Instructions to use properly59/Jumini-Ko-1.2B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use properly59/Jumini-Ko-1.2B with Transformers:

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

pipe = pipeline("text-generation", model="properly59/Jumini-Ko-1.2B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("properly59/Jumini-Ko-1.2B")
model = AutoModelForCausalLM.from_pretrained("properly59/Jumini-Ko-1.2B", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use properly59/Jumini-Ko-1.2B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "properly59/Jumini-Ko-1.2B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "properly59/Jumini-Ko-1.2B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/properly59/Jumini-Ko-1.2B

SGLang

How to use properly59/Jumini-Ko-1.2B 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 "properly59/Jumini-Ko-1.2B" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "properly59/Jumini-Ko-1.2B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "properly59/Jumini-Ko-1.2B" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "properly59/Jumini-Ko-1.2B",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use properly59/Jumini-Ko-1.2B with Docker Model Runner:
```
docker model run hf.co/properly59/Jumini-Ko-1.2B
```

properly59 commited on Jun 2

Commit

a586bc6

verified ·

1 Parent(s): e287a3c

Update model card with final V3B rejection audit

Browse files

Files changed (1) hide show

README.md +14 -1

README.md CHANGED Viewed

@@ -32,6 +32,8 @@ The model code, tokenizer pipeline, data filters, training loop, checkpointing,
 The current export candidate is the V3A retention step-6200 checkpoint. A later low-LR response-only SFT pilot improved SFT validation loss but was not promoted because it did not improve generation or mini-MCQ and degraded all source-bucket losses.
 ## Local Validation
 Train-time held-out validation on the V3A retention split improved monotonically through step 6200:
@@ -45,7 +47,7 @@ Train-time held-out validation on the V3A retention split improved monotonically
 | 6100 | 4.2970 | 73.48 |
 | 6200 | 4.2950 | 73.33 |
-Source-bucket validation at step 6200:
 | Source | loss | perplexity |
 | --- | ---: | ---: |
@@ -68,11 +70,22 @@ Diagnostic results:
 | BELEBELE-KOR subset | 47/200 |
 | GSM8K-Ko subset | 0/100 |
 ## Export Checks
 - Native-vs-HF logits equivalence: `ok=true`, max absolute diff `0.015625`, argmax mismatch rate `0.0`.
 - Local Transformers smoke: `AutoConfig`, `AutoTokenizer`, and `AutoModelForCausalLM` load without custom code as `LlamaForCausalLM`.
 - Local parameter count after HF load: `1,260,505,088`.
 ## Intended Use

 The current export candidate is the V3A retention step-6200 checkpoint. A later low-LR response-only SFT pilot improved SFT validation loss but was not promoted because it did not improve generation or mini-MCQ and degraded all source-bucket losses.
+Additional post-export probes were also rejected. A V3B TinyStories low-ratio probe improved its own validation split from step 6200 to step 6300, but it did not beat step 6200 on a same-condition source-bucket comparison and generation remained repetitive/malformed. The exported artifact therefore remains the V3A step-6200 base checkpoint.
 ## Local Validation
 Train-time held-out validation on the V3A retention split improved monotonically through step 6200:
 | 6100 | 4.2970 | 73.48 |
 | 6200 | 4.2950 | 73.33 |
+Source-bucket validation at step 6200. Web/wiki rows are from the stage-gate run with `steps=50`:
 | Source | loss | perplexity |
 | --- | ---: | ---: |
 | BELEBELE-KOR subset | 47/200 |
 | GSM8K-Ko subset | 0/100 |
+## Rejected Follow-Up Probes
+| Probe | Decision |
+| --- | --- |
+| Low-LR response-only SFT to step 6400 | Rejected: SFT validation improved, but generation did not improve and all source-bucket losses worsened. |
+| Average of step 6100/6150/6200 | Rejected: no mini-MCQ/generation gain and source buckets were slightly worse than step 6200. |
+| Mixed retention/SFT step 6250 | Rejected: retention validation improved slightly, but generation stayed repetitive and source buckets were mostly slightly worse. |
+| Low-LR V3A retention extension to step 6300 | Rejected: validation worsened versus step 6200. |
+| V3B TinyStories low-ratio step 6300 | Rejected: V3B validation improved, but same-condition source-bucket losses were flat/slightly worse and generation did not improve. |
 ## Export Checks
 - Native-vs-HF logits equivalence: `ok=true`, max absolute diff `0.015625`, argmax mismatch rate `0.0`.
 - Local Transformers smoke: `AutoConfig`, `AutoTokenizer`, and `AutoModelForCausalLM` load without custom code as `LlamaForCausalLM`.
 - Local parameter count after HF load: `1,260,505,088`.
+- Local submission secret scan: passed on text artifacts; no `hf_...` token pattern or generic long secret assignment was found.
 ## Intended Use