Text Generation
MLX
Safetensors
modilify_mk2
diffusion
mixture-of-experts
custom-code
modilify-mk2
conversational
Instructions to use modilify/Modilify-Mk2-mlx with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use modilify/Modilify-Mk2-mlx 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("modilify/Modilify-Mk2-mlx") 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
- Pi
How to use modilify/Modilify-Mk2-mlx with Pi:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "modilify/Modilify-Mk2-mlx"
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": "modilify/Modilify-Mk2-mlx" } ] } } }Run Pi
# Start Pi in your project directory: pi
- MLX LM
How to use modilify/Modilify-Mk2-mlx with MLX LM:
Generate or start a chat session
# Install MLX LM uv tool install mlx-lm # Interactive chat REPL mlx_lm.chat --model "modilify/Modilify-Mk2-mlx"
Run an OpenAI-compatible server
# Install MLX LM uv tool install mlx-lm # Start the server mlx_lm.server --model "modilify/Modilify-Mk2-mlx" # Calling the OpenAI-compatible server with curl curl -X POST "http://localhost:8080/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "modilify/Modilify-Mk2-mlx", "messages": [ {"role": "user", "content": "Hello"} ] }' - Hermes Agent
How to use modilify/Modilify-Mk2-mlx 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 "modilify/Modilify-Mk2-mlx"
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 modilify/Modilify-Mk2-mlx
Run Hermes
hermes
- Atomic Chat
- OpenClaw
How to use modilify/Modilify-Mk2-mlx with OpenClaw:
Start the MLX server
# Install MLX LM: uv tool install mlx-lm # Start a local OpenAI-compatible server: mlx_lm.server --model "modilify/Modilify-Mk2-mlx"
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 "modilify/Modilify-Mk2-mlx" \ --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 model.safetensors.index.json from modilify/Modilify-Mk2-mlx: direct link, hf CLI and curl.
- Browser
- Download file 121 kB
-
https://huggingface.co/modilify/Modilify-Mk2-mlx/resolve/main/model.safetensors.index.json
- Command line
-
hf download hf://modilify/Modilify-Mk2-mlx/model.safetensors.index.json
-
curl -L -o model.safetensors.index.json https://huggingface.co/modilify/Modilify-Mk2-mlx/resolve/main/model.safetensors.index.json
121 kB
{
"metadata": {
"total_parameters": 25895691125,
"total_size": 51791503298
},
"weight_map": {
"latent_deliberation.blocks.0.attn.k_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.attn.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.attn.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.attn.q_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.attn.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.attn.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.ff.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.ff.gate.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.ff.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.ff_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.attn.k_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.attn.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.attn.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.attn.q_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.attn.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.attn.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.ff.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.ff.gate.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.ff.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.ff_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.attn.k_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.attn.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.attn.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.attn.q_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.attn.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.attn.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.ff.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.ff.gate.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.ff.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.ff_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.attn.k_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.attn.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.attn.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.attn.q_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.attn.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.attn.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.ff.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.ff.gate.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.ff.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.ff_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.experience_in.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.output_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.persistent_memory_bus.alpha": "model-00001-of-00016.safetensors",
"latent_deliberation.reason_embed.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.a_log": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.b_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.dt_bias": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.f_proj.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.f_proj.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.g_proj.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.g_proj.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.w_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.a_log": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.b_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.dt_bias": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.f_proj.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.f_proj.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.g_proj.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.g_proj.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.w_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.probe_embed.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.a_log": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.b_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.dt_bias": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.f_proj.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.f_proj.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.g_proj.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.g_proj.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.w_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.address_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.alpha": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.memory_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.o_proj.0.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.o_proj.1.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.o_proj.2.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.o_proj.3.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.o_proj.4.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.q_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.q_proj.0.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.q_proj.1.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.q_proj.2.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.q_proj.3.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.q_proj.4.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.rel_bias": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.v_proj.weight": "model-00001-of-00016.safetensors",
"model.decoder.embed_tokens.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.experts.down_proj": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.experts.gate_up_proj": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.experts.lora_down_a": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.experts.lora_down_b": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.experts.lora_gate_up_a": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.experts.lora_gate_up_b": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.input_layernorm.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.layer_scalar": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.mlp.down_proj.base.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.mlp.down_proj.lora_a": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.mlp.down_proj.lora_b": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.mlp.gate_proj.base.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.mlp.gate_proj.lora_a": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.mlp.gate_proj.lora_b": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.mlp.up_proj.base.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.mlp.up_proj.lora_a": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.mlp.up_proj.lora_b": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.post_attention_layernorm.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.post_feedforward_layernorm_1.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.post_feedforward_layernorm_2.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.pre_feedforward_layernorm_2.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.router.per_expert_scale": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.router.proj.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.router.scale": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.k_norm.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.k_proj.base.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.k_proj.lora_a": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.k_proj.lora_b": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.o_proj.base.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.o_proj.lora_a": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.o_proj.lora_b": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.q_norm.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.q_proj.base.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.q_proj.lora_a": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.q_proj.lora_b": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.v_proj.base.weight": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.v_proj.lora_a": "model-00001-of-00016.safetensors",
