Instructions to use PursuitOfDataScience/Argonne-3.0-think with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use PursuitOfDataScience/Argonne-3.0-think with Transformers:

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

pipe = pipeline("text-generation", model="PursuitOfDataScience/Argonne-3.0-think", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("PursuitOfDataScience/Argonne-3.0-think", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use PursuitOfDataScience/Argonne-3.0-think with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "PursuitOfDataScience/Argonne-3.0-think"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "PursuitOfDataScience/Argonne-3.0-think",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/PursuitOfDataScience/Argonne-3.0-think

SGLang

How to use PursuitOfDataScience/Argonne-3.0-think 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 "PursuitOfDataScience/Argonne-3.0-think" \
    --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": "PursuitOfDataScience/Argonne-3.0-think",
		"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 "PursuitOfDataScience/Argonne-3.0-think" \
        --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": "PursuitOfDataScience/Argonne-3.0-think",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use PursuitOfDataScience/Argonne-3.0-think with Docker Model Runner:
```
docker model run hf.co/PursuitOfDataScience/Argonne-3.0-think
```

Argonne-3.0-think / config.json

PursuitOfDataScience

v3: short-trace termination + grade-school procedure distillation via cross-soup (x_v6v2_040). Clean held-out SVAMP/ASDiv greedy +5/+5 and self-consistency held vs v2; native <think> termination; config eos_token_id fixed to <|im_end|>.

3ce29e3 verified 28 days ago

Raw

History Blame Contribute Delete

1.22 kB

	{
	"_keep_in_fp32_modules": [],
	"architectures": [
	"ArgonneModel"
	],
	"attention_bias": false,
	"attention_dropout": 0.0,
	"block_size": 13568,
	"bos_token_id": null,
	"dtype": "bfloat16",
	"eos_token_id": 151645,
	"hidden_dropout": 0.0,
	"hidden_size": 3072,
	"interleaved_local_attention": true,
	"intermediate_size": 8192,
	"local_attention_window": 256,
	"logit_softcap": 15.0,
	"max_position_embeddings": 13568,
	"mlp_bias": false,
	"model_type": "argonne2",
	"mtp_horizon": 1,
	"mtp_loss_weight": 0.0,
	"n_embd": 3072,
	"n_head": 12,
	"n_layer": 24,
	"num_attention_heads": 12,
	"num_hidden_layers": 24,
	"num_key_value_heads": 4,
	"pad_token_id": null,
	"qk_norm": true,
	"rms_norm_eps": 1e-06,
	"rope_theta": 1000000.0,
	"sandwich_norm": true,
	"sliding_window": null,
	"tie_word_embeddings": true,
	"transformers_version": "5.6.2",
	"use_cache": false,
	"use_flash_attention": true,
	"use_gradient_checkpointing": false,
	"v_norm": true,
	"vocab_size": 151669,
	"z_loss_weight": 0.0,
	"torch_dtype": "bfloat16",
	"auto_map": {
	"AutoConfig": "model.ArgonneConfig",
	"AutoModel": "model.ArgonneModel",
	"AutoModelForCausalLM": "model.ArgonneModel"
	}
	}