Instructions to use codys12/bitnet-r1-llama-8b with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use codys12/bitnet-r1-llama-8b with Transformers:

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

pipe = pipeline("text-generation", model="codys12/bitnet-r1-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-r1-llama-8b")
model = AutoModelForCausalLM.from_pretrained("codys12/bitnet-r1-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 Settings

vLLM

How to use codys12/bitnet-r1-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-r1-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-r1-llama-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/codys12/bitnet-r1-llama-8b

SGLang

How to use codys12/bitnet-r1-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-r1-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-r1-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-r1-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-r1-llama-8b",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use codys12/bitnet-r1-llama-8b with Docker Model Runner:
```
docker model run hf.co/codys12/bitnet-r1-llama-8b
```

codys12 commited on May 11, 2025

Commit

4f87e78

verified ·

1 Parent(s): cc620bd

Upload LlamaForCausalLM

Browse files

Files changed (2) hide show

config.json +3 -4
pytorch_model.bin +1 -1

config.json CHANGED Viewed

@@ -19,11 +19,10 @@
   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
-    "linear_class": "autobitlinear",
     "modules_to_not_convert": [],
-    "quantization_mode": "online",
     "quant_method": "bitnet",
-    "pre_quantized": false,
     "with_rms_norm": true
   },
   "rms_norm_eps": 1e-05,
@@ -36,7 +35,7 @@
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
-  "torch_dtype": "float16",
   "transformers_version": "4.52.0.dev0",
   "use_cache": true,
   "vocab_size": 128256

   "num_key_value_heads": 8,
   "pretraining_tp": 1,
   "quantization_config": {
+    "linear_class": "bitlinear",
     "modules_to_not_convert": [],
     "quant_method": "bitnet",
+    "quantization_mode": "offline",
     "with_rms_norm": true
   },
   "rms_norm_eps": 1e-05,
   },
   "rope_theta": 500000.0,
   "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
   "transformers_version": "4.52.0.dev0",
   "use_cache": true,
   "vocab_size": 128256

pytorch_model.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b123b35bc08be4601ff5a39debf0f5ddb66c3a687a0c0fd03a172125cd98010
 size 2930108766

 version https://git-lfs.github.com/spec/v1
+oid sha256:b1071a4553fc5f0c2fa6959936abf141090ab06748eb37cd9067ad913511482a
 size 2930108766