"model.decoder.layers.0.self_attn.v_proj.lora_b": "model-00001-of-00016.safetensors",
"model.decoder.layers.1.experts.down_proj": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.experts.gate_up_proj": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.experts.lora_down_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.experts.lora_down_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.experts.lora_gate_up_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.experts.lora_gate_up_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.input_layernorm.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.layer_scalar": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.mlp.down_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.mlp.down_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.mlp.down_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.mlp.gate_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.mlp.gate_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.mlp.gate_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.mlp.up_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.mlp.up_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.mlp.up_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.post_feedforward_layernorm.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.post_feedforward_layernorm_1.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.post_feedforward_layernorm_2.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.pre_feedforward_layernorm.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.pre_feedforward_layernorm_2.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.router.per_expert_scale": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.router.proj.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.router.scale": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.k_norm.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.k_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.k_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.k_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.o_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.o_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.o_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.q_norm.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.q_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.q_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.q_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.v_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.v_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.1.self_attn.v_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.10.experts.down_proj": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.experts.gate_up_proj": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.experts.lora_down_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.experts.lora_down_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.experts.lora_gate_up_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.experts.lora_gate_up_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.input_layernorm.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.layer_scalar": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.mlp.down_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.mlp.down_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.mlp.down_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.mlp.gate_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.mlp.gate_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.mlp.gate_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.mlp.up_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.mlp.up_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.mlp.up_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.post_feedforward_layernorm.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.post_feedforward_layernorm_1.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.post_feedforward_layernorm_2.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.pre_feedforward_layernorm.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.pre_feedforward_layernorm_2.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.router.per_expert_scale": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.router.proj.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.router.scale": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.k_norm.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.k_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.k_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.k_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.o_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.o_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.o_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.q_norm.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.q_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.q_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.q_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.v_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.v_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.10.self_attn.v_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.11.experts.down_proj": "model-00006-of-00016.safetensors",
"model.decoder.layers.11.experts.gate_up_proj": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.experts.lora_down_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.experts.lora_down_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.experts.lora_gate_up_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.experts.lora_gate_up_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.input_layernorm.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.layer_scalar": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.mlp.down_proj.base.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.mlp.down_proj.lora_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.mlp.down_proj.lora_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.mlp.gate_proj.base.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.mlp.gate_proj.lora_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.mlp.gate_proj.lora_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.mlp.up_proj.base.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.mlp.up_proj.lora_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.mlp.up_proj.lora_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.post_feedforward_layernorm.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.post_feedforward_layernorm_1.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.post_feedforward_layernorm_2.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.pre_feedforward_layernorm.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.pre_feedforward_layernorm_2.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.router.per_expert_scale": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.router.proj.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.router.scale": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.self_attn.k_norm.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.self_attn.k_proj.base.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.self_attn.k_proj.lora_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.self_attn.k_proj.lora_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.self_attn.o_proj.base.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.self_attn.o_proj.lora_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.self_attn.o_proj.lora_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.self_attn.q_norm.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.self_attn.q_proj.base.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.self_attn.q_proj.lora_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.11.self_attn.q_proj.lora_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.experts.down_proj": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.experts.gate_up_proj": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.experts.lora_down_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.experts.lora_down_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.experts.lora_gate_up_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.experts.lora_gate_up_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.input_layernorm.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.layer_scalar": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.mlp.down_proj.base.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.mlp.down_proj.lora_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.mlp.down_proj.lora_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.mlp.gate_proj.base.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.mlp.gate_proj.lora_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.mlp.gate_proj.lora_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.mlp.up_proj.base.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.mlp.up_proj.lora_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.mlp.up_proj.lora_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.post_feedforward_layernorm.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.post_feedforward_layernorm_1.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.post_feedforward_layernorm_2.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.pre_feedforward_layernorm.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.pre_feedforward_layernorm_2.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.router.per_expert_scale": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.router.proj.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.router.scale": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.k_norm.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.k_proj.base.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.k_proj.lora_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.k_proj.lora_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.o_proj.base.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.o_proj.lora_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.o_proj.lora_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.q_norm.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.q_proj.base.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.q_proj.lora_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.q_proj.lora_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.v_proj.base.weight": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.v_proj.lora_a": "model-00007-of-00016.safetensors",
