Instructions to use CodeIsAbstract/merged_llama_3.2_thinking_model with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use CodeIsAbstract/merged_llama_3.2_thinking_model with Transformers:

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

pipe = pipeline("text-generation", model="CodeIsAbstract/merged_llama_3.2_thinking_model")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("CodeIsAbstract/merged_llama_3.2_thinking_model")
model = AutoModelForCausalLM.from_pretrained("CodeIsAbstract/merged_llama_3.2_thinking_model")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use CodeIsAbstract/merged_llama_3.2_thinking_model with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "CodeIsAbstract/merged_llama_3.2_thinking_model"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "CodeIsAbstract/merged_llama_3.2_thinking_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/CodeIsAbstract/merged_llama_3.2_thinking_model

SGLang

How to use CodeIsAbstract/merged_llama_3.2_thinking_model 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 "CodeIsAbstract/merged_llama_3.2_thinking_model" \
    --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": "CodeIsAbstract/merged_llama_3.2_thinking_model",
		"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 "CodeIsAbstract/merged_llama_3.2_thinking_model" \
        --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": "CodeIsAbstract/merged_llama_3.2_thinking_model",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use CodeIsAbstract/merged_llama_3.2_thinking_model with Docker Model Runner:
```
docker model run hf.co/CodeIsAbstract/merged_llama_3.2_thinking_model
```

CodeIsAbstract commited on Apr 29, 2025

Commit

1129421

verified ·

1 Parent(s): 7cb8ed9

Upload tokenizer

Browse files

Files changed (1) hide show

tokenizer_config.json +2 -1

tokenizer_config.json CHANGED Viewed

@@ -2052,10 +2052,11 @@
   "bos_token": "<|begin_of_text|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
-  "tokenizer_class": "PreTrainedTokenizerFast"
 }

   "bos_token": "<|begin_of_text|>",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|end_of_text|>",
+  "extra_special_tokens": {},
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 131072,
+  "tokenizer_class": "PreTrainedTokenizer"
 }