Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK

Instructions to use Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK"

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": "Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK 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 "Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK"

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 Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK"

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 "Iambackup/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK" \
  --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"

Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK / jang_config.json

Iambackup

dealignai

Duplicate from dealignai/Nemotron-3.5-Lightning-30B-A3B-JANG_2L-CRACK

a698bd7 about 2 months ago

Raw History Blame Contribute Delete

107 kB

	{
	"quantization": {
	"method": "jang-importance",
	"profile": "JANG_2L",
	"target_bits": 2.0,
	"actual_bits": 3.73,
	"block_size": 64,
	"calibration_method": "weights",
	"quantization_method": "mse",
	"scoring_method": "weight-magnitude",
	"bit_widths_used": [
	2,
	3,
	4,
	6,
	8
	],
	"passthrough_bit_widths_used": [
	16
	],
	"passthrough_tensor_count": 115,
	"quantization_scheme": "asymmetric",
	"quantization_backend": "mx.quantize",
	"hadamard_rotation": false,
	"mlp_asymmetry_floor": true,
	"split_gate_up_quant": false,
	"split_gate_bits": null,
	"split_up_bits": null,
	"n2_down_bits": null,
	"n2_linear_attn_input_bits": null,
	"n2_linear_attn_out_bits": null,
	"n2_self_attn_bits": null,
	"n2_shared_expert_gate_up_bits": null,
	"n2_token_io_bits": null,
	"n2_lm_head_bits": null,
	"expert_prune_keep": null,
	"expert_prune_map": null,
	"expert_prune_method": null,
	"tensor_quantization_manifest_schema": 1,
	"tensor_quantization_manifest_count": 173,
	"tensor_quantization_manifest": {
	"backbone.embeddings": {
	"source_tensor": "backbone.embeddings.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.embeddings.weight",
	"scales_key": "backbone.embeddings.scales",
	"biases_key": "backbone.embeddings.biases",
	"weight_shape": [
	131072,
	504
	],
	"scales_shape": [
	131072,
	42
	],
	"biases_shape": [
	131072,
	42
	]
	},
	"backbone.layers.0.mixer.in_proj": {
	"source_tensor": "backbone.layers.0.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.0.mixer.in_proj.weight",
	"scales_key": "backbone.layers.0.mixer.in_proj.scales",
	"biases_key": "backbone.layers.0.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.0.mixer.out_proj": {
	"source_tensor": "backbone.layers.0.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.0.mixer.out_proj.weight",
	"scales_key": "backbone.layers.0.mixer.out_proj.scales",
	"biases_key": "backbone.layers.0.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.1.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.1.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.1.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.1.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.1.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.1.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.1.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.1.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.1.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.1.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.1.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.1.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.1.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.1.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.1.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.1.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.1.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.1.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.1.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.1.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.2.mixer.in_proj": {
	"source_tensor": "backbone.layers.2.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.2.mixer.in_proj.weight",
	"scales_key": "backbone.layers.2.mixer.in_proj.scales",
	"biases_key": "backbone.layers.2.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.2.mixer.out_proj": {
	"source_tensor": "backbone.layers.2.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.2.mixer.out_proj.weight",
	"scales_key": "backbone.layers.2.mixer.out_proj.scales",
	"biases_key": "backbone.layers.2.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.3.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.3.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.3.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.3.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.3.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.3.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.3.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.3.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.3.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.3.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.3.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.3.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.3.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.3.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.3.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.3.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.3.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.3.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.3.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.3.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.4.mixer.in_proj": {
	"source_tensor": "backbone.layers.4.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.4.mixer.in_proj.weight",
	"scales_key": "backbone.layers.4.mixer.in_proj.scales",
	"biases_key": "backbone.layers.4.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.4.mixer.out_proj": {
	"source_tensor": "backbone.layers.4.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.4.mixer.out_proj.weight",
	"scales_key": "backbone.layers.4.mixer.out_proj.scales",
	"biases_key": "backbone.layers.4.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.5.mixer.k_proj": {
	"source_tensor": "backbone.layers.5.mixer.k_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.5.mixer.k_proj.weight",
	"scales_key": "backbone.layers.5.mixer.k_proj.scales",
	"biases_key": "backbone.layers.5.mixer.k_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"backbone.layers.5.mixer.o_proj": {
	"source_tensor": "backbone.layers.5.mixer.o_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.5.mixer.o_proj.weight",
	"scales_key": "backbone.layers.5.mixer.o_proj.scales",
	"biases_key": "backbone.layers.5.mixer.o_proj.biases",
	"weight_shape": [
	2688,
	1024
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.5.mixer.q_proj": {
	"source_tensor": "backbone.layers.5.mixer.q_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.5.mixer.q_proj.weight",
