Instructions to use Lanni-ni/alibi_2_4_256_babylm_10m_seed43 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Lanni-ni/alibi_2_4_256_babylm_10m_seed43 with Transformers:

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

pipe = pipeline("text-generation", model="Lanni-ni/alibi_2_4_256_babylm_10m_seed43", trust_remote_code=True)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("Lanni-ni/alibi_2_4_256_babylm_10m_seed43", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use Lanni-ni/alibi_2_4_256_babylm_10m_seed43 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "Lanni-ni/alibi_2_4_256_babylm_10m_seed43"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "Lanni-ni/alibi_2_4_256_babylm_10m_seed43",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/Lanni-ni/alibi_2_4_256_babylm_10m_seed43

SGLang

How to use Lanni-ni/alibi_2_4_256_babylm_10m_seed43 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 "Lanni-ni/alibi_2_4_256_babylm_10m_seed43" \
    --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": "Lanni-ni/alibi_2_4_256_babylm_10m_seed43",
		"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 "Lanni-ni/alibi_2_4_256_babylm_10m_seed43" \
        --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": "Lanni-ni/alibi_2_4_256_babylm_10m_seed43",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use Lanni-ni/alibi_2_4_256_babylm_10m_seed43 with Docker Model Runner:
```
docker model run hf.co/Lanni-ni/alibi_2_4_256_babylm_10m_seed43
```

Lanni-ni commited on 15 days ago

Commit

3c65c19

verified ·

1 Parent(s): 0313894

Upload config.json with huggingface_hub

Browse files

Files changed (1) hide show

config.json +3 -4

config.json CHANGED Viewed

@@ -1,6 +1,6 @@
 {
   "architectures": [
-    "AlibiForCausalLM"
   ],
   "attention_bias": false,
   "auto_map": {
@@ -27,9 +27,8 @@
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.44.0",
-  "use_alibi": true,
   "use_cache": true,
-  "use_rope": false,
   "vocab_size": 50277,
   "window_size": null
-}

 {
   "architectures": [
+    "TransformerForCausalLM"
   ],
   "attention_bias": false,
   "auto_map": {
   "tie_word_embeddings": false,
   "torch_dtype": "float32",
   "transformers_version": "4.44.0",
   "use_cache": true,
+  "use_rope": true,
   "vocab_size": 50277,
   "window_size": null
+}