Instructions to use Eclipse-Senpai/KeyLM-75M-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Eclipse-Senpai/KeyLM-75M-Instruct with Transformers:

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

pipe = pipeline("text-generation", model="Eclipse-Senpai/KeyLM-75M-Instruct", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Eclipse-Senpai/KeyLM-75M-Instruct", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use Eclipse-Senpai/KeyLM-75M-Instruct with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Eclipse-Senpai/KeyLM-75M-Instruct"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Eclipse-Senpai/KeyLM-75M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/Eclipse-Senpai/KeyLM-75M-Instruct

SGLang

How to use Eclipse-Senpai/KeyLM-75M-Instruct 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 "Eclipse-Senpai/KeyLM-75M-Instruct" \
    --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": "Eclipse-Senpai/KeyLM-75M-Instruct",
		"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 "Eclipse-Senpai/KeyLM-75M-Instruct" \
        --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": "Eclipse-Senpai/KeyLM-75M-Instruct",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use Eclipse-Senpai/KeyLM-75M-Instruct with Docker Model Runner:
```
docker model run hf.co/Eclipse-Senpai/KeyLM-75M-Instruct
```

Eclipse-Senpai commited on 3 days ago

Commit

2dc5cfa

verified ·

1 Parent(s): 349d587

Knowledge/reasoning table: drop external models, show KeyLM base vs instruct

Browse files

Files changed (1) hide show

README.md +9 -12

README.md CHANGED Viewed

@@ -101,18 +101,15 @@ KeyLM beats the original SmolLM-135M-Instruct at roughly half the size and a fra
 ### Knowledge and reasoning
-On standard multiple-choice benchmarks KeyLM performs at or near random chance. This is the expected trade-off at 75M parameters and 18B tokens: the model has little parametric knowledge, and its useful behavior comes from instruction tuning rather than recall. All KeyLM scores are zero-shot via `lm_eval` (accuracy; ARC and HellaSwag use length-normalized accuracy).
-| Model | Params | MMLU | ARC (avg) | HellaSwag | PIQA | WinoGrande | OpenBookQA |
-|---|---|---|---|---|---|---|---|
-| **KeyLM-75M-Instruct** | **75M** | **23.0** | **26.1** | **26.7** | **53.1** | **48.9** | **18.4** |
-| Random baseline | n/a | 25.0 | 25.0 | 25.0 | 50.0 | 50.0 | 25.0 |
-| GPT-2 (137M) | 137M | 26.3 | 31.1 | 29.8 | 62.5 | 49.7 | 29.4 |
-| Pythia-160M | 160M | 26.7 | 31.9 | 29.6 | 61.6 | 49.5 | 27.8 |
-| MobileLLM-125M | 125M | n/a | 35.5 | 38.9 | 65.3 | 53.1 | 39.5 |
-| SmolLM-135M | 135M | 30.2 | 44.0 | 42.3 | 69.6 | 52.7 | 33.6 |
-Figures for the comparison models are as reported in the SmolLM technical report and are included for rough context only; they may use different evaluation setups than the KeyLM rows.
 ## Training

 ### Knowledge and reasoning
+On standard multiple-choice benchmarks KeyLM performs at or near random chance. This is the expected trade-off at 75M parameters and 18B tokens: the model holds little parametric knowledge, and instruction tuning changes its behavior, not its knowledge. Scores are zero-shot via `lm_eval` (accuracy; ARC and HellaSwag use length-normalized accuracy).
+| Model | MMLU | ARC (avg) | HellaSwag | PIQA | WinoGrande | OpenBookQA |
+|---|---|---|---|---|---|---|
+| KeyLM-75M (base) | 23.0 | 26.4 | — | 52.9 | 48.3 | 19.8 |
+| **KeyLM-75M-Instruct** | **23.0** | **26.1** | **26.7** | **53.1** | **48.9** | **18.4** |
+| Random baseline | 25.0 | 25.0 | 25.0 | 50.0 | 50.0 | 25.0 |
+Instruction tuning leaves knowledge and reasoning essentially unchanged: the base and instruct checkpoints track each other and both sit close to the random baseline. The base model's HellaSwag score will be added with its release.
 ## Training