Instructions to use Jahirrrr/Klyra-64M-Midtrain with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Jahirrrr/Klyra-64M-Midtrain with Transformers:

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

pipe = pipeline("text-generation", model="Jahirrrr/Klyra-64M-Midtrain")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Jahirrrr/Klyra-64M-Midtrain", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Jahirrrr/Klyra-64M-Midtrain with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Jahirrrr/Klyra-64M-Midtrain"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Jahirrrr/Klyra-64M-Midtrain",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Jahirrrr/Klyra-64M-Midtrain

SGLang

How to use Jahirrrr/Klyra-64M-Midtrain 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 "Jahirrrr/Klyra-64M-Midtrain" \
    --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": "Jahirrrr/Klyra-64M-Midtrain",
		"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 "Jahirrrr/Klyra-64M-Midtrain" \
        --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": "Jahirrrr/Klyra-64M-Midtrain",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Jahirrrr/Klyra-64M-Midtrain with Docker Model Runner:
```
docker model run hf.co/Jahirrrr/Klyra-64M-Midtrain
```

Klyra-64M-Midtrain

Klyra-64M-Midtrain is the continued-pretraining checkpoint of Klyra-64M.

It starts from Klyra-64M-Base and adds approximately 2B additional tokens, bringing the cumulative pretraining + midtraining exposure to about 3B tokens.

Midtraining Mixture

Source	Approx. tokens
DCLM-Edu	720M
FineWeb-Edu	480M
Stack-Edu	500M
FineMath	120M
InfiMM-WebMath	80M
Cosmopedia v2	100M

Training used a 1,024-token context and BF16 precision.

Intended Use

This checkpoint is intended for:

continued pretraining,
downstream SFT,
domain adaptation,
experiments that need the strongest pre-instruction Klyra checkpoint.

It is not yet instruction tuned.

About Klyra

Klyra-64M is a compact language-model research project initiated and developed by a student of Informatics Engineering at Politeknik Negeri Jakarta (State Polytechnic of Jakarta).

The model uses a MiniMind-compatible decoder-only architecture and was trained through a staged pipeline from random initialization.

Main project: Jahirrrr/Klyra-64M

Architecture

Component	Value
Unique runtime parameters	~63.9M
Transformer layers	8
Hidden size	768
Attention heads	8
KV heads	4
Vocabulary	~6.4K
Context length	1,024
MoE	No

Parameter note: Klyra uses tied input/output embeddings at runtime. Some exported safetensors files may contain both model.embed_tokens.weight and lm_head.weight as separate serialized tensors. The intended runtime model has 63,912,192 unique parameters after weight tying.

Downloads last month: 282

Safetensors

Model size

68.8M params

Tensor type

F16

Collection including Jahirrrr/Klyra-64M-Midtrain

Klyra 64M

Collection

Klyra-64M is a compact 64M-parameter language model family trained from scratch. • 6 items • Updated 28 days ago