Instructions to use sajalregmi4/arkios-1b-base with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use sajalregmi4/arkios-1b-base with Transformers:

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

pipe = pipeline("text-generation", model="sajalregmi4/arkios-1b-base")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("sajalregmi4/arkios-1b-base")
model = AutoModelForCausalLM.from_pretrained("sajalregmi4/arkios-1b-base", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use sajalregmi4/arkios-1b-base with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "sajalregmi4/arkios-1b-base"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "sajalregmi4/arkios-1b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/sajalregmi4/arkios-1b-base

SGLang

How to use sajalregmi4/arkios-1b-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 "sajalregmi4/arkios-1b-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": "sajalregmi4/arkios-1b-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 "sajalregmi4/arkios-1b-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": "sajalregmi4/arkios-1b-base",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use sajalregmi4/arkios-1b-base with Docker Model Runner:
```
docker model run hf.co/sajalregmi4/arkios-1b-base
```

sajalregmi4 commited on Aug 30

Commit

b008bf5

verified ·

1 Parent(s): 199b751

Add base model weights

Browse files

Files changed (5) hide show

config.json +22 -0
model.safetensors +3 -0
special_tokens_map.json +6 -0
tokenizer.json +0 -0
tokenizer_config.json +9 -0

config.json ADDED Viewed

	@@ -0,0 +1,22 @@

+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "model_type": "qwen3",
+  "hidden_size": 2048,
+  "intermediate_size": 6144,
+  "num_hidden_layers": 18,
+  "num_attention_heads": 16,
+  "num_key_value_heads": 8,
+  "head_dim": 128,
+  "vocab_size": 65536,
+  "max_position_embeddings": 4096,
+  "rope_theta": 1000000.0,
+  "rms_norm_eps": 1e-06,
+  "tie_word_embeddings": true,
+  "hidden_act": "silu",
+  "attention_bias": false,
+  "torch_dtype": "float32",
+  "bos_token_id": 65510,
+  "eos_token_id": 65511
+}

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a673023c1f96129eb01c17d0240d1b8b37f021bf2318a3cc73f9f63a51d33aae
+size 4161093840

special_tokens_map.json ADDED Viewed

	@@ -0,0 +1,6 @@

+{
+  "bos_token": "<|bos|>",
+  "eos_token": "<|eos|>",
+  "pad_token": "<|eos|>",
+  "additional_special_tokens": ["<|im_start|>", "<|im_end|>", "<tool_call>", "</tool_call>", "<tool_response>", "</tool_response>"]
+}

tokenizer.json ADDED Viewed

The diff for this file is too large to render. See raw diff

tokenizer_config.json ADDED Viewed

	@@ -0,0 +1,9 @@

+{
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "bos_token": "<|bos|>",
+  "eos_token": "<|eos|>",
+  "pad_token": "<|eos|>",
+  "model_max_length": 4096,
+  "clean_up_tokenization_spaces": false,
+  "add_bos_token": false
+}