Instructions to use LastTransformer/tinystarcoder-muon-sft-ddp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LastTransformer/tinystarcoder-muon-sft-ddp with Transformers:

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

pipe = pipeline("text-generation", model="LastTransformer/tinystarcoder-muon-sft-ddp")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("LastTransformer/tinystarcoder-muon-sft-ddp")
model = AutoModelForCausalLM.from_pretrained("LastTransformer/tinystarcoder-muon-sft-ddp", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LastTransformer/tinystarcoder-muon-sft-ddp with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/LastTransformer/tinystarcoder-muon-sft-ddp

SGLang

How to use LastTransformer/tinystarcoder-muon-sft-ddp 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 "LastTransformer/tinystarcoder-muon-sft-ddp" \
    --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": "LastTransformer/tinystarcoder-muon-sft-ddp",
		"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 "LastTransformer/tinystarcoder-muon-sft-ddp" \
        --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": "LastTransformer/tinystarcoder-muon-sft-ddp",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LastTransformer/tinystarcoder-muon-sft-ddp with Docker Model Runner:
```
docker model run hf.co/LastTransformer/tinystarcoder-muon-sft-ddp
```

LastTransformer commited on Jun 28

Commit

5e056c0

verified ·

1 Parent(s): eaf6778

Upload GPTBigCodeForCausalLM

Browse files

Files changed (2) hide show

config.json +1 -1
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -7,7 +7,7 @@
   "attention_softmax_in_fp32": true,
   "attn_pdrop": 0.1,
   "bos_token_id": 0,
-  "dtype": "float16",
   "embd_pdrop": 0.1,
   "eos_token_id": 0,
   "inference_runner": 0,

   "attention_softmax_in_fp32": true,
   "attn_pdrop": 0.1,
   "bos_token_id": 0,
+  "dtype": "float32",
   "embd_pdrop": 0.1,
   "eos_token_id": 0,
   "inference_runner": 0,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e764569769fcf42ad83f963c6b4ea59f8dc9e193f997687570f95247d55c6f0b
-size 328312936

 version https://git-lfs.github.com/spec/v1
+oid sha256:49591a865902adc93d5acee684adf796a4a4d7a45bb7ddd95e064ff3f83b9304
+size 656601304