Instructions to use Bochkov/llm-fix-min-fixed-minimal-binary-code with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Bochkov/llm-fix-min-fixed-minimal-binary-code with Transformers:

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

pipe = pipeline("text-generation", model="Bochkov/llm-fix-min-fixed-minimal-binary-code", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("Bochkov/llm-fix-min-fixed-minimal-binary-code", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Bochkov/llm-fix-min-fixed-minimal-binary-code with vLLM:

Install from pip and serve model

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

Use Docker

docker model run hf.co/Bochkov/llm-fix-min-fixed-minimal-binary-code

SGLang

How to use Bochkov/llm-fix-min-fixed-minimal-binary-code 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 "Bochkov/llm-fix-min-fixed-minimal-binary-code" \
    --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": "Bochkov/llm-fix-min-fixed-minimal-binary-code",
		"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 "Bochkov/llm-fix-min-fixed-minimal-binary-code" \
        --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": "Bochkov/llm-fix-min-fixed-minimal-binary-code",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Bochkov/llm-fix-min-fixed-minimal-binary-code with Docker Model Runner:
```
docker model run hf.co/Bochkov/llm-fix-min-fixed-minimal-binary-code
```

Bochkov commited on 10 days ago

Commit

684afe4

verified ·

1 Parent(s): 05ffae4

Update README.md

Browse files

Files changed (1) hide show

README.md +0 -2

README.md CHANGED Viewed

@@ -165,7 +165,6 @@ expected = ((ids[:, None] >> positions[None, :]) & 1).float()
 expected[model.config.pad_token_id].zero_()
 print("shape:", tuple(weight.shape))
-print("requires_grad:", embedding.weight.requires_grad)
 print("unique values:", torch.unique(weight).tolist())
 print("all entries binary:", bool(torch.all((weight == 0) | (weight == 1))))
 print("exact canonical-code match:", bool(torch.equal(weight, expected)))
@@ -180,7 +179,6 @@ Expected audit properties:
 ```text
 shape: (65536, 16)
-requires_grad: True
 unique values: [0.0, 1.0]
 all entries binary: True
 exact canonical-code match: True

 expected[model.config.pad_token_id].zero_()
 print("shape:", tuple(weight.shape))
 print("unique values:", torch.unique(weight).tolist())
 print("all entries binary:", bool(torch.all((weight == 0) | (weight == 1))))
 print("exact canonical-code match:", bool(torch.equal(weight, expected)))
 ```text
 shape: (65536, 16)
 unique values: [0.0, 1.0]
 all entries binary: True
 exact canonical-code match: True