	"scales_key": "backbone.layers.5.mixer.q_proj.scales",
	"biases_key": "backbone.layers.5.mixer.q_proj.biases",
	"weight_shape": [
	4096,
	672
	],
	"scales_shape": [
	4096,
	42
	],
	"biases_shape": [
	4096,
	42
	]
	},
	"backbone.layers.5.mixer.v_proj": {
	"source_tensor": "backbone.layers.5.mixer.v_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.5.mixer.v_proj.weight",
	"scales_key": "backbone.layers.5.mixer.v_proj.scales",
	"biases_key": "backbone.layers.5.mixer.v_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"backbone.layers.6.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.6.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.6.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.6.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.6.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.6.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.6.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.6.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.6.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.6.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.6.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.6.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.6.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.6.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.6.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.6.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.6.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.6.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.6.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.6.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.7.mixer.in_proj": {
	"source_tensor": "backbone.layers.7.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.7.mixer.in_proj.weight",
	"scales_key": "backbone.layers.7.mixer.in_proj.scales",
	"biases_key": "backbone.layers.7.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.7.mixer.out_proj": {
	"source_tensor": "backbone.layers.7.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.7.mixer.out_proj.weight",
	"scales_key": "backbone.layers.7.mixer.out_proj.scales",
	"biases_key": "backbone.layers.7.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.10.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.10.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.10.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.10.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.10.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.10.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.10.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.10.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.10.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.10.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.10.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.10.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.10.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.10.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.10.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.10.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.10.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.10.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.10.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.10.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.11.mixer.in_proj": {
	"source_tensor": "backbone.layers.11.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.11.mixer.in_proj.weight",
	"scales_key": "backbone.layers.11.mixer.in_proj.scales",
	"biases_key": "backbone.layers.11.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.11.mixer.out_proj": {
	"source_tensor": "backbone.layers.11.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.11.mixer.out_proj.weight",
	"scales_key": "backbone.layers.11.mixer.out_proj.scales",
	"biases_key": "backbone.layers.11.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.12.mixer.k_proj": {
	"source_tensor": "backbone.layers.12.mixer.k_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.12.mixer.k_proj.weight",
	"scales_key": "backbone.layers.12.mixer.k_proj.scales",
	"biases_key": "backbone.layers.12.mixer.k_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"backbone.layers.12.mixer.o_proj": {
	"source_tensor": "backbone.layers.12.mixer.o_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.12.mixer.o_proj.weight",
	"scales_key": "backbone.layers.12.mixer.o_proj.scales",
	"biases_key": "backbone.layers.12.mixer.o_proj.biases",
	"weight_shape": [
	2688,
	1024
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.12.mixer.q_proj": {
	"source_tensor": "backbone.layers.12.mixer.q_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.12.mixer.q_proj.weight",
	"scales_key": "backbone.layers.12.mixer.q_proj.scales",
	"biases_key": "backbone.layers.12.mixer.q_proj.biases",
	"weight_shape": [
	4096,
	672
	],
	"scales_shape": [
	4096,
	42
	],
	"biases_shape": [
	4096,
	42
	]
	},
	"backbone.layers.12.mixer.v_proj": {
	"source_tensor": "backbone.layers.12.mixer.v_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.12.mixer.v_proj.weight",
	"scales_key": "backbone.layers.12.mixer.v_proj.scales",
	"biases_key": "backbone.layers.12.mixer.v_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"backbone.layers.8.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.8.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.8.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.8.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.8.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.8.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.8.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.8.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.8.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.8.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.8.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.8.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.8.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.8.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.8.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.8.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.8.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.8.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.8.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.8.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.9.mixer.in_proj": {
	"source_tensor": "backbone.layers.9.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.9.mixer.in_proj.weight",
	"scales_key": "backbone.layers.9.mixer.in_proj.scales",
	"biases_key": "backbone.layers.9.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.9.mixer.out_proj": {
	"source_tensor": "backbone.layers.9.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.9.mixer.out_proj.weight",
	"scales_key": "backbone.layers.9.mixer.out_proj.scales",
