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

Libraries

How to use skhatuya/tokenskip_test with PEFT:

from peft import PeftModel
from transformers import AutoModelForCausalLM

base_model = AutoModelForCausalLM.from_pretrained("deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B")
model = PeftModel.from_pretrained(base_model, "skhatuya/tokenskip_test")

Transformers

How to use skhatuya/tokenskip_test with Transformers:

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

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

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

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use skhatuya/tokenskip_test with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/skhatuya/tokenskip_test

SGLang

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

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

deepseek_Qwen_3B

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B on the mydataset_compressed_gsm8k_llmlingua2_qwen_3B dataset. It achieves the following results on the evaluation set:

Loss: 0.7736

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: 5e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 8
optimizer: Use OptimizerNames.ADAMW_TORCH 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: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.9263	0.4017	300	1.0222
0.7848	0.8035	600	0.8774
0.6880	1.2049	900	0.8267
0.6718	1.6066	1200	0.7993
0.7270	2.0080	1500	0.7799
0.6131	2.4098	1800	0.7756
0.6518	2.8115	2100	0.7738
0.6369	3.0	2241	0.7736

Framework versions

PEFT 0.18.1
Transformers 5.6.0
Pytorch 2.6.0+cu124
Datasets 3.1.0
Tokenizers 0.22.2

Downloads last month: 1

Model tree for skhatuya/tokenskip_test

Base model

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B

Adapter

(319)

this model