Instructions to use prefixsliding/1.5B-v70 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use prefixsliding/1.5B-v70 with Transformers:

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

pipe = pipeline("text-generation", model="prefixsliding/1.5B-v70")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("prefixsliding/1.5B-v70")
model = AutoModelForCausalLM.from_pretrained("prefixsliding/1.5B-v70", 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 prefixsliding/1.5B-v70 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "prefixsliding/1.5B-v70"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "prefixsliding/1.5B-v70",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/prefixsliding/1.5B-v70

SGLang

How to use prefixsliding/1.5B-v70 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 "prefixsliding/1.5B-v70" \
    --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": "prefixsliding/1.5B-v70",
		"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 "prefixsliding/1.5B-v70" \
        --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": "prefixsliding/1.5B-v70",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use prefixsliding/1.5B-v70 with Docker Model Runner:
```
docker model run hf.co/prefixsliding/1.5B-v70
```

Muennighoff commited on Sep 12, 2025

Commit

7540e91

verified ·

1 Parent(s): d6a9600

Training in progress, step 200

Browse files

Files changed (4) hide show

README.md +7 -7
config.json +3 -3
model.safetensors +1 -1
training_args.bin +2 -2

README.md CHANGED Viewed

@@ -3,8 +3,8 @@ library_name: transformers
 model_name: 1.5B-v70
 tags:
 - generated_from_trainer
-- grpo
 - trl
 licence: license
 ---
@@ -26,25 +26,25 @@ 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/muennighoff/s2/runs/hsee6t4x)
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
 ### Framework versions
-- TRL: 0.22.0.dev0
-- Transformers: 4.55.4
-- Pytorch: 2.7.1
 - Datasets: 4.0.0
-- Tokenizers: 0.21.4
 ## Citations
 Cite GRPO as:
 ```bibtex
-@article{zhihong2024deepseekmath,
     title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
     author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
     year         = 2024,

 model_name: 1.5B-v70
 tags:
 - generated_from_trainer
 - trl
+- grpo
 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/muennighoff/s2/runs/w2qkgot7)
 This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
 ### Framework versions
+- TRL: 0.23.0
+- Transformers: 4.56.1
+- Pytorch: 2.9.0.dev20250827+cu128
 - Datasets: 4.0.0
+- Tokenizers: 0.22.0
 ## Citations
 Cite GRPO as:
 ```bibtex
+@article{shao2024deepseekmath,
     title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
     author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
     year         = 2024,

config.json CHANGED Viewed

@@ -4,7 +4,7 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 151643,
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
@@ -47,13 +47,13 @@
   "num_attention_heads": 16,
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000,
   "sliding_window": 2048,
   "tie_word_embeddings": true,
-  "torch_dtype": "bfloat16",
-  "transformers_version": "4.55.4",
   "use_cache": false,
   "use_sliding_window": true,
   "vocab_size": 151936

   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "dtype": "bfloat16",
   "eos_token_id": 151645,
   "head_dim": 128,
   "hidden_act": "silu",
   "num_attention_heads": 16,
   "num_hidden_layers": 28,
   "num_key_value_heads": 8,
+  "pad_token_id": 151643,
   "rms_norm_eps": 1e-06,
   "rope_scaling": null,
   "rope_theta": 1000000,
   "sliding_window": 2048,
   "tie_word_embeddings": true,
+  "transformers_version": "4.56.1",
   "use_cache": false,
   "use_sliding_window": true,
   "vocab_size": 151936

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7b33577942909baf86426e784ef537737af0a75f2f89795c0f949ce41008e3e3
 size 4063515640

 version https://git-lfs.github.com/spec/v1
+oid sha256:d12a2b7919c43995d2ad6e1603ec1f1150f8a41a2d085f40c99f8acf5c4af8d2
 size 4063515640

training_args.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed933f9c05a8ada746dbb8c66c369b397f60efaae9c0c437ef3dacf8c75eb89a
-size 8785

 version https://git-lfs.github.com/spec/v1
+oid sha256:53ad4311ec5aa3db3dcbd4c3687f3b087eb8e2d880b7a90246033265773839b7
+size 8977