Instructions to use AngeloCurti22/StartCoder2_3b_sft with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AngeloCurti22/StartCoder2_3b_sft with Transformers:

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

pipe = pipeline("text-generation", model="AngeloCurti22/StartCoder2_3b_sft")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AngeloCurti22/StartCoder2_3b_sft")
model = AutoModelForCausalLM.from_pretrained("AngeloCurti22/StartCoder2_3b_sft")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use AngeloCurti22/StartCoder2_3b_sft with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AngeloCurti22/StartCoder2_3b_sft"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AngeloCurti22/StartCoder2_3b_sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/AngeloCurti22/StartCoder2_3b_sft

SGLang

How to use AngeloCurti22/StartCoder2_3b_sft 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 "AngeloCurti22/StartCoder2_3b_sft" \
    --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": "AngeloCurti22/StartCoder2_3b_sft",
		"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 "AngeloCurti22/StartCoder2_3b_sft" \
        --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": "AngeloCurti22/StartCoder2_3b_sft",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use AngeloCurti22/StartCoder2_3b_sft with Docker Model Runner:
```
docker model run hf.co/AngeloCurti22/StartCoder2_3b_sft
```

StartCoder2_3b_sft / config.json

AngeloCurti22

Upload Starcoder2ForCausalLM

8578da4 verified about 1 year ago

raw

history blame contribute delete

1.27 kB

	{
	"_name_or_path": "bigcode/starcoder2-3b",
	"architectures": [
	"Starcoder2ForCausalLM"
	],
	"attention_dropout": 0.1,
	"bos_token_id": 0,
	"embedding_dropout": 0.1,
	"eos_token_id": 0,
	"hidden_act": "gelu_pytorch_tanh",
	"hidden_size": 3072,
	"initializer_range": 0.018042,
	"intermediate_size": 12288,
	"max_position_embeddings": 16384,
	"mlp_type": "default",
	"model_type": "starcoder2",
	"norm_epsilon": 1e-05,
	"norm_type": "layer_norm",
	"num_attention_heads": 24,
	"num_hidden_layers": 30,
	"num_key_value_heads": 2,
	"quantization_config": {
	"_load_in_4bit": true,
	"_load_in_8bit": false,
	"bnb_4bit_compute_dtype": "bfloat16",
	"bnb_4bit_quant_storage": "uint8",
	"bnb_4bit_quant_type": "nf4",
	"bnb_4bit_use_double_quant": false,
	"llm_int8_enable_fp32_cpu_offload": false,
	"llm_int8_has_fp16_weight": false,
	"llm_int8_skip_modules": null,
	"llm_int8_threshold": 6.0,
	"load_in_4bit": true,
	"load_in_8bit": false,
	"quant_method": "bitsandbytes"
	},
	"residual_dropout": 0.1,
	"rope_scaling": null,
	"rope_theta": 999999.4420358813,
	"sliding_window": 4096,
	"torch_dtype": "float32",
	"transformers_version": "4.48.3",
	"use_bias": true,
	"use_cache": true,
	"vocab_size": 49152
	}