	"biases_key": "backbone.layers.9.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.13.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.13.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.13.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.13.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.13.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.13.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.13.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.13.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.13.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.13.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.13.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.13.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.13.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.13.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.13.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.13.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.13.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.13.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.13.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.13.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.14.mixer.in_proj": {
	"source_tensor": "backbone.layers.14.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.14.mixer.in_proj.weight",
	"scales_key": "backbone.layers.14.mixer.in_proj.scales",
	"biases_key": "backbone.layers.14.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.14.mixer.out_proj": {
	"source_tensor": "backbone.layers.14.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.14.mixer.out_proj.weight",
	"scales_key": "backbone.layers.14.mixer.out_proj.scales",
	"biases_key": "backbone.layers.14.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.15.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.15.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.15.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.15.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.15.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.15.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.15.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.15.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.15.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.15.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.15.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.15.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.15.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.15.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.15.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.15.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.15.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.15.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.15.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.15.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.16.mixer.in_proj": {
	"source_tensor": "backbone.layers.16.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.16.mixer.in_proj.weight",
	"scales_key": "backbone.layers.16.mixer.in_proj.scales",
	"biases_key": "backbone.layers.16.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.16.mixer.out_proj": {
	"source_tensor": "backbone.layers.16.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.16.mixer.out_proj.weight",
	"scales_key": "backbone.layers.16.mixer.out_proj.scales",
	"biases_key": "backbone.layers.16.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.17.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.17.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.17.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.17.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.17.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.17.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.17.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.17.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.17.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.17.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.17.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.17.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.17.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.17.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.17.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.17.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.17.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.17.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.17.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.17.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.18.mixer.in_proj": {
	"source_tensor": "backbone.layers.18.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.18.mixer.in_proj.weight",
	"scales_key": "backbone.layers.18.mixer.in_proj.scales",
	"biases_key": "backbone.layers.18.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.18.mixer.out_proj": {
	"source_tensor": "backbone.layers.18.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.18.mixer.out_proj.weight",
	"scales_key": "backbone.layers.18.mixer.out_proj.scales",
	"biases_key": "backbone.layers.18.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.19.mixer.k_proj": {
	"source_tensor": "backbone.layers.19.mixer.k_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.19.mixer.k_proj.weight",
	"scales_key": "backbone.layers.19.mixer.k_proj.scales",
	"biases_key": "backbone.layers.19.mixer.k_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"backbone.layers.19.mixer.o_proj": {
	"source_tensor": "backbone.layers.19.mixer.o_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.19.mixer.o_proj.weight",
	"scales_key": "backbone.layers.19.mixer.o_proj.scales",
	"biases_key": "backbone.layers.19.mixer.o_proj.biases",
	"weight_shape": [
	2688,
	1024
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.19.mixer.q_proj": {
	"source_tensor": "backbone.layers.19.mixer.q_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.19.mixer.q_proj.weight",
	"scales_key": "backbone.layers.19.mixer.q_proj.scales",
	"biases_key": "backbone.layers.19.mixer.q_proj.biases",
	"weight_shape": [
	4096,
	672
	],
	"scales_shape": [
	4096,
	42
	],
	"biases_shape": [
	4096,
	42
	]
	},
	"backbone.layers.19.mixer.v_proj": {
	"source_tensor": "backbone.layers.19.mixer.v_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.19.mixer.v_proj.weight",
	"scales_key": "backbone.layers.19.mixer.v_proj.scales",
