Instructions to use Hygaard/Inkling-2-Small-oQ2e with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use Hygaard/Inkling-2-Small-oQ2e with MLX:
# Make sure mlx-vlm is installed # pip install --upgrade mlx-vlm from mlx_vlm import load, generate from mlx_vlm.prompt_utils import apply_chat_template from mlx_vlm.utils import load_config # Load the model model, processor = load("Hygaard/Inkling-2-Small-oQ2e") config = load_config("Hygaard/Inkling-2-Small-oQ2e") # Prepare input image = ["http://images.cocodataset.org/val2017/000000039769.jpg"] prompt = "Describe this image." # Apply chat template formatted_prompt = apply_chat_template( processor, config, prompt, num_images=1 ) # Generate output output = generate(model, processor, formatted_prompt, image) print(output) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Pi
How to use Hygaard/Inkling-2-Small-oQ2e with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Hygaard/Inkling-2-Small-oQ2e"
Configure the model in Pi
# Install Pi: npm install -g @earendil-works/pi-coding-agent # Add to ~/.pi/agent/models.json: { "providers": { "mlx-lm": { "baseUrl": "http://localhost:8080/v1", "api": "openai-completions", "apiKey": "none", "models": [ { "id": "Hygaard/Inkling-2-Small-oQ2e" } ] } } }Run Pi
# Start Pi in your project directory: pi
- Hermes Agent
How to use Hygaard/Inkling-2-Small-oQ2e with Hermes Agent:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Hygaard/Inkling-2-Small-oQ2e"
Configure Hermes
# Install Hermes: curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash hermes setup # Point Hermes at the local server: hermes config set model.provider custom hermes config set model.base_url http://127.0.0.1:8080/v1 hermes config set model.default Hygaard/Inkling-2-Small-oQ2e
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use Hygaard/Inkling-2-Small-oQ2e with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "Hygaard/Inkling-2-Small-oQ2e"
Configure OpenClaw
# Install OpenClaw: npm install -g openclaw@latest # Register the local server and set it as the default model: openclaw onboard --non-interactive --mode local \ --auth-choice custom-api-key \ --custom-base-url http://127.0.0.1:8080/v1 \ --custom-model-id "Hygaard/Inkling-2-Small-oQ2e" \ --custom-provider-id mlx-lm \ --custom-compatibility openai \ --custom-text-input \ --accept-risk \ --skip-health
Run OpenClaw
openclaw agent --local --agent main --message "Hello from Hugging Face"
Download config.json from Hygaard/Inkling-2-Small-oQ2e: direct link, hf CLI and curl.
- Browser
- Download file 27.7 kB
-
https://huggingface.co/Hygaard/Inkling-2-Small-oQ2e/resolve/main/config.json
- Command line
-
hf download hf://Hygaard/Inkling-2-Small-oQ2e/config.json
-
curl -L -o config.json https://huggingface.co/Hygaard/Inkling-2-Small-oQ2e/resolve/main/config.json
27.7 kB
{
"architectures": [
"Inkling2ForConditionalGeneration"
],
"model_type": "inkling2",
"eos_token_id": 200006,
"text_config": {
"model_max_length": 1048576,
"torch_dtype": "bfloat16",
"hidden_size": 4608,
"num_hidden_layers": 48,
"vocab_size": 201024,
"num_attention_heads": 48,
"num_key_value_heads": 8,
"head_dim": 128,
"d_rel": 16,
"rel_extent": 1024,
"q_bias": false,
"o_bias": false,
"log_scaling_n_floor": 128000,
"log_scaling_alpha": 0.1,
"rms_norm_eps": 1e-06,
"pre_norm_pre_affine": false,
"final_norm_pre_affine": false,
"use_value_norm_no_gamma": true,
"qk_l2_clip_threshold": 22.627416997969522,
"rel_l2_clip_threshold": 8.0,
"local_layer_ids": [
0,
1,
2,
3,
4,
6,
7,
8,
9,
10,
12,
13,
14,
15,
16,
18,
19,
20,
21,
22,
24,
25,
26,
27,
28,
30,
31,
32,
33,
34,
36,
37,
38,
39,
40,
42,
43,
44,
45,
46
],
"sconv_kernel_size": 4,
"unpadded_vocab_size": 200058,
"final_logit_softcapping": 30.0,
"swa_head_dim": 128,
"swa_num_attention_heads": 48,
"swa_num_key_value_heads": 8,
"sliding_window_size": 1024,
"n_layers_per_attn_res_block": 6,
"attn_res_normalize_values": true,
"n_routed_experts": 384,
"num_experts_per_tok": 8,
"n_shared_experts": 0,
"intermediate_size": 2304,
"mlp_gate_softcap": 4.0,
"mlp_up_softcap": 25.0,
"route_scale": 8.0,
"use_gate_bias": true
},
"vision_config": {
"temporal_patch_size": 2,
"native_patch_size": 20,
"adapter_merge_size": 2,
"projection_hidden_dim": 4096,
"projector_bias": false,
"hidden_size": 1024,
"num_hidden_layers": 23,
"num_attention_heads": 16,
"mlp_ratio": 4.0,
"posemb_grid_size": 32,
"layer_norm_eps": 1e-05
},
"mtp_config": {
"hidden_size": 4608,
"num_hidden_layers": 5,
"num_attention_heads": 48,
"num_key_value_heads": 8,
"head_dim": 128,
"intermediate_size": 18432,
"max_position_embeddings": 1048576,
"torch_dtype": "bfloat16",
"q_bias": false,
"o_bias": false,
"rms_norm_eps": 1e-06,
"rope_theta": 1000000.0,
"local_layer_ids": [
0,
1,
3,
4
],
"sliding_window_size": 1024,
"block_size": 8,
"markov_rank": 256,
"markov_head_type": "rnn_hidden",
"target_layer_ids": [
5,
11,
17,
23,
29,
35,
41,
48
]
},
"quantization": {
"group_size": 64,
"bits": 2,
"mode": "affine",
"model.embed": {
"bits": 8,
"group_size": 64,
"mode": "affine"
},
"lm_head": {
"bits": 8,
"group_size": 64,
"mode": "affine"
},
"model.layers.0.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.0.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.1.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.1.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.10.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.10.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.11.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.11.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.11.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.11.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.12.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.12.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.13.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.13.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.14.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.14.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.15.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.15.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.16.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.16.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.17.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.17.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.17.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.17.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.18.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.18.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.19.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.19.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.2.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.2.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.20.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.20.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.21.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.21.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.22.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.22.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.23.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.23.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.23.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.23.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.24.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.24.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.25.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.25.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.26.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.26.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.27.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.27.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.28.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.28.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.29.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.29.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.29.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.29.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.3.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.3.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.30.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.30.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.31.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.31.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.32.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.32.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.33.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.33.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.34.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.34.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.35.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.35.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.35.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.35.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.36.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.36.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.37.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.37.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.38.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.38.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.39.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.39.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.4.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.4.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.40.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.40.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.41.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.41.