Instructions to use xfcxcxcdfdfd/1hbit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use xfcxcxcdfdfd/1hbit with Transformers:

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

pipe = pipeline("text-generation", model="xfcxcxcdfdfd/1hbit")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("xfcxcxcdfdfd/1hbit")
model = AutoModelForCausalLM.from_pretrained("xfcxcxcdfdfd/1hbit")
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 xfcxcxcdfdfd/1hbit with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "xfcxcxcdfdfd/1hbit"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "xfcxcxcdfdfd/1hbit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/xfcxcxcdfdfd/1hbit

SGLang

How to use xfcxcxcdfdfd/1hbit 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 "xfcxcxcdfdfd/1hbit" \
    --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": "xfcxcxcdfdfd/1hbit",
		"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 "xfcxcxcdfdfd/1hbit" \
        --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": "xfcxcxcdfdfd/1hbit",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use xfcxcxcdfdfd/1hbit with Docker Model Runner:
```
docker model run hf.co/xfcxcxcdfdfd/1hbit
```

xfcxcxcdfdfd commited on Dec 13, 2024

Commit

9aefbdf

verified ·

1 Parent(s): 565165c

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

pytorch_model-00001-of-00002.bin +2 -2
pytorch_model-00002-of-00002.bin +2 -2
pytorch_model.bin.index.json +4 -4

pytorch_model-00001-of-00002.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8559d2f1f15961c019870fbacdaa34b9f3e1c3668e7f90b76a762e2bd9868e18
-size 4838640322

 version https://git-lfs.github.com/spec/v1
+oid sha256:0f793a1eed262ceced707cdaf8c33d1c77427e5d59fa8b1a98d512a7d41a5f94
+size 4838615042

pytorch_model-00002-of-00002.bin CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1dbd1d14db1ae344d0e36d218d11143e1e6e26bba7b4c18fefd61c0d5ac2a645
-size 1651559595

 version https://git-lfs.github.com/spec/v1
+oid sha256:624c1d90e368e405dffb098c06432835a9c4e5c89f1427cf477e405c3bf27d26
+size 3227594782

pytorch_model.bin.index.json CHANGED Viewed

@@ -1,15 +1,15 @@
 {
   "metadata": {
-    "total_size": 6490177552
   },
   "weight_map": {
-    "draft_model.embed_tokens.weight": "pytorch_model-00001-of-00002.bin",
     "draft_model.emotion_vector": "pytorch_model-00001-of-00002.bin",
     "draft_model.lm_head.weight": "pytorch_model-00002-of-00002.bin",
     "draft_model.memory_keys": "pytorch_model-00001-of-00002.bin",
     "draft_model.memory_values": "pytorch_model-00001-of-00002.bin",
-    "draft_model.norm.bias": "pytorch_model-00001-of-00002.bin",
-    "draft_model.norm.weight": "pytorch_model-00001-of-00002.bin",
     "draft_model.prediction_head.bias": "pytorch_model-00002-of-00002.bin",
     "draft_model.prediction_head.weight": "pytorch_model-00002-of-00002.bin",
     "draft_model.response_selector.bias": "pytorch_model-00002-of-00002.bin",

 {
   "metadata": {
+    "total_size": 8066187280
   },
   "weight_map": {
+    "draft_model.embed_tokens.weight": "pytorch_model-00002-of-00002.bin",
     "draft_model.emotion_vector": "pytorch_model-00001-of-00002.bin",
     "draft_model.lm_head.weight": "pytorch_model-00002-of-00002.bin",
     "draft_model.memory_keys": "pytorch_model-00001-of-00002.bin",
     "draft_model.memory_values": "pytorch_model-00001-of-00002.bin",
+    "draft_model.norm.bias": "pytorch_model-00002-of-00002.bin",
+    "draft_model.norm.weight": "pytorch_model-00002-of-00002.bin",
     "draft_model.prediction_head.bias": "pytorch_model-00002-of-00002.bin",
     "draft_model.prediction_head.weight": "pytorch_model-00002-of-00002.bin",
     "draft_model.response_selector.bias": "pytorch_model-00002-of-00002.bin",