Instructions to use Ilides/cortex-0.3-0.02b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Ilides/cortex-0.3-0.02b with Transformers:

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

pipe = pipeline("text-generation", model="Ilides/cortex-0.3-0.02b", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Ilides/cortex-0.3-0.02b", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Ilides/cortex-0.3-0.02b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Ilides/cortex-0.3-0.02b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Ilides/cortex-0.3-0.02b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Ilides/cortex-0.3-0.02b

SGLang

How to use Ilides/cortex-0.3-0.02b 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 "Ilides/cortex-0.3-0.02b" \
    --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": "Ilides/cortex-0.3-0.02b",
		"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 "Ilides/cortex-0.3-0.02b" \
        --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": "Ilides/cortex-0.3-0.02b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Ilides/cortex-0.3-0.02b with Docker Model Runner:
```
docker model run hf.co/Ilides/cortex-0.3-0.02b
```

cortex-0.3-0.02b / tokenizer_config.json

Ilides

cortex-0.3-0.02b: export HF (sft step 2250, val 2.566) + model card + charts

f4e6a29 verified 25 days ago

Raw History Blame Contribute Delete

847 Bytes

{
  "tokenizer_class": "CortexTokenizer",
  "auto_map": {
    "AutoTokenizer": [
      "tokenization_cortex.CortexTokenizer",
      null
    ]
  },
  "model_max_length": 512,
  "bos_token": "<|endoftext|>",
  "eos_token": "<|endoftext|>",
  "pad_token": "<|pad|>",
  "unk_token": "<|unk|>",
  "additional_special_tokens": [
    "<|system|>",
    "<|user|>",
    "<|assistant|>",
    "<|end|>",
    "<|doc|>",
    "<|code|>"
  ],
  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}<|system|>\n{{ message['content'] }}\n<|end|>\n{% elif message['role'] == 'user' %}<|user|>\n{{ message['content'] }}\n<|end|>\n{% else %}<|assistant|>\n{{ message['content'] }}\n<|end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|assistant|>\n{% endif %}",
  "tokenizer_files": [
    "vocab.json",
    "merges.txt"
  ]
}

	{
	"tokenizer_class": "CortexTokenizer",
	"auto_map": {
	"AutoTokenizer": [
	"tokenization_cortex.CortexTokenizer",
	null
	]
	},
	"model_max_length": 512,
	"bos_token": "<\|endoftext\|>",
	"eos_token": "<\|endoftext\|>",
	"pad_token": "<\|pad\|>",
	"unk_token": "<\|unk\|>",
	"additional_special_tokens": [
	"<\|system\|>",
	"<\|user\|>",
	"<\|assistant\|>",
	"<\|end\|>",
	"<\|doc\|>",
	"<\|code\|>"
	],
	"chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}<\|system\|>\n{{ message['content'] }}\n<\|end\|>\n{% elif message['role'] == 'user' %}<\|user\|>\n{{ message['content'] }}\n<\|end\|>\n{% else %}<\|assistant\|>\n{{ message['content'] }}\n<\|end\|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<\|assistant\|>\n{% endif %}",
	"tokenizer_files": [
	"vocab.json",
	"merges.txt"
	]
	}