Instructions to use Ba2han/model-phase2-4096 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ba2han/model-phase2-4096 with Transformers:

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

pipe = pipeline("text-generation", model="Ba2han/model-phase2-4096")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Ba2han/model-phase2-4096")
model = AutoModelForCausalLM.from_pretrained("Ba2han/model-phase2-4096")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Ba2han/model-phase2-4096 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ba2han/model-phase2-4096"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ba2han/model-phase2-4096",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Ba2han/model-phase2-4096

SGLang

How to use Ba2han/model-phase2-4096 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 "Ba2han/model-phase2-4096" \
    --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": "Ba2han/model-phase2-4096",
		"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 "Ba2han/model-phase2-4096" \
        --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": "Ba2han/model-phase2-4096",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Unsloth Studio new

How to use Ba2han/model-phase2-4096 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 Ba2han/model-phase2-4096 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 Ba2han/model-phase2-4096 to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for Ba2han/model-phase2-4096 to start chatting

Load model with FastModel

pip install unsloth
from unsloth import FastModel
model, tokenizer = FastModel.from_pretrained(
    model_name="Ba2han/model-phase2-4096",
    max_seq_length=2048,
)

Docker Model Runner
How to use Ba2han/model-phase2-4096 with Docker Model Runner:
```
docker model run hf.co/Ba2han/model-phase2-4096
```

Ba2han commited on Dec 5, 2025

Commit

cda0032

verified ·

1 Parent(s): a831301

Training in progress, step 23500

Browse files

Files changed (3) hide show

README.md +3 -3
model.safetensors +1 -1
training_args.bin +1 -1

README.md CHANGED Viewed

@@ -5,8 +5,8 @@ model_name: model-phase2-4096
 tags:
 - generated_from_trainer
 - unsloth
-- sft
 - trl
 licence: license
 ---
@@ -28,7 +28,7 @@ print(output["generated_text"])
 ## Training procedure
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/wjh5bn9j)
 This model was trained with SFT.
@@ -37,7 +37,7 @@ This model was trained with SFT.
 - TRL: 0.24.0
 - Transformers: 4.57.2
-- Pytorch: 2.9.0
 - Datasets: 4.3.0
 - Tokenizers: 0.22.1

 tags:
 - generated_from_trainer
 - unsloth
 - trl
+- sft
 licence: license
 ---
 ## Training procedure
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/batuhan409/huggingface/runs/twlb3ka7)
 This model was trained with SFT.
 - TRL: 0.24.0
 - Transformers: 4.57.2
+- Pytorch: 2.9.1
 - Datasets: 4.3.0
 - Tokenizers: 0.22.1

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:489656f73a36f900e70f6beb14e3f1d339f3b46083c69974b32a5a1d2377f870
 size 1000555808

 version https://git-lfs.github.com/spec/v1
+oid sha256:4e68365d634df885e2ccb22b9e0405446541877ee8e62ec1302fff49e3c3e0cc
 size 1000555808

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efde65cd60c3637730e0c67040f557bc455d6373dd712ad06b1d4a101b477a1d
 size 6289

 version https://git-lfs.github.com/spec/v1
+oid sha256:47478d0364a9e5b4a3d11e4abd89537a080c247d5b4ca266aa2094c02d65ddf1
 size 6289