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 2 days ago

Commit

d137cc3

verified ·

1 Parent(s): 7f614be

Update README.md

Browse files

Files changed (1) hide show

README.md +2 -6

README.md CHANGED Viewed

@@ -62,8 +62,6 @@ GGUF builds for `llama.cpp`, LM Studio, and Ollama are available at [KeyLM-75M-I
 ## How to Use
-KeyLM ships its own modeling code, so load it with `trust_remote_code=True`. It requires `transformers>=4.51`.
 ```python
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
@@ -85,8 +83,6 @@ outputs = model.generate(
 print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
 ```
-The model uses a plain `User:` / `Assistant:` chat format, applied automatically by `apply_chat_template`. Assistant turns end with `</s>`.
 ## Evaluation
 ### Instruction following (IFEval)
@@ -103,7 +99,7 @@ KeyLM beats the original SmolLM-135M-Instruct at roughly half the size and a fra
 ### Base vs Instruct
-The base and instruction-tuned checkpoints across all benchmarks. Commonsense and knowledge tasks are zero-shot via `lm_eval` (accuracy; ARC and HellaSwag length-normalized); IFEval is the 4-metric average. Bold marks the stronger version per row.
 | Benchmark | KeyLM-75M (base) | KeyLM-75M-Instruct | Random |
 |---|---|---|---|
@@ -133,7 +129,7 @@ KeyLM was pretrained from random initialization on approximately 18B tokens, dra
 ### Post-training
-Instruction tuning used `smol-smoltalk`, `ultrachat_200k`, and several `smoltalk2` splits (magpie, persona instruction-following, science, OpenHermes, system chats, summarization), with assistant-only loss masking, plus a set of custom synthetic instruction-following examples. A final personality tuning pass produced the released checkpoint.
 ## Limitations

 ## How to Use
 ```python
 import torch
 from transformers import AutoModelForCausalLM, AutoTokenizer
 print(tokenizer.decode(outputs[0][inputs.shape[1]:], skip_special_tokens=True))
 ```
 ## Evaluation
 ### Instruction following (IFEval)
 ### Base vs Instruct
+The base and instruction-tuned checkpoints across all benchmarks. Commonsense and knowledge tasks are zero-shot via `lm_eval` (accuracy; ARC and HellaSwag length-normalized); IFEval is the 4-metric average.
 | Benchmark | KeyLM-75M (base) | KeyLM-75M-Instruct | Random |
 |---|---|---|---|
 ### Post-training
+Instruction tuning used `smol-smoltalk`, `ultrachat_200k`, and several `smoltalk2` splits (magpie, persona instruction-following, science, OpenHermes, system chats, summarization), with assistant-only loss masking, plus a set of custom synthetic instruction-following examples.
 ## Limitations