	"biases_key": "backbone.layers.19.mixer.v_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"backbone.layers.20.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.20.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.20.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.20.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.20.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.20.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.20.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.20.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.20.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.20.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.20.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.20.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.20.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.20.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.20.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.20.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.20.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.20.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.20.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.20.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.21.mixer.in_proj": {
	"source_tensor": "backbone.layers.21.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.21.mixer.in_proj.weight",
	"scales_key": "backbone.layers.21.mixer.in_proj.scales",
	"biases_key": "backbone.layers.21.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.21.mixer.out_proj": {
	"source_tensor": "backbone.layers.21.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.21.mixer.out_proj.weight",
	"scales_key": "backbone.layers.21.mixer.out_proj.scales",
	"biases_key": "backbone.layers.21.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.22.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.22.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.22.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.22.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.22.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.22.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.22.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.22.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.22.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.22.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.22.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.22.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.22.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.22.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.22.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.22.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.22.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.22.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.22.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.22.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.23.mixer.in_proj": {
	"source_tensor": "backbone.layers.23.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.23.mixer.in_proj.weight",
	"scales_key": "backbone.layers.23.mixer.in_proj.scales",
	"biases_key": "backbone.layers.23.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.23.mixer.out_proj": {
	"source_tensor": "backbone.layers.23.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.23.mixer.out_proj.weight",
	"scales_key": "backbone.layers.23.mixer.out_proj.scales",
	"biases_key": "backbone.layers.23.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.24.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.24.mixer.experts.127.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.24.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.24.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.24.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.24.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.24.mixer.experts.127.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.24.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.24.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.24.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.24.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.24.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.24.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.24.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.24.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.24.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.24.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.24.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.24.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.24.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.25.mixer.in_proj": {
	"source_tensor": "backbone.layers.25.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.25.mixer.in_proj.weight",
	"scales_key": "backbone.layers.25.mixer.in_proj.scales",
	"biases_key": "backbone.layers.25.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.25.mixer.out_proj": {
	"source_tensor": "backbone.layers.25.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.25.mixer.out_proj.weight",
	"scales_key": "backbone.layers.25.mixer.out_proj.scales",
	"biases_key": "backbone.layers.25.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.26.mixer.k_proj": {
	"source_tensor": "backbone.layers.26.mixer.k_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.26.mixer.k_proj.weight",
	"scales_key": "backbone.layers.26.mixer.k_proj.scales",
	"biases_key": "backbone.layers.26.mixer.k_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"backbone.layers.26.mixer.o_proj": {
	"source_tensor": "backbone.layers.26.mixer.o_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.26.mixer.o_proj.weight",
	"scales_key": "backbone.layers.26.mixer.o_proj.scales",
	"biases_key": "backbone.layers.26.mixer.o_proj.biases",
	"weight_shape": [
	2688,
	1024
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.26.mixer.q_proj": {
	"source_tensor": "backbone.layers.26.mixer.q_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.26.mixer.q_proj.weight",
	"scales_key": "backbone.layers.26.mixer.q_proj.scales",
	"biases_key": "backbone.layers.26.mixer.q_proj.biases",
	"weight_shape": [
	4096,
	672
	],
	"scales_shape": [
	4096,
	42
	],
	"biases_shape": [
	4096,
	42
	]
	},
	"backbone.layers.26.mixer.v_proj": {
	"source_tensor": "backbone.layers.26.mixer.v_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.26.mixer.v_proj.weight",
	"scales_key": "backbone.layers.26.mixer.v_proj.scales",
	"biases_key": "backbone.layers.26.mixer.v_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"backbone.layers.27.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.27.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.27.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.27.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.27.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.27.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.27.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.27.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.27.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.27.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.27.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.27.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.27.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.27.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.27.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.27.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.27.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.27.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.27.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.27.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.28.mixer.in_proj": {
