Instructions to use WilliamHH/Assignment2-modified-V2 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use WilliamHH/Assignment2-modified-V2 with Transformers:

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

pipe = pipeline("text-generation", model="WilliamHH/Assignment2-modified-V2")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("WilliamHH/Assignment2-modified-V2")
model = AutoModelForCausalLM.from_pretrained("WilliamHH/Assignment2-modified-V2")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use WilliamHH/Assignment2-modified-V2 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "WilliamHH/Assignment2-modified-V2"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "WilliamHH/Assignment2-modified-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/WilliamHH/Assignment2-modified-V2

SGLang

How to use WilliamHH/Assignment2-modified-V2 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 "WilliamHH/Assignment2-modified-V2" \
    --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": "WilliamHH/Assignment2-modified-V2",
		"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 "WilliamHH/Assignment2-modified-V2" \
        --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": "WilliamHH/Assignment2-modified-V2",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use WilliamHH/Assignment2-modified-V2 with Docker Model Runner:
```
docker model run hf.co/WilliamHH/Assignment2-modified-V2
```

WilliamHH commited on Sep 29, 2025

Commit

bbff4cc

verified ·

1 Parent(s): f17f2df

End of training

Browse files

Files changed (1) hide show

README.md +17 -23

README.md CHANGED Viewed

@@ -16,7 +16,7 @@ should probably proofread and complete it, then remove this comment. -->
 This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M) on an unknown dataset.
 It achieves the following results on the evaluation set:
-- Loss: 3.3182
 ## Model description
@@ -35,36 +35,30 @@ More information needed
 ### Training hyperparameters
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - 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
-- num_epochs: 3
 ### Training results
-| Training Loss | Epoch  | Step | Validation Loss |
-|:-------------:|:------:|:----:|:---------------:|
-| 3.5481        | 0.16   | 200  | 3.5522          |
-| 3.3347        | 0.32   | 400  | 3.4636          |
-| 3.2411        | 0.48   | 600  | 3.4149          |
-| 3.1745        | 0.64   | 800  | 3.3833          |
-| 3.1201        | 0.8    | 1000 | 3.3612          |
-| 3.1183        | 0.96   | 1200 | 3.3416          |
-| 2.9506        | 1.12   | 1400 | 3.3406          |
-| 2.8795        | 1.28   | 1600 | 3.3321          |
-| 2.8574        | 1.44   | 1800 | 3.3245          |
-| 2.8394        | 1.6    | 2000 | 3.3197          |
-| 2.8623        | 1.76   | 2200 | 3.3150          |
-| 2.8496        | 1.92   | 2400 | 3.3101          |
-| 2.7784        | 2.08   | 2600 | 3.3150          |
-| 2.7302        | 2.24   | 2800 | 3.3180          |
-| 2.7181        | 2.4    | 3000 | 3.3185          |
-| 2.729         | 2.56   | 3200 | 3.3186          |
-| 2.7404        | 2.7200 | 3400 | 3.3182          |
-| 2.7329        | 2.88   | 3600 | 3.3182          |
 ### Framework versions

 This model is a fine-tuned version of [HuggingFaceTB/SmolLM-135M](https://huggingface.co/HuggingFaceTB/SmolLM-135M) on an unknown dataset.
 It achieves the following results on the evaluation set:
+- Loss: 2.8719
 ## Model description
 ### Training hyperparameters
 The following hyperparameters were used during training:
+- learning_rate: 3e-05
 - train_batch_size: 8
 - eval_batch_size: 8
 - seed: 42
 - 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
+- num_epochs: 2
 ### Training results
+| Training Loss | Epoch | Step | Validation Loss |
+|:-------------:|:-----:|:----:|:---------------:|
+| 2.594         | 0.16  | 200  | 2.9858          |
+| 2.5675        | 0.32  | 400  | 2.9604          |
+| 2.5578        | 0.48  | 600  | 2.9417          |
+| 2.6641        | 0.64  | 800  | 2.9061          |
+| 2.6633        | 0.8   | 1000 | 2.8829          |
+| 2.6115        | 0.96  | 1200 | 2.8656          |
+| 2.4333        | 1.12  | 1400 | 2.8809          |
+| 2.3539        | 1.28  | 1600 | 2.8797          |
+| 2.3336        | 1.44  | 1800 | 2.8743          |
+| 2.334         | 1.6   | 2000 | 2.8731          |
+| 2.3502        | 1.76  | 2200 | 2.8723          |
+| 2.3205        | 1.92  | 2400 | 2.8719          |
 ### Framework versions