"model.decoder.layers.12.self_attn.v_proj.lora_b": "model-00007-of-00016.safetensors",
"model.decoder.layers.13.experts.down_proj": "model-00007-of-00016.safetensors",
"model.decoder.layers.13.experts.gate_up_proj": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.experts.lora_down_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.experts.lora_down_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.experts.lora_gate_up_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.experts.lora_gate_up_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.input_layernorm.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.layer_scalar": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.mlp.down_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.mlp.down_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.mlp.down_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.mlp.gate_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.mlp.gate_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.mlp.gate_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.mlp.up_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.mlp.up_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.mlp.up_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.post_feedforward_layernorm.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.post_feedforward_layernorm_1.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.post_feedforward_layernorm_2.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.pre_feedforward_layernorm.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.pre_feedforward_layernorm_2.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.router.per_expert_scale": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.router.proj.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.router.scale": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.k_norm.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.k_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.k_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.k_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.o_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.o_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.o_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.q_norm.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.q_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.q_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.q_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.v_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.v_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.13.self_attn.v_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.experts.down_proj": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.experts.gate_up_proj": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.experts.lora_down_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.experts.lora_down_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.experts.lora_gate_up_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.experts.lora_gate_up_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.input_layernorm.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.layer_scalar": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.mlp.down_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.mlp.down_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.mlp.down_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.mlp.gate_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.mlp.gate_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.mlp.gate_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.mlp.up_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.mlp.up_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.mlp.up_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.post_feedforward_layernorm.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.post_feedforward_layernorm_1.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.post_feedforward_layernorm_2.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.pre_feedforward_layernorm.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.pre_feedforward_layernorm_2.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.router.per_expert_scale": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.router.proj.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.router.scale": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.k_norm.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.k_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.k_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.k_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.o_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.o_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.o_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.q_norm.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.q_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.q_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.q_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.v_proj.base.weight": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.v_proj.lora_a": "model-00008-of-00016.safetensors",
"model.decoder.layers.14.self_attn.v_proj.lora_b": "model-00008-of-00016.safetensors",
"model.decoder.layers.15.experts.down_proj": "model-00008-of-00016.safetensors",
"model.decoder.layers.15.experts.gate_up_proj": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.experts.lora_down_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.experts.lora_down_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.experts.lora_gate_up_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.experts.lora_gate_up_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.input_layernorm.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.layer_scalar": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.mlp.down_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.mlp.down_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.mlp.down_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.mlp.gate_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.mlp.gate_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.mlp.gate_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.mlp.up_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.mlp.up_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.mlp.up_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.post_feedforward_layernorm.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.post_feedforward_layernorm_1.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.post_feedforward_layernorm_2.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.pre_feedforward_layernorm.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.pre_feedforward_layernorm_2.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.router.per_expert_scale": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.router.proj.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.router.scale": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.k_norm.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.k_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.k_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.k_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.o_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.o_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.o_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.q_norm.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.q_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.q_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.q_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.v_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.v_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.15.self_attn.v_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.experts.down_proj": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.experts.gate_up_proj": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.experts.lora_down_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.experts.lora_down_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.experts.lora_gate_up_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.experts.lora_gate_up_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.input_layernorm.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.layer_scalar": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.mlp.down_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.mlp.down_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.mlp.down_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.mlp.gate_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.mlp.gate_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.mlp.gate_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.mlp.up_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.mlp.up_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.mlp.up_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.post_feedforward_layernorm.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.post_feedforward_layernorm_1.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.post_feedforward_layernorm_2.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.pre_feedforward_layernorm.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.pre_feedforward_layernorm_2.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.router.per_expert_scale": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.router.proj.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.router.scale": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.k_norm.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.k_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.k_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.k_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.o_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.o_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.o_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.q_norm.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.q_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.q_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.q_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.v_proj.base.weight": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.v_proj.lora_a": "model-00009-of-00016.safetensors",