	"source_tensor": "backbone.layers.28.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.28.mixer.in_proj.weight",
	"scales_key": "backbone.layers.28.mixer.in_proj.scales",
	"biases_key": "backbone.layers.28.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.28.mixer.out_proj": {
	"source_tensor": "backbone.layers.28.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.28.mixer.out_proj.weight",
	"scales_key": "backbone.layers.28.mixer.out_proj.scales",
	"biases_key": "backbone.layers.28.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.29.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.29.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.29.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.29.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.29.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.29.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.29.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.29.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.29.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.29.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.29.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.29.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.29.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.29.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.29.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.29.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.29.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.29.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.29.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.29.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.30.mixer.in_proj": {
	"source_tensor": "backbone.layers.30.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.30.mixer.in_proj.weight",
	"scales_key": "backbone.layers.30.mixer.in_proj.scales",
	"biases_key": "backbone.layers.30.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.30.mixer.out_proj": {
	"source_tensor": "backbone.layers.30.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.30.mixer.out_proj.weight",
	"scales_key": "backbone.layers.30.mixer.out_proj.scales",
	"biases_key": "backbone.layers.30.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.31.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.31.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.31.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.31.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.31.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.31.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.31.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.31.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.31.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.31.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.31.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.31.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.31.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.31.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.31.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.31.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.31.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.31.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.31.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.31.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.32.mixer.in_proj": {
	"source_tensor": "backbone.layers.32.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.32.mixer.in_proj.weight",
	"scales_key": "backbone.layers.32.mixer.in_proj.scales",
	"biases_key": "backbone.layers.32.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.32.mixer.out_proj": {
	"source_tensor": "backbone.layers.32.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.32.mixer.out_proj.weight",
	"scales_key": "backbone.layers.32.mixer.out_proj.scales",
	"biases_key": "backbone.layers.32.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.33.mixer.k_proj": {
	"source_tensor": "backbone.layers.33.mixer.k_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.33.mixer.k_proj.weight",
	"scales_key": "backbone.layers.33.mixer.k_proj.scales",
	"biases_key": "backbone.layers.33.mixer.k_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"backbone.layers.33.mixer.o_proj": {
	"source_tensor": "backbone.layers.33.mixer.o_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.33.mixer.o_proj.weight",
	"scales_key": "backbone.layers.33.mixer.o_proj.scales",
	"biases_key": "backbone.layers.33.mixer.o_proj.biases",
	"weight_shape": [
	2688,
	1024
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.33.mixer.q_proj": {
	"source_tensor": "backbone.layers.33.mixer.q_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.33.mixer.q_proj.weight",
	"scales_key": "backbone.layers.33.mixer.q_proj.scales",
	"biases_key": "backbone.layers.33.mixer.q_proj.biases",
	"weight_shape": [
	4096,
	672
	],
	"scales_shape": [
	4096,
	42
	],
	"biases_shape": [
	4096,
	42
	]
	},
	"backbone.layers.33.mixer.v_proj": {
	"source_tensor": "backbone.layers.33.mixer.v_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.33.mixer.v_proj.weight",
	"scales_key": "backbone.layers.33.mixer.v_proj.scales",
	"biases_key": "backbone.layers.33.mixer.v_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"backbone.layers.34.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.34.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.34.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.34.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.34.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.34.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.34.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.34.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.34.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.34.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.34.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.34.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.34.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.34.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.34.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.34.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.34.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.34.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.34.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.34.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.35.mixer.in_proj": {
	"source_tensor": "backbone.layers.35.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.35.mixer.in_proj.weight",
	"scales_key": "backbone.layers.35.mixer.in_proj.scales",
