Instructions to use caikybaldo999/webcoder-100m-instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use caikybaldo999/webcoder-100m-instruct with Transformers:

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

pipe = pipeline("text-generation", model="caikybaldo999/webcoder-100m-instruct")

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

tokenizer = AutoTokenizer.from_pretrained("caikybaldo999/webcoder-100m-instruct")
model = AutoModelForCausalLM.from_pretrained("caikybaldo999/webcoder-100m-instruct", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use caikybaldo999/webcoder-100m-instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "caikybaldo999/webcoder-100m-instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "caikybaldo999/webcoder-100m-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/caikybaldo999/webcoder-100m-instruct

SGLang

How to use caikybaldo999/webcoder-100m-instruct 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 "caikybaldo999/webcoder-100m-instruct" \
    --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": "caikybaldo999/webcoder-100m-instruct",
		"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 "caikybaldo999/webcoder-100m-instruct" \
        --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": "caikybaldo999/webcoder-100m-instruct",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use caikybaldo999/webcoder-100m-instruct with Docker Model Runner:
```
docker model run hf.co/caikybaldo999/webcoder-100m-instruct
```

WebCoder-100M-Instruct

Instruction-tuned version of caikybaldo999/webcoder-100m-html-css-js specialized in HTML, CSS and JavaScript.

Training

Full SFT
Parameters: 99,894,528
Dataset: iamtarun/code_instructions_120k_alpaca filtered for web-development examples
Training examples: 30,032
Max sequence length: 1024
Tokens processed: 78,226,740
Supervised response tokens: 48,809,920

Loss is masked on system/user tokens and computed on assistant response tokens.

Prompt format

<|system|>
You are WebCoder...<|end|>
<|user|>
Create a responsive website...<|end|>
<|assistant|>
...

Limitations

This is a small ~100M parameter model. Review generated code before deployment.

Downloads last month: 10

Safetensors

Model size

99.9M params

Tensor type

BF16

Model tree for caikybaldo999/webcoder-100m-instruct

Base model

caikybaldo999/webcoder-100m-html-css-js

Finetuned

(1)

this model