Instructions to use modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora with Transformers:

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

pipe = pipeline("text-generation", model="modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora

SGLang

How to use modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora 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 "modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora" \
    --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": "modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora",
		"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 "modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora" \
        --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": "modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora with Docker Model Runner:
```
docker model run hf.co/modrill/qwen3_4b_base_kodcode4o_shortcot_8k_lora
```

modrill commited on 13 days ago

Commit

9adb64e

verified ·

1 Parent(s): 9ced64a

Update model card

Browse files

Files changed (1) hide show

README.md +9 -58

README.md CHANGED Viewed

@@ -1,64 +1,15 @@
 ---
-library_name: peft
-license: other
-base_model: Qwen/Qwen3-4B-Base
 tags:
-- base_model:adapter:Qwen/Qwen3-4B-Base
-- llama-factory
-- lora
-- transformers
-pipeline_tag: text-generation
-model-index:
-- name: qwen3-4b-base-kodcode4o-shortcot-8k-lora
-  results: []
 ---
-<!-- This model card has been generated automatically according to the information the Trainer had access to. You
-should probably proofread and complete it, then remove this comment. -->
-# qwen3-4b-base-kodcode4o-shortcot-8k-lora
-This model is a fine-tuned version of [Qwen/Qwen3-4B-Base](https://huggingface.co/Qwen/Qwen3-4B-Base) on the restart_kodcode4o_shortcot_conv_correct_fixed200k_8k dataset.
-## Model description
-More information needed
-## Intended uses & limitations
-More information needed
-## Training and evaluation data
-More information needed
-## Training procedure
-### Training hyperparameters
-The following hyperparameters were used during training:
-- learning_rate: 0.0001
-- train_batch_size: 2
-- eval_batch_size: 2
-- seed: 42
-- distributed_type: multi-GPU
-- num_devices: 4
-- gradient_accumulation_steps: 8
-- total_train_batch_size: 64
-- total_eval_batch_size: 8
-- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
-- lr_scheduler_type: cosine
-- lr_scheduler_warmup_steps: 0.05
-- num_epochs: 1.0
-### Training results
-### Framework versions
-- PEFT 0.18.1
-- Transformers 5.2.0
-- Pytorch 2.11.0+cu130
-- Datasets 4.0.0
-- Tokenizers 0.22.2

 ---
+license: cc-by-nc-4.0
 tags:
+- mhm
+- text-generation
+library_name: transformers
 ---
+# qwen3_4b_base_kodcode4o_shortcot_8k_lora
+Auto-uploaded by watcher (MergeBench excluded).
+- Source path: `LlamaFactory/saves/restart/qwen3-4b-base-kodcode4o-shortcot-8k-lora`
+- Uploaded at: `2026-05-25T14:48:25.300413`
+- Visibility: `public`