Instructions to use FirstPotatoCoder/KhmerLLM_instruct_e3 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use FirstPotatoCoder/KhmerLLM_instruct_e3 with Transformers:

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

pipe = pipeline("text-generation", model="FirstPotatoCoder/KhmerLLM_instruct_e3")
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("FirstPotatoCoder/KhmerLLM_instruct_e3")
model = AutoModelForCausalLM.from_pretrained("FirstPotatoCoder/KhmerLLM_instruct_e3", 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 FirstPotatoCoder/KhmerLLM_instruct_e3 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "FirstPotatoCoder/KhmerLLM_instruct_e3"
# 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_instruct_e3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/FirstPotatoCoder/KhmerLLM_instruct_e3

SGLang

How to use FirstPotatoCoder/KhmerLLM_instruct_e3 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_instruct_e3" \
    --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_instruct_e3",
		"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_instruct_e3" \
        --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_instruct_e3",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use FirstPotatoCoder/KhmerLLM_instruct_e3 with Docker Model Runner:
```
docker model run hf.co/FirstPotatoCoder/KhmerLLM_instruct_e3
```

FirstPotatoCoder commited on Jul 24, 2025

Commit

4a927ad

verified ·

1 Parent(s): 351fe50

Upload losses.json with huggingface_hub

Browse files

Files changed (1) hide show

losses.json +146 -0

losses.json ADDED Viewed

	@@ -0,0 +1,146 @@

+{
+  "epoch_1": {
+    "train": [
+      5.271936893463135,
+      1.9609320962147132,
+      1.9740553322323673,
+      2.139290197198657,
+      2.247907088415043,
+      2.285330520112168,
+      2.2319649446604624,
+      2.243296389228891,
+      2.2536917634157314,
+      2.209015501663089,
+      2.226236399967928,
+      2.206922415883054,
+      2.178474697989185,
+      2.1676215355385198,
+      2.1512051139756836,
+      2.1398139397638873,
+      2.1226689175551607,
+      2.073150171520742,
+      2.1201384635516316,
+      2.076858220269551,
+      2.097028753606955
+    ],
+    "valid": [
+      1.1291518211364746,
+      2.067204667814784,
+      2.0799241820668994,
+      2.0836550180902953,
+      2.0208084501694366,
+      2.046902624599834,
+      2.048392039174816,
+      2.0523822885502425,
+      2.1093318052164953,
+      2.045438961157781,
+      2.0284024898543556,
+      2.0823902644132026,
+      2.068561091735789,
+      2.04120002024074,
+      2.110343912481808,
+      2.0642544958074738,
+      2.1391414723468825,
+      2.0862888607688728,
+      2.0415287822371653,
+      2.102056995770777,
+      2.0660724703349995
+    ]
+  },
+  "epoch_2": {
+    "train": [
+      1.1250828504562378,
+      1.6866733151915911,
+      1.6711480116874382,
+      1.6840804061046928,
+      1.68249223763249,
+      1.70828488573583,
+      1.6997642467125647,
+      1.6986137225569502,
+      1.680408867195601,
+      1.709202501557868,
+      1.7080492489857952,
+      1.6736224725515254,
+      1.68992514700654,
+      1.6553177957586642,
+      1.6625943104862362,
+      1.6536764682874687,
+      1.6486711747365426,
+      1.6435150859902639,
+      1.6376260894954808,
+      1.6223357702366303,
+      1.6161062715675782
+    ],
+    "valid": [
+      0.7614306211471558,
+      1.9096627201417553,
+      1.9389004737931965,
+      1.9154423076390314,
+      1.8614522431739837,
+      1.88988713721812,
+      1.8942808100932451,
+      1.904625305431424,
+      1.9441249492957111,
+      1.880363641469651,
+      1.8738720467448688,
+      1.9273116527401448,
+      1.9208439817446719,
+      1.8939266498324536,
+      1.9537830798118287,
+      1.8849086070242036,
+      1.9721769031009746,
+      1.9307436939654694,
+      1.8900886493037408,
+      1.9701839389683176,
+      1.899274163146436
+    ]
+  },
+  "epoch_3": {
+    "train": [
+      1.1513729095458984,
+      1.06434254796949,
+      1.0766028918489512,
+      1.0793594382199887,
+      1.0857450410320952,
+      1.0669733012674023,
+      1.0846032033410125,
+      1.081505761809043,
+      1.0676487164250952,
+      1.0597493878905535,
+      1.0608423910563107,
+      1.069292292146742,
+      1.044115708225306,
+      1.0520662938722887,
+      1.041138549011226,
+      1.0357335644956627,
+      1.022188963157729,
+      1.0211489132882372,
+      1.0403658007963787,
+      1.0455147695060618,
+      1.0299970061184738
+    ],
+    "valid": [
+      0.4119639992713928,
+      1.9787316288331616,
+      1.9904993831431457,
+      1.976195783329554,
+      1.9031735930889278,
+      1.9484034901052827,
+      1.9585362489232545,
+      1.9623318482827778,
+      1.998200187551658,
+      1.9331881993170474,
+      1.935898186022791,
+      1.9807388553601255,
+      1.978663128138495,
+      1.966193325392647,
+      2.0159074038607088,
+      1.926523634689389,
+      2.0204776920406537,
+      1.9855956211969426,
+      1.9435239793456554,
+      2.030767936896915,
+      1.9467219725081222
+    ]
+  }
+}