	"biases_key": "backbone.layers.35.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.35.mixer.out_proj": {
	"source_tensor": "backbone.layers.35.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.35.mixer.out_proj.weight",
	"scales_key": "backbone.layers.35.mixer.out_proj.scales",
	"biases_key": "backbone.layers.35.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.36.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.36.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.36.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.36.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.36.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.36.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.36.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.36.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.36.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.36.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.36.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.36.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.36.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.36.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.36.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.36.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.36.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.36.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.36.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.36.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.37.mixer.in_proj": {
	"source_tensor": "backbone.layers.37.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.37.mixer.in_proj.weight",
	"scales_key": "backbone.layers.37.mixer.in_proj.scales",
	"biases_key": "backbone.layers.37.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.37.mixer.out_proj": {
	"source_tensor": "backbone.layers.37.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.37.mixer.out_proj.weight",
	"scales_key": "backbone.layers.37.mixer.out_proj.scales",
	"biases_key": "backbone.layers.37.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.38.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.38.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.38.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.38.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.38.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.38.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.38.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.38.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.38.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.38.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.38.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.38.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.38.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.38.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.38.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.38.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.38.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.38.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.38.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.38.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.39.mixer.in_proj": {
	"source_tensor": "backbone.layers.39.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.39.mixer.in_proj.weight",
	"scales_key": "backbone.layers.39.mixer.in_proj.scales",
	"biases_key": "backbone.layers.39.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.39.mixer.out_proj": {
	"source_tensor": "backbone.layers.39.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.39.mixer.out_proj.weight",
	"scales_key": "backbone.layers.39.mixer.out_proj.scales",
	"biases_key": "backbone.layers.39.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.40.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.40.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.40.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.40.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.40.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.40.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.40.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.40.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.40.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.40.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.40.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.40.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.40.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.40.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.40.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.40.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.40.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.40.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.40.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.40.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.41.mixer.in_proj": {
	"source_tensor": "backbone.layers.41.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.41.mixer.in_proj.weight",
	"scales_key": "backbone.layers.41.mixer.in_proj.scales",
	"biases_key": "backbone.layers.41.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.41.mixer.out_proj": {
	"source_tensor": "backbone.layers.41.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.41.mixer.out_proj.weight",
	"scales_key": "backbone.layers.41.mixer.out_proj.scales",
	"biases_key": "backbone.layers.41.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.42.mixer.k_proj": {
	"source_tensor": "backbone.layers.42.mixer.k_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.42.mixer.k_proj.weight",
	"scales_key": "backbone.layers.42.mixer.k_proj.scales",
	"biases_key": "backbone.layers.42.mixer.k_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"backbone.layers.42.mixer.o_proj": {
	"source_tensor": "backbone.layers.42.mixer.o_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.42.mixer.o_proj.weight",
	"scales_key": "backbone.layers.42.mixer.o_proj.scales",
	"biases_key": "backbone.layers.42.mixer.o_proj.biases",
	"weight_shape": [
	2688,
	1024
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.42.mixer.q_proj": {
	"source_tensor": "backbone.layers.42.mixer.q_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.42.mixer.q_proj.weight",
	"scales_key": "backbone.layers.42.mixer.q_proj.scales",
	"biases_key": "backbone.layers.42.mixer.q_proj.biases",
	"weight_shape": [
	4096,
	672
	],
	"scales_shape": [
	4096,
	42
	],
	"biases_shape": [
	4096,
	42
	]
	},
	"backbone.layers.42.mixer.v_proj": {
	"source_tensor": "backbone.layers.42.mixer.v_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.42.mixer.v_proj.weight",
	"scales_key": "backbone.layers.42.mixer.v_proj.scales",