"model.decoder.layers.16.self_attn.v_proj.lora_b": "model-00009-of-00016.safetensors",
"model.decoder.layers.17.experts.down_proj": "model-00009-of-00016.safetensors",
"model.decoder.layers.17.experts.gate_up_proj": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.experts.lora_down_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.experts.lora_down_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.experts.lora_gate_up_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.experts.lora_gate_up_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.input_layernorm.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.layer_scalar": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.mlp.down_proj.base.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.mlp.down_proj.lora_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.mlp.down_proj.lora_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.mlp.gate_proj.base.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.mlp.gate_proj.lora_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.mlp.gate_proj.lora_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.mlp.up_proj.base.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.mlp.up_proj.lora_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.mlp.up_proj.lora_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.post_feedforward_layernorm.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.post_feedforward_layernorm_1.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.post_feedforward_layernorm_2.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.pre_feedforward_layernorm.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.pre_feedforward_layernorm_2.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.router.per_expert_scale": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.router.proj.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.router.scale": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.self_attn.k_norm.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.self_attn.k_proj.base.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.self_attn.k_proj.lora_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.self_attn.k_proj.lora_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.self_attn.o_proj.base.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.self_attn.o_proj.lora_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.self_attn.o_proj.lora_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.self_attn.q_norm.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.self_attn.q_proj.base.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.self_attn.q_proj.lora_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.17.self_attn.q_proj.lora_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.experts.down_proj": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.experts.gate_up_proj": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.experts.lora_down_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.experts.lora_down_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.experts.lora_gate_up_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.experts.lora_gate_up_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.input_layernorm.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.layer_scalar": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.mlp.down_proj.base.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.mlp.down_proj.lora_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.mlp.down_proj.lora_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.mlp.gate_proj.base.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.mlp.gate_proj.lora_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.mlp.gate_proj.lora_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.mlp.up_proj.base.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.mlp.up_proj.lora_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.mlp.up_proj.lora_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.post_feedforward_layernorm.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.post_feedforward_layernorm_1.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.post_feedforward_layernorm_2.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.pre_feedforward_layernorm.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.pre_feedforward_layernorm_2.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.router.per_expert_scale": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.router.proj.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.router.scale": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.k_norm.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.k_proj.base.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.k_proj.lora_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.k_proj.lora_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.o_proj.base.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.o_proj.lora_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.o_proj.lora_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.q_norm.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.q_proj.base.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.q_proj.lora_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.q_proj.lora_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.v_proj.base.weight": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.v_proj.lora_a": "model-00010-of-00016.safetensors",
"model.decoder.layers.18.self_attn.v_proj.lora_b": "model-00010-of-00016.safetensors",
"model.decoder.layers.19.experts.down_proj": "model-00010-of-00016.safetensors",
"model.decoder.layers.19.experts.gate_up_proj": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.experts.lora_down_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.experts.lora_down_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.experts.lora_gate_up_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.experts.lora_gate_up_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.input_layernorm.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.layer_scalar": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.mlp.down_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.mlp.down_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.mlp.down_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.mlp.gate_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.mlp.gate_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.mlp.gate_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.mlp.up_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.mlp.up_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.mlp.up_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.post_feedforward_layernorm.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.post_feedforward_layernorm_1.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.post_feedforward_layernorm_2.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.pre_feedforward_layernorm.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.pre_feedforward_layernorm_2.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.router.per_expert_scale": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.router.proj.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.router.scale": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.k_norm.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.k_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.k_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.k_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.o_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.o_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.o_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.q_norm.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.q_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.q_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.q_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.v_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.v_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.19.self_attn.v_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.2.experts.down_proj": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.experts.gate_up_proj": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.experts.lora_down_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.experts.lora_down_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.experts.lora_gate_up_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.experts.lora_gate_up_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.input_layernorm.