Instructions to use cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100 with Transformers:

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

pipe = pipeline("text-generation", model="cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100")
model = AutoModelForCausalLM.from_pretrained("cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100

SGLang

How to use cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100 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 "cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100" \
    --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": "cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100",
		"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 "cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100" \
        --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": "cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100 with Docker Model Runner:
```
docker model run hf.co/cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100
```

Direct-OPD pilot — SFT-shifted base teacher (Phase 2)

deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B @ ad9f0ae0864d7fbcd1cd905e3c6c5b069cc8b562 supervised-fine-tuned for one pass over the 6400 pre-registered sft_train rows of cmpatino/direct-opd-sft-deepmath-pilot-data @ 22625ae5db434947195bf862c429cd94504a4809.

This is an experiment artifact of the Direct-OPD SFT-vs-RL policy-shift pilot: it is the SFT-shifted teacher whose divergence from the base teacher Phase 3/4 measures. It is not intended or evaluated as a general-purpose model.

Configuration (pre-registered)


steps / global batch	100 x 64 = 6400 examples (6400 rows available)
optimizer	AdamW lr 5e-06, betas (0.9, 0.95), eps 1e-08, wd 0.1 (no decay on 1-D params)
schedule	linear decay, 10 warmup steps, grad-norm clip 1.0
precision	fp32 master weights, autocast bf16 compute, bf16 checkpoints
max sequence	3072 tokens (prompt <= 1024, target + EOS <= 2048)
supervised tokens	10,950,054
seed	42 (data order `numpy.random.default_rng(42).permutation(n_train) [PCG64; NOT RandomState/MT19937], n_train=6400`)
attention	flash_attention_2 (requested `auto`)
target construction	completion-style: prompt via `add_generation_prompt=True`, target = `adapted_target` + EOS, prompt tokens masked with -100

checkpoint-20/ — optimizer step 20
checkpoint-40/ — optimizer step 40
checkpoint-60/ — optimizer step 60
checkpoint-80/ — optimizer step 80
checkpoint-100/ — optimizer step 100
repo root — same weights as checkpoint-100 (so from_pretrained works directly)
logs/run_manifest.json, logs/metrics.jsonl — full config, per-step metrics, tokenization statistics and every post-training assertion result

Tokenizer files are byte-identical to the base revision (asserted per checkpoint); the vocabulary and embedding matrices are never resized.

Reported numbers (see `logs/run_manifest.json` for the full record)

validation loss on the 512-row teacher_eval split: step 0 0.5155 -> step 20 0.4633 -> step 40 0.4469 -> step 60 0.4428 -> step 80 0.4413 -> step 100 0.4409
teacher-forced mean log-prob of the eval targets, base -> trained: -0.443386 -> -0.353899 (mean |delta| 0.089488 over 64 prompts)
post-training verification failures: []

Downloads last month: 20

Safetensors

Model size

2B params

Tensor type

BF16

Model tree for cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100

Base model

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

Finetuned

(661)

this model

cmpatino
/

DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100

Direct-OPD pilot — SFT-shifted base teacher (Phase 2)

Configuration (pre-registered)

Contents

Reported numbers (see `logs/run_manifest.json` for the full record)

Model tree for cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100

Direct-OPD pilot — SFT-shifted base teacher (Phase 2)

Configuration (pre-registered)

Contents

Reported numbers (see logs/run_manifest.json for the full record)

Model tree for cmpatino/DeepSeek-R1-Distill-Qwen-1.5B-DeepMath-SFT100

Reported numbers (see `logs/run_manifest.json` for the full record)