Instructions to use Nanthasit/sakthai-plus-1.5b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Nanthasit/sakthai-plus-1.5b with Transformers:

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

pipe = pipeline("text-generation", model="Nanthasit/sakthai-plus-1.5b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Nanthasit/sakthai-plus-1.5b")
model = AutoModelForCausalLM.from_pretrained("Nanthasit/sakthai-plus-1.5b", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Nanthasit/sakthai-plus-1.5b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Nanthasit/sakthai-plus-1.5b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Nanthasit/sakthai-plus-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Nanthasit/sakthai-plus-1.5b

SGLang

How to use Nanthasit/sakthai-plus-1.5b 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 "Nanthasit/sakthai-plus-1.5b" \
    --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": "Nanthasit/sakthai-plus-1.5b",
		"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 "Nanthasit/sakthai-plus-1.5b" \
        --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": "Nanthasit/sakthai-plus-1.5b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Nanthasit/sakthai-plus-1.5b with Docker Model Runner:
```
docker model run hf.co/Nanthasit/sakthai-plus-1.5b
```

Nanthasit commited on Jul 30

Commit

02fe9f4

verified ·

1 Parent(s): 67c84d3

Delete .eval_results/health-check-plus-1.5b-20260730.yaml with huggingface_hub

Browse files

Files changed (1) hide show

.eval_results/health-check-plus-1.5b-20260730.yaml +0 -142

.eval_results/health-check-plus-1.5b-20260730.yaml DELETED Viewed

@@ -1,142 +0,0 @@
-# Health Check Report
-# Generated: 2026-07-30T20:46:36Z
-# Cron: Free model health eval
-model:
-  id: Nanthasit/sakthai-plus-1.5b
-  private: false
-  gated: false
-  disabled: false
-  pipeline_tag: text-generation
-  library_name: transformers
-  base_model: Qwen/Qwen2.5-1.5B-Instruct
-  sha: 659d0e6f1be5e1d2d57f68d6e27d31e000b65b3f
-  architecture: Qwen2ForCausalLM
-  model_type: qwen2
-config:
-  hidden_size: 1536
-  num_attention_heads: 12
-  num_key_value_heads: 2
-  num_hidden_layers: 28
-  vocab_size: 151936
-  intermediate_size: 8960
-  max_position_embeddings: 32768
-  rms_norm_eps: 1e-06
-  torch_dtype: bfloat16
-  attention_dropout: 0.0
-  hidden_act: silu
-  tie_word_embeddings: true
-  use_cache: true
-  transformers_version: "5.14.1"
-  layer_count: 28
-  layer_types:
-    - full_attention (28 layers)
-  max_window_layers: 21
-  rope_parameters:
-    rope_theta: 1000000.0
-    rope_type: default
-  sliding_window: null
-  use_sliding_window: false
-  bos_token_id: 151643
-  eos_token_id: 151645
-  pad_token_id: null
-metrics:
-  downloads: 0
-  likes: 0
-  download_velocity_per_day: 0.0000
-  created_at: "2026-07-30T13:02:40.000Z"
-  last_modified: "2026-07-30T20:41:13.000Z"
-  days_since_creation: 0.3222
-  days_since_update: 0.0037
-  age_hours: 7.7
-  used_storage_bytes: 6186356180
-  used_storage_readable: "5.76 GB"
-  total_sibling_files: 15
-  storage_backend: xet
-tags:
-  - conversational
-  - en
-  - endpoints_compatible
-  - family
-  - function-calling
-  - house-of-sak
-  - license:apache-2.0
-  - merged
-  - plus
-  - qwen2
-  - qwen2.5
-  - rslor
-  - safetensors
-  - sakthai
-  - text-generation
-  - text-generation-inference
-  - tool-calling
-  - transformers
-datasets:
-  - Nanthasit/sakthai-combined-v7
-  - Nanthasit/sakthai-combined-v8
-base_models:
-  - Qwen/Qwen2.5-1.5B-Instruct
-  - Qwen/Qwen2.5-1.5B-Instruct
-  - finetune:Qwen/Qwen2.5-1.5B-Instruct
-inference:
-  gated: false
-  disabled: false
-  endpoints_compatible: true
-  text_generation_inference_compatible: true
-cards:
-  model_card_present: true
-  model_card_has_yaml: true
-  model_index_present: true
-  eval_results_present: true
-  eval_result_count: 7
-model_index:
-  task_type: "text-generation"
-  task_name: "Tool-Calling"
-  dataset: "SakThai Bench v2 (500 rows, scorer multiset-selection-v2)"
-  dataset_type: "Nanthasit/sakthai-bench-v2"
-  metrics:
-    Selection Accuracy: "pending (verified: false)"
-    Degenerate Rate: "0 (verified: false)"
-alerts:
-  - type: info
-    message: "Zero downloads since creation (7.7 hours old) — normal for newly published model."
-  - type: info
-    message: "Model uses Xet storage backend. File sizes returned as null via API; config.json retrieved separately."
-  - type: info
-    message: "Used storage: 5.76 GB (6,186,356,180 bytes)."
-  - type: info
-    message: "15 sibling files, including 1 safetensors shard and model card with YAML frontmatter + model-index."
-  - type: info
-    message: "Full_attention all 28 layers, 12 heads / 2 KV heads (GQA), 32K context, bfloat16, RoPE theta=1e6."
-health_score: 0.85
-health_breakdown:
-  availability: 1.00
-  documentation: 1.00
-  eval_results: 1.00
-  inference_ready: 1.00
-  metadata_completeness: 1.00
-  popularity: 0.00
-delta_since_previous_check:
-  previous_generated: "2026-07-30T20:40:35Z"
-  elapsed_minutes: 6.0
-  sha_changed: true
-  previous_sha: "0b23b60f8ac0"
-  new_sha: "659d0e6f1be5e1d2d57f68d6e27d31e000b65b3f"
-  downloads_delta: 0
-  likes_delta: 0
-  last_modified_updated: true
-  previous_last_modified: "2026-07-30T20:36:19Z"
-  new_last_modified: "2026-07-30T20:41:13.000Z"
-  sibling_count_unchanged: true