Instructions to use JonathanMiddleton/daisy-milli-18.11 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use JonathanMiddleton/daisy-milli-18.11 with Transformers:

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

pipe = pipeline("text-generation", model="JonathanMiddleton/daisy-milli-18.11")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("JonathanMiddleton/daisy-milli-18.11", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use JonathanMiddleton/daisy-milli-18.11 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "JonathanMiddleton/daisy-milli-18.11"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "JonathanMiddleton/daisy-milli-18.11",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/JonathanMiddleton/daisy-milli-18.11

SGLang

How to use JonathanMiddleton/daisy-milli-18.11 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 "JonathanMiddleton/daisy-milli-18.11" \
    --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": "JonathanMiddleton/daisy-milli-18.11",
		"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 "JonathanMiddleton/daisy-milli-18.11" \
        --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": "JonathanMiddleton/daisy-milli-18.11",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use JonathanMiddleton/daisy-milli-18.11 with Docker Model Runner:
```
docker model run hf.co/JonathanMiddleton/daisy-milli-18.11
```

daisy-milli-18.11 / config.json

JonathanMiddleton

Add files using upload-large-folder tool

49ab70f verified 6 months ago

Raw

History Blame Contribute Delete

659 Bytes

	{
	"architectures": [
	"DaisyForCausalLM"
	],
	"attn_all_layers": true,
	"attn_impl": "standard",
	"bos_token_id": 49131,
	"dtype": "float32",
	"eos_token_id": 49131,
	"eot_token_id": 49134,
	"head_dim": 128,
	"kd_alpha": null,
	"kd_eps": null,
	"kd_temperature": null,
	"max_position_embeddings": 131072,
	"model_dim": 1792,
	"model_type": "daisy",
	"num_heads": 14,
	"num_layers": 26,
	"padded_embeddings": false,
	"skip_mix_mode": "linear",
	"tokenizer_name": "jonathanmiddleton/daisy",
	"transformers_version": "5.2.0",
	"use_tied_embeddings": false,
	"use_value_embeddings": true,
	"vocab_size": 49152,
	"window_size": 2048
	}