Instructions to use dhanesh-hf/Jarvis-Titan-M4-Activated with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use dhanesh-hf/Jarvis-Titan-M4-Activated with Transformers:

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

pipe = pipeline("text-generation", model="dhanesh-hf/Jarvis-Titan-M4-Activated", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("dhanesh-hf/Jarvis-Titan-M4-Activated", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use dhanesh-hf/Jarvis-Titan-M4-Activated with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "dhanesh-hf/Jarvis-Titan-M4-Activated"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "dhanesh-hf/Jarvis-Titan-M4-Activated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/dhanesh-hf/Jarvis-Titan-M4-Activated

SGLang

How to use dhanesh-hf/Jarvis-Titan-M4-Activated 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 "dhanesh-hf/Jarvis-Titan-M4-Activated" \
    --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": "dhanesh-hf/Jarvis-Titan-M4-Activated",
		"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 "dhanesh-hf/Jarvis-Titan-M4-Activated" \
        --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": "dhanesh-hf/Jarvis-Titan-M4-Activated",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use dhanesh-hf/Jarvis-Titan-M4-Activated with Docker Model Runner:
```
docker model run hf.co/dhanesh-hf/Jarvis-Titan-M4-Activated
```

dhanesh-hf commited on 12 days ago

Commit

2ac4b1f

verified ·

1 Parent(s): 27f09e6

Sync config.json from Phase 0 base

Browse files

Files changed (1) hide show

config.json +126 -0

config.json ADDED Viewed

	@@ -0,0 +1,126 @@

+{
+  "transformers_version": "5.12.1",
+  "architectures": [
+    "JarvisTitanMoEForCausalLM"
+  ],
+  "output_hidden_states": false,
+  "return_dict": true,
+  "dtype": "bfloat16",
+  "chunk_size_feed_forward": 0,
+  "is_encoder_decoder": false,
+  "id2label": {
+    "0": "LABEL_0",
+    "1": "LABEL_1"
+  },
+  "label2id": {
+    "LABEL_0": 0,
+    "LABEL_1": 1
+  },
+  "problem_type": null,
+  "vocab_size": 152064,
+  "hidden_size": 3584,
+  "intermediate_size": 18944,
+  "num_hidden_layers": 28,
+  "num_attention_heads": 28,
+  "num_key_value_heads": 4,
+  "hidden_act": "silu",
+  "max_position_embeddings": 32768,
+  "initializer_range": 0.02,
+  "rms_norm_eps": 1e-06,
+  "use_cache": true,
+  "tie_word_embeddings": false,
+  "rope_parameters": {
+    "rope_theta": 1000000.0,
+    "rope_type": "default"
+  },
+  "use_sliding_window": false,
+  "sliding_window": 2048,
+  "max_window_layers": 28,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "attention_dropout": 0.0,
+  "pad_token_id": null,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "_name_or_path": "dhanesh-hf/Jarvis-Titan-V12-SFT-Merged",
+  "model_type": "jarvis_titan_moe",
+  "output_attentions": false,
+  "num_routed_experts": 8,
+  "num_shared_experts": 1,
+  "num_experts_per_tok": 2,
+  "expert_intermediate_size": 4736,
+  "routed_scaling_factor": 1.5,
+  "auto_map": {
+    "AutoConfig": "modeling_jarvis_titan_moe.JarvisTitanMoEConfig",
+    "AutoModelForCausalLM": "modeling_jarvis_titan_moe.JarvisTitanMoEForCausalLM"
+  },
+  "m4_calibrated": true,
+  "architecture_milestone": "M4",
+  "injection_layers": [
+    3,
+    7,
+    11,
+    15,
+    19,
+    23,
+    27
+  ],
+  "memory_dim": 512,
+  "d_reservoir": 512,
+  "sliding_window_size": 2048,
+  "tribrid_target_distribution": [
+    0.55,
+    0.25,
+    0.2
+  ],
+  "upstream_m4_adapter": "dhanesh-hf/Jarvis-Titan-M4-Calibrated-Adapter",
+  "base_backbone": "dhanesh-hf/Jarvis-Titan-V14-MoE-Merged",
+  "m4_architecture": "tribrid_dha3_mtp",
+  "dha3_holographic_decoupling": true,
+  "dha3_anchor_interval": 4,
+  "csa3_delta_caching": true,
+  "csa3_anchor_interval": 4,
+  "m4_bridge_layers": [
+    3,
+    7,
+    11,
+    15,
+    19,
+    23,
+    27
+  ],
+  "dynamic_mag_gating": true,
+  "dynamic_mag_soft_floor": 0.05,
+  "fim_regularization_lambda": 0.005,
+  "mtp_num_targets": 1,
+  "license": "other",
+  "license_name": "jtrl-v1.0"
+}