Instructions to use turtle170/TinyCode-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use turtle170/TinyCode-4B with Transformers:

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

pipe = pipeline("text-generation", model="turtle170/TinyCode-4B", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("turtle170/TinyCode-4B", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("turtle170/TinyCode-4B", trust_remote_code=True, 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use turtle170/TinyCode-4B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "turtle170/TinyCode-4B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "turtle170/TinyCode-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/turtle170/TinyCode-4B

SGLang

How to use turtle170/TinyCode-4B 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 "turtle170/TinyCode-4B" \
    --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": "turtle170/TinyCode-4B",
		"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 "turtle170/TinyCode-4B" \
        --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": "turtle170/TinyCode-4B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use turtle170/TinyCode-4B with Docker Model Runner:
```
docker model run hf.co/turtle170/TinyCode-4B
```

turtle170 commited on 13 days ago

Commit

4d90603

verified ·

1 Parent(s): b850892

Swap in TinyCode-4B-Vibe fine-tuned weights

Browse files

Files changed (4) hide show

config.json +1 -1
generation_config.json +1 -1
model.safetensors +1 -1
tokenizer_config.json +1 -1

config.json CHANGED Viewed

@@ -140,7 +140,7 @@
   },
   "sliding_window": 262144,
   "tie_word_embeddings": true,
-  "transformers_version": "5.8.1",
   "use_cache": false,
   "vocab_size": 200064
 }

   },
   "sliding_window": 262144,
   "tie_word_embeddings": true,
+  "transformers_version": "5.17.0",
   "use_cache": false,
   "vocab_size": 200064
 }

generation_config.json CHANGED Viewed

@@ -6,5 +6,5 @@
     199999
   ],
   "pad_token_id": 199999,
-  "transformers_version": "5.8.1"
 }

     199999
   ],
   "pad_token_id": 199999,
+  "transformers_version": "5.17.0"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39bf9eebac99925ab91a992d48e9035025ba89f36b81c0ba179069a0581e6054
 size 7672066248

 version https://git-lfs.github.com/spec/v1
+oid sha256:e799199feea72d3ea6be8c593751a88ad89ccb63285f73b290177f1bdda88baf
 size 7672066248

tokenizer_config.json CHANGED Viewed

@@ -4,7 +4,7 @@
   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
-  "is_local": false,
   "local_files_only": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",

   "bos_token": "<|endoftext|>",
   "clean_up_tokenization_spaces": false,
   "eos_token": "<|endoftext|>",
+  "is_local": true,
   "local_files_only": false,
   "model_max_length": 131072,
   "pad_token": "<|endoftext|>",