Instructions to use Colby/tiny-starcoder-eluse with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Colby/tiny-starcoder-eluse with Transformers:

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

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

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Colby/tiny-starcoder-eluse")
model = AutoModelForCausalLM.from_pretrained("Colby/tiny-starcoder-eluse")
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]:]))

PEFT
How to use Colby/tiny-starcoder-eluse with PEFT:
```
Task type is invalid.
```
Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Colby/tiny-starcoder-eluse with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Colby/tiny-starcoder-eluse

SGLang

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

Docker Model Runner
How to use Colby/tiny-starcoder-eluse with Docker Model Runner:
```
docker model run hf.co/Colby/tiny-starcoder-eluse
```

Colby commited on Sep 26, 2024

Commit

3ccaa3c

verified ·

1 Parent(s): 5ee1c3b

Upload config.json

Browse files

Files changed (1) hide show

config.json +39 -0

config.json ADDED Viewed

	@@ -0,0 +1,39 @@

+{
+  "_name_or_path": "/fsx/bigcode/tinystarcoder/saves/large-model",
+  "activation_function": "gelu_pytorch_tanh",
+  "architectures": [
+    "GPTBigCodeForCausalLM"
+  ],
+  "attention_softmax_in_fp32": true,
+  "multi_query": true,
+  "attn_pdrop": 0.1,
+  "bos_token_id": 0,
+  "embd_pdrop": 0.1,
+  "eos_token_id": 0,
+  "inference_runner": 0,
+  "initializer_range": 0.02,
+  "layer_norm_epsilon": 1e-05,
+  "max_batch_size": null,
+  "max_sequence_length": null,
+  "model_type": "gpt_bigcode",
+  "n_embd": 768,
+  "n_head": 12,
+  "n_inner": 3072,
+  "n_layer": 20,
+  "n_positions": 8192,
+  "pad_key_length": true,
+  "pre_allocate_kv_cache": false,
+  "resid_pdrop": 0.1,
+  "scale_attention_softmax_in_fp32": true,
+  "scale_attn_weights": true,
+  "summary_activation": null,
+  "summary_first_dropout": 0.1,
+  "summary_proj_to_labels": true,
+  "summary_type": "cls_index",
+  "summary_use_proj": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.28.1",
+  "use_cache": true,
+  "validate_runner_input": true,
+  "vocab_size": 49152
+}