Instructions to use FirstPotatoCoder/KhmerLLM_full with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FirstPotatoCoder/KhmerLLM_full with Transformers:

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

pipe = pipeline("text-generation", model="FirstPotatoCoder/KhmerLLM_full")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("FirstPotatoCoder/KhmerLLM_full")
model = AutoModelForCausalLM.from_pretrained("FirstPotatoCoder/KhmerLLM_full")
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=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use FirstPotatoCoder/KhmerLLM_full with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/FirstPotatoCoder/KhmerLLM_full

SGLang

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

Docker Model Runner
How to use FirstPotatoCoder/KhmerLLM_full with Docker Model Runner:
```
docker model run hf.co/FirstPotatoCoder/KhmerLLM_full
```

FirstPotatoCoder commited on Jul 18, 2025

Commit

97e2c43

verified ·

1 Parent(s): 9e50765

Upload losses.json with huggingface_hub

Browse files

Files changed (1) hide show

losses.json +57 -0

losses.json ADDED Viewed

	@@ -0,0 +1,57 @@

+{
+  "epoch_1": {
+    "train": [
+      12.986456871032715,
+      8.242310097591936,
+      6.103185503936011,
+      4.625102449842721,
+      4.073614676530696,
+      5.594025807735348,
+      3.14445710261006,
+      2.8427582374289018,
+      2.6573131159317396,
+      2.5581798939665488,
+      2.487692332070721,
+      2.4221809978327475,
+      2.3744151996186944,
+      2.3369295461118713,
+      2.2947631965984,
+      2.2793206945923736,
+      2.235823899064182,
+      2.202956847711043,
+      2.1905788616700606,
+      2.1760405711891235,
+      2.147873802815587,
+      2.1373383323023143,
+      2.115493049109278,
+      2.093070942508288,
+      2.069805771457262,
+      2.071623833317402,
+      2.041620403281913,
+      2.0338821135276604,
+      2.027073261363447,
+      2.0037578815271044,
+      1.9955629202945173,
+      1.9807603455772085,
+      1.9763815410866226,
+      1.9703653786793227,
+      1.9624102986548557,
+      1.9408840425743545,
+      1.9266109708912116,
+      1.936342299477128,
+      1.9150524722643134,
+      1.9088118700941732,
+      1.9036740681356634,
+      1.878493307641715,
+      1.880729602585154,
+      1.8804447402638838,
+      1.8716453221218645,
+      1.8813945673713999,
+      1.8745401167672529,
+      1.8709548193561145,
+      1.8608385588511949,
+      1.8541411072754663,
+      1.8461788908509182
+    ]
+  }
+}