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.41.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.41.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.42.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.42.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.43.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.43.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.44.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.44.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.45.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.45.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.46.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.46.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.47.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.47.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.47.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.47.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.5.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.5.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.5.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.5.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.6.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.6.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.7.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.7.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.8.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.8.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.9.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.9.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
}
},
"quantization_config": {
"group_size": 64,
"bits": 2,
"mode": "affine",
"model.embed": {
"bits": 8,
"group_size": 64,
"mode": "affine"
},
"lm_head": {
"bits": 8,
"group_size": 64,
"mode": "affine"
},
"model.layers.0.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.0.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.1.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.1.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.10.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.10.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.11.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.11.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.11.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.11.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.12.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.12.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.13.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.13.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.14.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.14.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.15.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.15.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.16.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.16.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.17.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.17.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.17.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.17.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.18.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.18.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.19.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.19.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.2.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.2.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.20.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.20.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.21.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.21.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.22.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.22.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.23.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.23.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.23.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.23.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.24.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.24.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.25.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.25.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.26.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.26.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.27.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.27.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.28.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.28.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.29.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.29.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.29.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.29.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.3.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.3.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.30.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.30.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.31.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.31.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.32.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.32.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.33.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.33.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.34.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.34.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.35.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.35.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.35.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.35.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.36.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.36.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.37.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.37.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.38.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.38.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.39.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.39.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.4.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.4.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.40.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.40.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.41.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.41.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.41.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.41.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.42.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.42.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.43.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.43.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.44.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.44.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.45.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.45.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.46.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.46.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.47.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.47.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.47.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.47.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.5.attn.q_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.5.attn.k_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.5.attn.v_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.5.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.6.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.6.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.7.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.7.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.8.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.8.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.9.attn.in_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
},
"model.layers.9.attn.o_proj": {
"bits": 8,
"group_size": 128,
"mode": "affine"
}
}
}
{
"architectures": [
"Inkling2ForConditionalGeneration"
],
"model_type": "inkling2",
"eos_token_id": 200006,
"text_config": {
"model_max_length": 1048576,
"torch_dtype": "bfloat16",
"hidden_size": 4608,
"num_hidden_layers": 48,
"vocab_size": 201024,
"num_attention_heads": 48,
"num_key_value_heads": 8,
"head_dim": 128,
"d_rel": 16,
"rel_extent": 1024,
"q_bias": false,
"o_bias": false,
"log_scaling_n_floor": 128000,
"log_scaling_alpha": 0.1,
"rms_norm_eps": 1e-06,
"pre_norm_pre_affine": false,
"final_norm_pre_affine": false,
"use_value_norm_no_gamma": true,
"qk_l2_clip_threshold": 22.627416997969522,
"rel_l2_clip_threshold": 8.0,
"local_layer_ids": [
0,
1,
2,
3,
4,
6,
7,
8,
9,
10,
12,
13,
14,
15,
16,
18,
19,
20,
21,
22,
24,
25,
26,
27,
28,
30,
31,
32,
33,
34,
36,
37,
38,
39,
40,
42,
43,
44,
45,
46
],
"sconv_kernel_size": 4,
"unpadded_vocab_size": 200058,
"final_logit_softcapping": 30.0,
"swa_head_dim": 128,
"swa_num_attention_heads": 48,
"swa_num_key_value_heads": 8,
"sliding_window_size": 1024,
"n_layers_per_attn_res_block": 6,
"attn_res_normalize_values": true,
"n_routed_experts": 384,
"num_experts_per_tok": 8,
"n_shared_experts": 0,
"intermediate_size": 2304,
"mlp_gate_softcap": 4.0,
"mlp_up_softcap": 25.0,
"route_scale": 8.0,
"use_gate_bias": true
},
"vision_config": {
"temporal_patch_size": 2,
"native_patch_size": 20,
"adapter_merge_size": 2,
"projection_hidden_dim": 4096,
"projector_bias": false,
"hidden_size": 1024,
"num_hidden_layers": 23,
"num_attention_heads": 16,
"mlp_ratio": 4.0,
"posemb_grid_size": 32,
"layer_norm_eps": 1e-05
},