	"biases_key": "backbone.layers.42.mixer.v_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"backbone.layers.43.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.43.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.43.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.43.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.43.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.43.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.43.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.43.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.43.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.43.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.43.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.43.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.43.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.43.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.43.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.43.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.43.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.43.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.43.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.43.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.44.mixer.in_proj": {
	"source_tensor": "backbone.layers.44.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.44.mixer.in_proj.weight",
	"scales_key": "backbone.layers.44.mixer.in_proj.scales",
	"biases_key": "backbone.layers.44.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.44.mixer.out_proj": {
	"source_tensor": "backbone.layers.44.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.44.mixer.out_proj.weight",
	"scales_key": "backbone.layers.44.mixer.out_proj.scales",
	"biases_key": "backbone.layers.44.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.45.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.45.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.45.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.45.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.45.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.45.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.45.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.45.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.45.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.45.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.45.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.45.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.45.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.45.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.45.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.45.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.45.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.45.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.45.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.45.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.46.mixer.in_proj": {
	"source_tensor": "backbone.layers.46.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.46.mixer.in_proj.weight",
	"scales_key": "backbone.layers.46.mixer.in_proj.scales",
	"biases_key": "backbone.layers.46.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.46.mixer.out_proj": {
	"source_tensor": "backbone.layers.46.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.46.mixer.out_proj.weight",
	"scales_key": "backbone.layers.46.mixer.out_proj.scales",
	"biases_key": "backbone.layers.46.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.47.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.47.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.47.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.47.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.47.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.47.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.47.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.47.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.47.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.47.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.47.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.47.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.47.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.47.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.47.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.47.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.47.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.47.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.47.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.47.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.48.mixer.in_proj": {
	"source_tensor": "backbone.layers.48.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.48.mixer.in_proj.weight",
	"scales_key": "backbone.layers.48.mixer.in_proj.scales",
	"biases_key": "backbone.layers.48.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.48.mixer.out_proj": {
	"source_tensor": "backbone.layers.48.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.48.mixer.out_proj.weight",
	"scales_key": "backbone.layers.48.mixer.out_proj.scales",
	"biases_key": "backbone.layers.48.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.49.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.49.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.49.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.49.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.49.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.49.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.49.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.49.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.49.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.49.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.49.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.49.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.49.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.49.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.49.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.49.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.49.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.49.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.49.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.49.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"backbone.layers.50.mixer.in_proj": {
	"source_tensor": "backbone.layers.50.mixer.in_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.50.mixer.in_proj.weight",
	"scales_key": "backbone.layers.50.mixer.in_proj.scales",
	"biases_key": "backbone.layers.50.mixer.in_proj.biases",
	"weight_shape": [
	10304,
	504
	],
	"scales_shape": [
	10304,
	42
	],
	"biases_shape": [
	10304,
	42
	]
	},
	"backbone.layers.50.mixer.out_proj": {
	"source_tensor": "backbone.layers.50.mixer.out_proj.weight",
	"bits": 6,
	"group_size": 64,
	"weight_key": "backbone.layers.50.mixer.out_proj.weight",
	"scales_key": "backbone.layers.50.mixer.out_proj.scales",
	"biases_key": "backbone.layers.50.mixer.out_proj.biases",
	"weight_shape": [
	2688,
	768
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"backbone.layers.51.mixer.switch_mlp.fc2": {
