Instructions to use AjayRangoji/AR-4B-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AjayRangoji/AR-4B-base with Transformers:

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

pipe = pipeline("text-generation", model="AjayRangoji/AR-4B-base", 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("AjayRangoji/AR-4B-base", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use AjayRangoji/AR-4B-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AjayRangoji/AR-4B-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AjayRangoji/AR-4B-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AjayRangoji/AR-4B-base

SGLang

How to use AjayRangoji/AR-4B-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 "AjayRangoji/AR-4B-base" \
    --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": "AjayRangoji/AR-4B-base",
		"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 "AjayRangoji/AR-4B-base" \
        --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": "AjayRangoji/AR-4B-base",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AjayRangoji/AR-4B-base with Docker Model Runner:
```
docker model run hf.co/AjayRangoji/AR-4B-base
```

AR-4B-base / config.json

AjayRangoji

Initial release: AR-4B base model, pretrained from scratch on ~325B tokens

226b931 verified 25 days ago

Raw History Blame Contribute Delete

793 Bytes

{
  "model_type": "ar",
  "architectures": [
    "ARForCausalLM"
  ],
  "auto_map": {
    "AutoConfig": "modeling_ar.ARConfigHF",
    "AutoModelForCausalLM": "modeling_ar.ARForCausalLM"
  },
  "vocab_size": 151936,
  "hidden_size": 2560,
  "intermediate_size": 9728,
  "num_hidden_layers": 36,
  "num_attention_heads": 32,
  "num_key_value_heads": 8,
  "head_dim": 128,
  "max_position_embeddings": 40960,
  "rope_theta": 1000000.0,
  "rms_norm_eps": 1e-06,
  "tie_word_embeddings": true,
  "torch_dtype": "bfloat16",
  "transformers_version": "4.40.0",
  "eos_token_id": 151645,
  "bos_token_id": 151645,
  "pad_token_id": 151643,
  "tokenizer_class": "Qwen2Tokenizer",
  "use_cache": true,
  "hidden_act": "silu",
  "attention_bias": false,
  "mlp_bias": false,
  "initializer_range": 0.02
}

	{
	"model_type": "ar",
	"architectures": [
	"ARForCausalLM"
	],
	"auto_map": {
	"AutoConfig": "modeling_ar.ARConfigHF",
	"AutoModelForCausalLM": "modeling_ar.ARForCausalLM"
	},
	"vocab_size": 151936,
	"hidden_size": 2560,
	"intermediate_size": 9728,
	"num_hidden_layers": 36,
	"num_attention_heads": 32,
	"num_key_value_heads": 8,
	"head_dim": 128,
	"max_position_embeddings": 40960,
	"rope_theta": 1000000.0,
	"rms_norm_eps": 1e-06,
	"tie_word_embeddings": true,
	"torch_dtype": "bfloat16",
	"transformers_version": "4.40.0",
	"eos_token_id": 151645,
	"bos_token_id": 151645,
	"pad_token_id": 151643,
	"tokenizer_class": "Qwen2Tokenizer",
	"use_cache": true,
	"hidden_act": "silu",
	"attention_bias": false,
	"mlp_bias": false,
	"initializer_range": 0.02
	}