Instructions to use Serdar404/RecGPT-100M-Fixed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Serdar404/RecGPT-100M-Fixed with Transformers:

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

pipe = pipeline("text-generation", model="Serdar404/RecGPT-100M-Fixed", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Serdar404/RecGPT-100M-Fixed", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Serdar404/RecGPT-100M-Fixed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Serdar404/RecGPT-100M-Fixed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Serdar404/RecGPT-100M-Fixed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Serdar404/RecGPT-100M-Fixed

SGLang

How to use Serdar404/RecGPT-100M-Fixed 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 "Serdar404/RecGPT-100M-Fixed" \
    --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": "Serdar404/RecGPT-100M-Fixed",
		"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 "Serdar404/RecGPT-100M-Fixed" \
        --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": "Serdar404/RecGPT-100M-Fixed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Serdar404/RecGPT-100M-Fixed with Docker Model Runner:
```
docker model run hf.co/Serdar404/RecGPT-100M-Fixed
```

Serdar404 commited on Jul 20

Commit

bef6a07

verified ·

1 Parent(s): 0c66a68

Update README.md

Browse files

Files changed (1) hide show

README.md +3 -4

README.md CHANGED Viewed

@@ -11,11 +11,11 @@ tags:
 - custom_code
 ---
-# BabyLM Challenge 2026 submission | RecGPT-100M-Fixed
-RecGPT-100M-Fixed is a 124.03M-parameter recursive causal language model trained for the BabyLM 2026 Strict track. It was trained for 10 epochs on a custom 100M-word English corpus using a 32,768-token BPE vocabulary.
-The model applies a shared Transformer block recursively for 24 iterations. Its hidden size is 1,408, embedding size is 768, and feed-forward intermediate size is 22,528. Training used Muon for the recursive block and AdamW for the embedding-related parameters, with a token batch size of 32,768 and sequence length 512.
 ## Usage
@@ -44,7 +44,6 @@ Final-checkpoint results before leaderboard submission:
 | COMPS | 60.55 |
 | GlobalPIQA | 43.15 |
 | (Super)GLUE | 71.84 |
-| NLP Average | 57.63 |
 Intermediate Strict checkpoints are published as Hub revisions named `chck_1M` through `chck_1000M` using the official BabyLM checkpoint schedule.

 - custom_code
 ---
+# BabyLM Challenge 2026 submission | RecGPT-100M
+RecGPT-100M is a 124.03M-parameter recursive causal language model trained for the BabyLM 2026 Strict track. It was trained for 10 epochs on a custom 100M-word English corpus using a 32,768-token BPE vocabulary.
+The model applies a shared Transformer block recursively for 24 iterations. Its hidden size is 1,408, embedding size is 768, and feed-forward intermediate size is 22,528. Training used Aurora for the recursive block and AdamW for the embedding-related parameters, with a token batch size of 32,768 and sequence length 512.
 ## Usage
 | COMPS | 60.55 |
 | GlobalPIQA | 43.15 |
 | (Super)GLUE | 71.84 |
 Intermediate Strict checkpoints are published as Hub revisions named `chck_1M` through `chck_1000M` using the official BabyLM checkpoint schedule.