Instructions to use HuggingFaceM4/tiny-random-LlamaForCausalLM with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use HuggingFaceM4/tiny-random-LlamaForCausalLM with Transformers:

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

pipe = pipeline("text-generation", model="HuggingFaceM4/tiny-random-LlamaForCausalLM")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("HuggingFaceM4/tiny-random-LlamaForCausalLM")
model = AutoModelForCausalLM.from_pretrained("HuggingFaceM4/tiny-random-LlamaForCausalLM")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use HuggingFaceM4/tiny-random-LlamaForCausalLM with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "HuggingFaceM4/tiny-random-LlamaForCausalLM"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "HuggingFaceM4/tiny-random-LlamaForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/HuggingFaceM4/tiny-random-LlamaForCausalLM

SGLang

How to use HuggingFaceM4/tiny-random-LlamaForCausalLM 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 "HuggingFaceM4/tiny-random-LlamaForCausalLM" \
    --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": "HuggingFaceM4/tiny-random-LlamaForCausalLM",
		"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 "HuggingFaceM4/tiny-random-LlamaForCausalLM" \
        --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": "HuggingFaceM4/tiny-random-LlamaForCausalLM",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use HuggingFaceM4/tiny-random-LlamaForCausalLM with Docker Model Runner:
```
docker model run hf.co/HuggingFaceM4/tiny-random-LlamaForCausalLM
```

Match the tokenizer

by lsb - opened Aug 7, 2025

base: refs/heads/main

←

from: refs/pr/5

Discussion Files changed

-3

Files changed (1) hide show

config.json +3 -3

config.json CHANGED Viewed

@@ -2,8 +2,8 @@
   "architectures": [
     "LlamaForCausalLM"
   ],
-  "bos_token_id": 0,
-  "eos_token_id": 1,
   "hidden_act": "silu",
   "hidden_size": 16,
   "initializer_range": 0.02,
@@ -11,7 +11,7 @@
   "model_type": "llama",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
-  "pad_token_id": -1,
   "rms_norm_eps": 1e-06,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",

   "architectures": [
     "LlamaForCausalLM"
   ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 16,
   "initializer_range": 0.02,
   "model_type": "llama",
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
+  "pad_token_id": 0,
   "rms_norm_eps": 1e-06,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",