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 31

Commit

15c2ffb

verified ·

1 Parent(s): 2067ee7

Fix dead cross-link: sakthai-combined-v8 (404) -> sakthai-combined-v10 (normalized v7+v8)

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -20,7 +20,7 @@ tags:
 base_model: Qwen/Qwen2.5-1.5B-Instruct
 datasets:
 - Nanthasit/sakthai-combined-v7
-- Nanthasit/sakthai-combined-v8
 ---
 # SakThai Plus 1.5B — Merged
@@ -42,7 +42,7 @@ datasets:
 ## Model Description
-SakThai Plus 1.5B is the next-generation tool-calling model in the SakThai family. It uses **rsLoRA** (rank-stabilized LoRA) across **all 7 linear modules** (q, k, v, o, gate, up, down) with reduced dropout (0.05) and expanded training data (v7+v8, 2,962 rows). The result is a merged full-weight checkpoint that delivers improved instruction-following and tool-calling fidelity over the v1 generation.
 **Key improvements over v1:**
 - rsLoRA instead of standard LoRA — better rank utilization
@@ -101,7 +101,7 @@ llama-cli -m sakthai-plus-1.5b-Q4_K_M.gguf \
 | **LoRA alpha** | 32 |
 | **LoRA dropout** | 0.05 |
 | **Target modules** | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
-| **Training data** | Nanthasit/sakthai-combined-v7 + v8 (2,962 rows) |
 | **Optimizer** | AdamW (8-bit) |
 | **Learning rate** | 2e-4 |
 | **Epochs** | 3 |

 base_model: Qwen/Qwen2.5-1.5B-Instruct
 datasets:
 - Nanthasit/sakthai-combined-v7
+- Nanthasit/sakthai-combined-v10
 ---
 # SakThai Plus 1.5B — Merged
 ## Model Description
+SakThai Plus 1.5B is the next-generation tool-calling model in the SakThai family. It uses **rsLoRA** (rank-stabilized LoRA) across **all 7 linear modules** (q, k, v, o, gate, up, down) with reduced dropout (0.05) and expanded training data (v7+v8, 2,962 rows, published as [sakthai-combined-v10](https://huggingface.co/datasets/Nanthasit/sakthai-combined-v10)). The result is a merged full-weight checkpoint that delivers improved instruction-following and tool-calling fidelity over the v1 generation.
 **Key improvements over v1:**
 - rsLoRA instead of standard LoRA — better rank utilization
 | **LoRA alpha** | 32 |
 | **LoRA dropout** | 0.05 |
 | **Target modules** | q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj |
+| **Training data** | [sakthai-combined-v10](https://huggingface.co/datasets/Nanthasit/sakthai-combined-v10) (v7 + v8, 2,962 rows) |
 | **Optimizer** | AdamW (8-bit) |
 | **Learning rate** | 2e-4 |
 | **Epochs** | 3 |