Instructions to use hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18 with Transformers:

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

pipe = pipeline("text-generation", model="hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18

SGLang

How to use hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18 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 "hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18" \
    --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": "hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18",
		"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 "hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18" \
        --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": "hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18 with Docker Model Runner:
```
docker model run hf.co/hosseinbv/newData-progressive-yoco-tiny-llama-CDL-18
```

newData-progressive-yoco-tiny-llama-CDL-18 / config.json

hosseinbv

Uploading /ephemeral/hossein/output/newData-progressive-yoco-tiny-llama-CDL-18

3ada004 verified over 1 year ago

raw

history blame contribute delete

705 Bytes

{"_name_or_path": "TinyLlama/TinyLlama_v1.1", "architectures": ["ProgressiveYocoLlamaForCausalLM"], "attention_bias": false, "attention_dropout": 0.0, "bos_token_id": 1, "crossDecoder_start_idx": 4, "eos_token_id": 2, "hidden_act": "silu", "hidden_size": 2048, "initializer_range": 0.02, "intermediate_size": 5632, "max_position_embeddings": 2048, "mlp_bias": false, "model_type": "progressive_yoco_llama", "num_attention_heads": 32, "num_hidden_layers": 22, "num_key_value_heads": 4, "pretraining_tp": 1, "rms_norm_eps": 1e-05, "rope_scaling": null, "rope_theta": 10000.0, "tie_word_embeddings": false, "torch_dtype": "bfloat16", "transformers_version": "4.45.2", "use_cache": false, "vocab_size": 32000}