Instructions to use uuugi/gclm-constrained-decoding with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use uuugi/gclm-constrained-decoding with Transformers:

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

pipe = pipeline("text-generation", model="uuugi/gclm-constrained-decoding")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("uuugi/gclm-constrained-decoding", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use uuugi/gclm-constrained-decoding with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/uuugi/gclm-constrained-decoding

SGLang

How to use uuugi/gclm-constrained-decoding 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 "uuugi/gclm-constrained-decoding" \
    --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": "uuugi/gclm-constrained-decoding",
		"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 "uuugi/gclm-constrained-decoding" \
        --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": "uuugi/gclm-constrained-decoding",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use uuugi/gclm-constrained-decoding with Docker Model Runner:
```
docker model run hf.co/uuugi/gclm-constrained-decoding
```

uuugi commited on 3 days ago

Commit

94c3e52

verified ·

1 Parent(s): b984b6d

Fix inline math text notation in Mathematical Formulation and Scaling sections

Browse files

Files changed (1) hide show

README.md +3 -3

README.md CHANGED Viewed

@@ -51,7 +51,7 @@ GCLM mathematically guarantees that an LLM will strictly reach designated goal/a
 ## 📐 Mathematical Formulation
 ### 1. Offline Backward BFS Table Builder
-Given an FSM $(S, \Sigma, \delta, s_0, S_{\text{goal}})$ and maximum token budget $T_{\max}$, we precompute a reachability tensor $R \in \{0, 1\}^{(T_{\max} + 1) \times |S|}$ via vectorized backward BFS:
 ```python
 # Base Step (t = 0):
@@ -62,7 +62,7 @@ R[t, s] = R[t-1, s]  OR  (∃ v ∈ V such that δ(s, v) >= 0 and R[t-1, δ(s, v
 ```
 ### 2. Strict O(1) Runtime Logits Masking
-At decoding step $k$ with remaining token budget $T_{\text{rem}} = T_{\max} - k$:
 ```python
 # Step 1: Vectorized check for valid transitions within remaining budget
@@ -139,7 +139,7 @@ gclm_project/
 ---
 ### 4. FSM Complexity & Strict O(1) Runtime Scaling
-> Scaling state count \(|S|\) from 10 to 10,000 (1,000x increase). Plot saved as `paper_figure_scaling.png`.
 | Vocabulary Size (V) | State Count (S) | Offline BFS Time | Memory Footprint | Online Latency per Token |
 | :--- | :---: | :---: | :---: | :---: |

 ## 📐 Mathematical Formulation
 ### 1. Offline Backward BFS Table Builder
+Given an FSM `(S, Σ, δ, s_0, S_goal)` and maximum token budget `T_max`, we precompute a reachability tensor `R` of shape `(T_max + 1, |S|)` via vectorized backward BFS:
 ```python
 # Base Step (t = 0):
 ```
 ### 2. Strict O(1) Runtime Logits Masking
+At decoding step `k` with remaining token budget `T_rem = T_max - k`:
 ```python
 # Step 1: Vectorized check for valid transitions within remaining budget
 ---
 ### 4. FSM Complexity & Strict O(1) Runtime Scaling
+> Scaling state count `|S|` from 10 to 10,000 (1,000x increase). Plot saved as `paper_figure_scaling.png`.
 | Vocabulary Size (V) | State Count (S) | Offline BFS Time | Memory Footprint | Online Latency per Token |
 | :--- | :---: | :---: | :---: | :---: |