Instructions to use codelion/dhara-250m-ar-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codelion/dhara-250m-ar-base with Transformers:

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

pipe = pipeline("text-generation", model="codelion/dhara-250m-ar-base", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("codelion/dhara-250m-ar-base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use codelion/dhara-250m-ar-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codelion/dhara-250m-ar-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codelion/dhara-250m-ar-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/codelion/dhara-250m-ar-base

SGLang

How to use codelion/dhara-250m-ar-base 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 "codelion/dhara-250m-ar-base" \
    --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": "codelion/dhara-250m-ar-base",
		"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 "codelion/dhara-250m-ar-base" \
        --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": "codelion/dhara-250m-ar-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use codelion/dhara-250m-ar-base with Docker Model Runner:
```
docker model run hf.co/codelion/dhara-250m-ar-base
```

dhara-250m-ar-base / config.json

codelion

Initial upload: Dhara-250M-AR-Base with Canon layers and 32K context

5965ce1 verified 5 months ago

Raw

History Blame Contribute Delete

891 Bytes

	{
	"architectures": [
	"DharaARForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "configuration_dhara_ar.DharaARConfig",
	"AutoModelForCausalLM": "modeling_dhara_ar.DharaARForCausalLM"
	},
	"attention_bias": false,
	"attention_dropout": 0.0,
	"canon_activation": false,
	"canon_bias": false,
	"canon_kernel": 4,
	"canon_residual": true,
	"canon_set": "ABCD",
	"dtype": "bfloat16",
	"hidden_act": "silu",
	"hidden_size": 768,
	"initializer_range": 0.02,
	"intermediate_size": 2176,
	"logit_softcap": 30.0,
	"max_position_embeddings": 32768,
	"mlp_bias": false,
	"model_type": "dhara_ar",
	"num_attention_heads": 12,
	"num_hidden_layers": 32,
	"num_key_value_heads": 4,
	"rms_norm_eps": 1e-06,
	"rope_theta": 8000000.0,
	"tie_word_embeddings": true,
	"transformers_version": "5.2.0",
	"use_logit_softcap": true,
	"use_qk_norm": true,
	"vocab_size": 49152
	}