	"source_tensor": "backbone.layers.51.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "backbone.layers.51.mixer.switch_mlp.fc2.weight",
	"scales_key": "backbone.layers.51.mixer.switch_mlp.fc2.scales",
	"biases_key": "backbone.layers.51.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"backbone.layers.51.mixer.switch_mlp.fc1": {
	"source_tensor": "backbone.layers.51.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "backbone.layers.51.mixer.switch_mlp.fc1.weight",
	"scales_key": "backbone.layers.51.mixer.switch_mlp.fc1.scales",
	"biases_key": "backbone.layers.51.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"backbone.layers.51.mixer.shared_experts.down_proj": {
	"source_tensor": "backbone.layers.51.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.51.mixer.shared_experts.down_proj.weight",
	"scales_key": "backbone.layers.51.mixer.shared_experts.down_proj.scales",
	"biases_key": "backbone.layers.51.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"backbone.layers.51.mixer.shared_experts.up_proj": {
	"source_tensor": "backbone.layers.51.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "backbone.layers.51.mixer.shared_experts.up_proj.weight",
	"scales_key": "backbone.layers.51.mixer.shared_experts.up_proj.scales",
	"biases_key": "backbone.layers.51.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	},
	"lm_head": {
	"source_tensor": "lm_head.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "lm_head.weight",
	"scales_key": "lm_head.scales",
	"biases_key": "lm_head.biases",
	"weight_shape": [
	131072,
	672
	],
	"scales_shape": [
	131072,
	42
	],
	"biases_shape": [
	131072,
	42
	]
	},
	"mtp.layers.0.eh_proj": {
	"source_tensor": "mtp.layers.0.eh_proj.weight",
	"bits": 2,
	"group_size": 64,
	"weight_key": "mtp.layers.0.eh_proj.weight",
	"scales_key": "mtp.layers.0.eh_proj.scales",
	"biases_key": "mtp.layers.0.eh_proj.biases",
	"weight_shape": [
	2688,
	336
	],
	"scales_shape": [
	2688,
	84
	],
	"biases_shape": [
	2688,
	84
	]
	},
	"mtp.layers.0.mixer.k_proj": {
	"source_tensor": "mtp.layers.0.mixer.k_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "mtp.layers.0.mixer.k_proj.weight",
	"scales_key": "mtp.layers.0.mixer.k_proj.scales",
	"biases_key": "mtp.layers.0.mixer.k_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"mtp.layers.0.mixer.o_proj": {
	"source_tensor": "mtp.layers.0.mixer.o_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "mtp.layers.0.mixer.o_proj.weight",
	"scales_key": "mtp.layers.0.mixer.o_proj.scales",
	"biases_key": "mtp.layers.0.mixer.o_proj.biases",
	"weight_shape": [
	2688,
	1024
	],
	"scales_shape": [
	2688,
	64
	],
	"biases_shape": [
	2688,
	64
	]
	},
	"mtp.layers.0.mixer.q_proj": {
	"source_tensor": "mtp.layers.0.mixer.q_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "mtp.layers.0.mixer.q_proj.weight",
	"scales_key": "mtp.layers.0.mixer.q_proj.scales",
	"biases_key": "mtp.layers.0.mixer.q_proj.biases",
	"weight_shape": [
	4096,
	672
	],
	"scales_shape": [
	4096,
	42
	],
	"biases_shape": [
	4096,
	42
	]
	},
	"mtp.layers.0.mixer.v_proj": {
	"source_tensor": "mtp.layers.0.mixer.v_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "mtp.layers.0.mixer.v_proj.weight",
	"scales_key": "mtp.layers.0.mixer.v_proj.scales",
	"biases_key": "mtp.layers.0.mixer.v_proj.biases",
	"weight_shape": [
	256,
	672
	],
	"scales_shape": [
	256,
	42
	],
	"biases_shape": [
	256,
	42
	]
	},
	"mtp.layers.1.mixer.switch_mlp.fc2": {
	"source_tensor": "mtp.layers.1.mixer.experts.99.down_proj.weight",
	"bits": 3,
	"group_size": 64,
	"weight_key": "mtp.layers.1.mixer.switch_mlp.fc2.weight",
	"scales_key": "mtp.layers.1.mixer.switch_mlp.fc2.scales",
	"biases_key": "mtp.layers.1.mixer.switch_mlp.fc2.biases",
	"weight_shape": [
	128,
	2688,
	174
	],
	"scales_shape": [
	128,
	2688,
	29
	],
	"biases_shape": [
	128,
	2688,
	29
	]
	},
	"mtp.layers.1.mixer.switch_mlp.fc1": {
	"source_tensor": "mtp.layers.1.mixer.experts.99.up_proj.weight",
	"bits": 4,
	"group_size": 64,
	"weight_key": "mtp.layers.1.mixer.switch_mlp.fc1.weight",
	"scales_key": "mtp.layers.1.mixer.switch_mlp.fc1.scales",
	"biases_key": "mtp.layers.1.mixer.switch_mlp.fc1.biases",
	"weight_shape": [
	128,
	1856,
	336
	],
	"scales_shape": [
	128,
	1856,
	42
	],
	"biases_shape": [
	128,
	1856,
	42
	]
	},
	"mtp.layers.1.mixer.shared_experts.down_proj": {
	"source_tensor": "mtp.layers.1.mixer.shared_experts.down_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "mtp.layers.1.mixer.shared_experts.down_proj.weight",
	"scales_key": "mtp.layers.1.mixer.shared_experts.down_proj.scales",
	"biases_key": "mtp.layers.1.mixer.shared_experts.down_proj.biases",
	"weight_shape": [
	2688,
	928
	],
	"scales_shape": [
	2688,
	58
	],
	"biases_shape": [
	2688,
	58
	]
	},
	"mtp.layers.1.mixer.shared_experts.up_proj": {
	"source_tensor": "mtp.layers.1.mixer.shared_experts.up_proj.weight",
	"bits": 8,
	"group_size": 64,
	"weight_key": "mtp.layers.1.mixer.shared_experts.up_proj.weight",
	"scales_key": "mtp.layers.1.mixer.shared_experts.up_proj.scales",
	"biases_key": "mtp.layers.1.mixer.shared_experts.up_proj.biases",
	"weight_shape": [
	3712,
	672
	],
	"scales_shape": [
	3712,
	42
	],
	"biases_shape": [
	3712,
	42
	]
	}
	}
	},
	"source_model": {
	"name": "NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16",
	"dtype": "bfloat16",
	"parameters": "2.6B"
	},
	"architecture": {
	"type": "moe",
	"attention": "gqa",
	"has_vision": false,
	"has_ssm": false,
	"has_moe": true
	},
	"runtime": {
	"total_weight_bytes": 17415865096,
	"total_weight_gb": 16.22,
	"bundle_has_mtp": true,
	"mtp_layers": 1,
	"mtp_mode": "preserved_enabled"
	},
	"mtp": {
	"artifact_available": true,
	"runtime_available": false,
	"num_nextn_predict_layers": 1,
	"shape": "deepseek_v3_eh_proj",
	"shares_embeddings_and_lm_head": true
	},
	"bundle_has_mtp": true,
	"mtp_layers": 1,
	"capabilities": {
	"reasoning_parser": "deepseek_r1",
	"tool_parser": "nemotron",
	"think_in_template": true,
	"supports_tools": true,
	"supports_thinking": true,
	"family": "nemotron_h",
	"modality": "text",
	"modalities": {
	"text": true,
	"vision": false,
	"audio": false,
	"video": false
	},
	"has_vision": false,
	"has_audio": false,
	"has_video": false,
	"cache_type": "hybrid",
	"default_reasoning": "on"
	},
	"format": "jang",
	"format_version": "2.0",
	"chat": {
	"sampling_defaults": {
	"temperature": 1.0,
	"top_p": 0.95,
	"top_k": 0,
	"repetition_penalty": 1.0,
	"source": "vendor_card+generation_config_2026-08-11"
	},
	"add_bos_token": false,
	"stop_token_ids": [
	2,
	11
	]
	},
	"reasoning": {
	"supported": true,
	"parser": "deepseek_r1",
	"default": "on",
	"think_in_template": true,
	"tiers": null,
	"budget": "server_side",
	"enable_kwarg": "enable_thinking",
	"off_is_prefilled_empty_block": true,
	"truncate_history_thinking_default": true
	},
	"tools": {
	"supported": true,
	"parser": "nemotron",
	"dialect": "xml_function",
	"tools_in_system_prompt": true,
	"tool_results_role": "tool",
	"force_nonempty_content_supported": false
	}
	}