Instructions to use AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq with Transformers:

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

pipe = pipeline("text-generation", model="AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq")
model = AutoModelForCausalLM.from_pretrained("AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq")
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 AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq

SGLang

How to use AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq 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 "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq" \
    --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": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
		"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 "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq" \
        --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": "AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq with Docker Model Runner:
```
docker model run hf.co/AlignmentResearch/Llama-3.3-Tiny-Instruct-boolq
```

skar0 commited on Aug 21, 2025

Commit

0051ec0

verified ·

1 Parent(s): c794b0b

Upload LlamaForCausalLM

Browse files

Files changed (3) hide show

config.json +29 -13
generation_config.json +6 -3
model.safetensors +2 -2

config.json CHANGED Viewed

@@ -4,27 +4,43 @@
   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
   "head_dim": 64,
   "hidden_act": "silu",
-  "hidden_size": 768,
   "initializer_range": 0.02,
-  "intermediate_size": 3072,
-  "max_position_embeddings": 2048,
   "mlp_bias": false,
   "model_type": "llama",
-  "num_attention_heads": 12,
-  "num_hidden_layers": 2,
-  "num_key_value_heads": 12,
-  "pad_token_id": 0,
   "pretraining_tp": 1,
-  "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.54.1",
   "use_cache": true,
-  "vocab_size": 32000
 }

   ],
   "attention_bias": false,
   "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "head_dim": 64,
   "hidden_act": "silu",
+  "hidden_size": 256,
+  "id2label": {
+    "0": "LABEL_0"
+  },
   "initializer_range": 0.02,
+  "intermediate_size": 768,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 131072,
   "mlp_bias": false,
   "model_type": "llama",
+  "num_attention_heads": 4,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 2,
+  "pad_token_id": 128004,
   "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.54.1",
   "use_cache": true,
+  "vocab_size": 128256
 }

generation_config.json CHANGED Viewed

@@ -1,7 +1,10 @@
 {
   "_from_model_config": true,
-  "bos_token_id": 0,
-  "eos_token_id": 2,
-  "pad_token_id": 1,
   "transformers_version": "4.54.1"
 }

 {
   "_from_model_config": true,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
   "transformers_version": "4.54.1"
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a5af49d3cf4e8de6e5208c9e11d5a3effb421b2385d0ec0b93e79e3f125ef094
-size 136062744

 version https://git-lfs.github.com/spec/v1
+oid sha256:e2c5aeb07d4e6e23406ee8bcb36b04700fb73364cdebe8991491dab02777a9f3
+size 150233704