Instructions to use antoinechss/performer-checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use antoinechss/performer-checkpoints with Transformers:

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

pipe = pipeline("text-generation", model="antoinechss/performer-checkpoints")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("antoinechss/performer-checkpoints", dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use antoinechss/performer-checkpoints with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/antoinechss/performer-checkpoints

SGLang

How to use antoinechss/performer-checkpoints 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 "antoinechss/performer-checkpoints" \
    --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": "antoinechss/performer-checkpoints",
		"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 "antoinechss/performer-checkpoints" \
        --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": "antoinechss/performer-checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use antoinechss/performer-checkpoints with Docker Model Runner:
```
docker model run hf.co/antoinechss/performer-checkpoints
```

performer-checkpoints / README.md

antoinechss

Update README.md

51192ad verified 13 days ago

preview code

raw

history blame contribute delete

950 Bytes

metadata

license: apache-2.0
datasets:
  - mindchain/wikitext2
  - allenai/c4
language:
  - en
metrics:
  - perplexity
base_model:
  - TinyLlama/TinyLlama-1.1B-Chat-v1.0
pipeline_tag: text-generation
library_name: transformers
tags:
  - performer
  - linear-attention
  - favor+
  - knowledge-distillation
  - research

Model description: TinyLlama 1.1B with K/32 softmax attention heads replaced by FAVOR+ linear attention, fine-tuned via knowledge distillation
Intended use: Research — evaluating quality/speed/approximation trade-offs of linear attention substitution
How to load: code snippet showing how to reconstruct MixedPerformerAttention and load the checkpoint
Training details: WikiText-103, 20k samples, SEQ_LEN=256, distillation loss, 4-phase curriculum
Results table: same as the README (ppl per phase)
Limitations: Phase 4 (32/32 heads) collapsed — not suitable for inference. Phase 2 is the recommended checkpoint.