Instructions to use ThaiLLM/ThaiLLM-8B-MedApp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use ThaiLLM/ThaiLLM-8B-MedApp with Transformers:

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

pipe = pipeline("text-generation", model="ThaiLLM/ThaiLLM-8B-MedApp")
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("ThaiLLM/ThaiLLM-8B-MedApp")
model = AutoModelForCausalLM.from_pretrained("ThaiLLM/ThaiLLM-8B-MedApp", 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 ThaiLLM/ThaiLLM-8B-MedApp with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "ThaiLLM/ThaiLLM-8B-MedApp"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "ThaiLLM/ThaiLLM-8B-MedApp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/ThaiLLM/ThaiLLM-8B-MedApp

SGLang

How to use ThaiLLM/ThaiLLM-8B-MedApp 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 "ThaiLLM/ThaiLLM-8B-MedApp" \
    --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": "ThaiLLM/ThaiLLM-8B-MedApp",
		"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 "ThaiLLM/ThaiLLM-8B-MedApp" \
        --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": "ThaiLLM/ThaiLLM-8B-MedApp",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use ThaiLLM/ThaiLLM-8B-MedApp with Docker Model Runner:
```
docker model run hf.co/ThaiLLM/ThaiLLM-8B-MedApp
```

cankruscan commited on Aug 12

Commit

7b58a96

verified ·

1 Parent(s): b4a6b2c

Add files using upload-large-folder tool

Browse files

Files changed (3) hide show

README.md +18 -3
provenance.json +1 -1
release_manifest.json +4 -4

README.md CHANGED Viewed

@@ -141,7 +141,10 @@ model = AutoModelForCausalLM.from_pretrained(
 )
 messages = [
-    {"role": "user", "content": "ช่วยเตือนให้ฉันทานยาพรุ่งนี้เวลา 8 โมงเช้า"},
 ]
 inputs = tokenizer.apply_chat_template(
     messages,
@@ -152,6 +155,15 @@ outputs = model.generate(inputs, generation_config=model.generation_config)
 print(tokenizer.decode(outputs[0, inputs.shape[-1]:], skip_special_tokens=True))
 ```
 To load the original MedApp checkpoint, use `revision="v1.0.0"`.
 ## Serving with vLLM
@@ -167,8 +179,11 @@ vllm serve ThaiLLM/ThaiLLM-8B-MedApp \
 ```
 When `--generation-config vllm` is used, send the stabilized sampling values in
-each request. Validate tool names and arguments against your schema, obtain any
-required user authorization, and make tool execution idempotent where possible.
 ## Intended use

 )
 messages = [
+    {
+        "role": "user",
+        "content": "ฉันเป็นผู้ใหญ่ ช่วงนี้นอนไม่ค่อยหลับ ควรเริ่มดูแลตัวเองอย่างไร",
+    },
 ]
 inputs = tokenizer.apply_chat_template(
     messages,
 print(tokenizer.decode(outputs[0, inputs.shape[-1]:], skip_special_tokens=True))
 ```
+This basic Transformers example demonstrates conversation only. For structured
+tool calling, serve the model with an OpenAI-compatible endpoint and provide
+the request's JSON tool schema. When a request contains a relative time such as
+"tomorrow," the application must either provide a trusted current datetime
+and timezone or resolve the request to an explicit timezone-aware datetime
+before calling the model. Never execute a guessed or stale timestamp. Require
+RFC 3339 with a numeric UTC offset, validate the tool name and arguments
+against the schema, and obtain user authorization before execution.
 To load the original MedApp checkpoint, use `revision="v1.0.0"`.
 ## Serving with vLLM
 ```
 When `--generation-config vllm` is used, send the stabilized sampling values in
+each request. For relative dates and times, supply a trusted current datetime
+and timezone or request clarification; require a timezone-aware RFC 3339 value
+before execution. Validate tool names and arguments against your schema, obtain
+any required user authorization, reject stale or guessed timestamps, and make
+tool execution idempotent where possible.
 ## Intended use

provenance.json CHANGED Viewed

@@ -1,5 +1,5 @@
 {
-  "created_at": "2026-08-06T15:51:20.173283+00:00",
   "evaluation_binding": {
     "note": "Historical evaluation manifests recorded the selected model path but did not hash its weight files. This release manifest is the first content-addressed fingerprint of that selected output.",
     "release_manifest_created_after_evaluation": true,

 {
+  "created_at": "2026-08-12T11:44:16.000183+00:00",
   "evaluation_binding": {
     "note": "Historical evaluation manifests recorded the selected model path but did not hash its weight files. This release manifest is the first content-addressed fingerprint of that selected output.",
     "release_manifest_created_after_evaluation": true,

release_manifest.json CHANGED Viewed

@@ -1,11 +1,11 @@
 {
   "baseline_main_sha": "95e93ca22bf8fdc4d7124872615c1d5df002dfa4",
-  "created_at": "2026-08-06T15:51:33.406461+00:00",
   "files": [
     {
       "path": "README.md",
-      "sha256": "6713897d69dee7f72d141233c26d6c5bdaf2a1f6b21a59169999e25355e003bb",
-      "size": 8409
     },
     {
       "path": "added_tokens.json",
@@ -69,7 +69,7 @@
     },
     {
       "path": "provenance.json",
-      "sha256": "f8e451ef4227931099bb6e86948b2571a3a5ee8572f3ddfb35461233e254093f",
       "size": 1454
     },
     {

 {
   "baseline_main_sha": "95e93ca22bf8fdc4d7124872615c1d5df002dfa4",
+  "created_at": "2026-08-12T11:44:43.025697+00:00",
   "files": [
     {
       "path": "README.md",
+      "sha256": "6aaa0ed6bbc9c42dfdc7f984b806c141a6575e1e88a8182087ec245b4642a790",
+      "size": 9297
     },
     {
       "path": "added_tokens.json",
     },
     {
       "path": "provenance.json",
+      "sha256": "153dfb05cf67839cc1c26a4ded92b94995ce654a6a681bec88c67dc678575195",
       "size": 1454
     },
     {