Instructions to use codys12/bitnet-llama-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codys12/bitnet-llama-8b with Transformers:

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

pipe = pipeline("text-generation", model="codys12/bitnet-llama-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("codys12/bitnet-llama-8b")
model = AutoModelForCausalLM.from_pretrained("codys12/bitnet-llama-8b")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use codys12/bitnet-llama-8b with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "codys12/bitnet-llama-8b"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "codys12/bitnet-llama-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/codys12/bitnet-llama-8b

SGLang

How to use codys12/bitnet-llama-8b 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 "codys12/bitnet-llama-8b" \
    --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": "codys12/bitnet-llama-8b",
		"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 "codys12/bitnet-llama-8b" \
        --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": "codys12/bitnet-llama-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use codys12/bitnet-llama-8b with Docker Model Runner:
```
docker model run hf.co/codys12/bitnet-llama-8b
```

codys12 commited on May 22, 2025

Commit

344e7e5

verified ·

1 Parent(s): 831de8d

Update config.json

Browse files

Files changed (1) hide show

config.json +2 -5

config.json CHANGED Viewed

@@ -24,10 +24,7 @@
   "pretraining_tp": 1,
   "quantization_config": {
     "linear_class": "bitlinear",
-    "quant_method": "gptq",
-    "bits": 2,
-    "group_size": -1,
-    "desc_act": false,
     "quantization_mode": "offline",
     "use_rms_norm": true
   },
@@ -45,4 +42,4 @@
   "transformers_version": "4.52.0.dev0",
   "use_cache": true,
   "vocab_size": 128256
-}

   "pretraining_tp": 1,
   "quantization_config": {
     "linear_class": "bitlinear",
+    "quant_method": "bitnet",
     "quantization_mode": "offline",
     "use_rms_norm": true
   },
   "transformers_version": "4.52.0.dev0",
   "use_cache": true,
   "vocab_size": 128256
+}