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")

# 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 / README.md

caikybaldo999

Full SFT WebCoder-100M-Instruct | 78,226,740 SFT tokens

062ffb1 verified about 22 hours ago

preview code

Raw

History Blame Contribute Delete

899 Bytes

	---
	language:
	- code
	library_name: transformers
	pipeline_tag: text-generation
	base_model: caikybaldo999/webcoder-100m-html-css-js
	tags:
	- html
	- css
	- javascript
	- instruct
	- sft
	---

	# 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
	```text
	<\|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.