": 32,
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "q_proj",
     "v_proj",
+    "down_proj",
     "k_proj",
     "up_proj",
+    "o_proj",
+    "gate_proj"
   ],
   "task_type": "CAUSAL_LM",
   "trainable_token_indices": null,
   "use_dora": false,

adapter_model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39416e56f085b4bd4692017e6d08f6e00902d1ed0688eb76c05a37aab0f5b423
 size 262406656

 version https://git-lfs.github.com/spec/v1
+oid sha256:4b8863a08a9e03e1385b1d8e43d6ceb78d559e59c3fd560051dd6c4ffea5ef01
 size 262406656

optimizer.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:290468d62ac7fb1f6ede41564c42c2c2ab8a9c75ac863de7e32e97c6e15449e0
-size 122872331

 version https://git-lfs.github.com/spec/v1
+oid sha256:3fd8fb0b9919222682bea835ce2ae0481fc1b0de959a33d4abb353b639eca7b1
+size 121633045

rng_state.pth CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afb4ac15ffccf801178d5786a8459b9990abd96e0d704db81c742dec6e0848f5
 size 14645

 version https://git-lfs.github.com/spec/v1
+oid sha256:a7f558d8446482efa60b14ceb530782da57f6ab2cf1d67c09fd1e5605f003a25
 size 14645

scheduler.pt CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:644c43a419e377e3e5016f5f85d0387179c5cbf9a34115954b9b8ec50c6d366a
 size 1465

 version https://git-lfs.github.com/spec/v1
+oid sha256:427c0c946dd9504d04f599e31438298f1906271364d5cb9e0d7a9a8880940c29
 size 1465

trainer_state.json CHANGED Viewed

The diff for this file is too large to render. See raw diff

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06b8aaf7531c31658bc348ea7261890de0a508e03bd1583a060f3f7aeaaafd4f
 size 7057

 version https://git-lfs.github.com/spec/v1
+oid sha256:ddb04574f7b9ade574879398471f2f78cd542b3e6ae301dc53991b01c8eb01df
 size 7057