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.layer_scalar": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.mlp.down_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.mlp.down_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.mlp.down_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.mlp.gate_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.mlp.gate_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.mlp.gate_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.mlp.up_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.mlp.up_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.mlp.up_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.post_feedforward_layernorm.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.post_feedforward_layernorm_1.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.post_feedforward_layernorm_2.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.pre_feedforward_layernorm.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.pre_feedforward_layernorm_2.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.router.per_expert_scale": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.router.proj.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.router.scale": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.k_norm.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.k_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.k_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.k_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.o_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.o_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.o_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.q_norm.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.q_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.q_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.q_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.v_proj.base.weight": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.v_proj.lora_a": "model-00002-of-00016.safetensors",
"model.decoder.layers.2.self_attn.v_proj.lora_b": "model-00002-of-00016.safetensors",
"model.decoder.layers.20.experts.down_proj": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.experts.gate_up_proj": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.experts.lora_down_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.experts.lora_down_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.experts.lora_gate_up_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.experts.lora_gate_up_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.input_layernorm.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.layer_scalar": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.mlp.down_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.mlp.down_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.mlp.down_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.mlp.gate_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.mlp.gate_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.mlp.gate_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.mlp.up_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.mlp.up_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.mlp.up_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.post_feedforward_layernorm.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.post_feedforward_layernorm_1.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.post_feedforward_layernorm_2.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.pre_feedforward_layernorm.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.pre_feedforward_layernorm_2.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.router.per_expert_scale": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.router.proj.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.router.scale": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.k_norm.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.k_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.k_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.k_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.o_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.o_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.o_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.q_norm.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.q_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.q_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.q_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.v_proj.base.weight": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.v_proj.lora_a": "model-00011-of-00016.safetensors",
"model.decoder.layers.20.self_attn.v_proj.lora_b": "model-00011-of-00016.safetensors",
"model.decoder.layers.21.experts.down_proj": "model-00011-of-00016.safetensors",
"model.decoder.layers.21.experts.gate_up_proj": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.experts.lora_down_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.experts.lora_down_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.experts.lora_gate_up_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.experts.lora_gate_up_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.input_layernorm.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.layer_scalar": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.mlp.down_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.mlp.down_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.mlp.down_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.mlp.gate_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.mlp.gate_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.mlp.gate_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.mlp.up_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.mlp.up_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.mlp.up_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.post_feedforward_layernorm.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.post_feedforward_layernorm_1.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.post_feedforward_layernorm_2.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.pre_feedforward_layernorm.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.pre_feedforward_layernorm_2.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.router.per_expert_scale": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.router.proj.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.router.scale": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.k_norm.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.k_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.k_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.k_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.o_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.o_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.o_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.q_norm.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.q_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.q_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.q_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.v_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.v_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.21.self_attn.v_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.experts.down_proj": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.experts.gate_up_proj": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.experts.lora_down_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.experts.lora_down_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.experts.lora_gate_up_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.experts.lora_gate_up_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.input_layernorm.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.layer_scalar": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.mlp.down_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.mlp.down_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.mlp.down_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.mlp.gate_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.mlp.gate_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.mlp.gate_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.mlp.up_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.mlp.up_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.mlp.up_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.post_feedforward_layernorm.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.post_feedforward_layernorm_1.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.post_feedforward_layernorm_2.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.pre_feedforward_layernorm.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.pre_feedforward_layernorm_2.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.router.per_expert_scale": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.router.proj.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.router.scale": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.k_norm.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.k_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.k_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.k_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.o_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.o_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.o_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.q_norm.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.q_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.q_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.q_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.v_proj.base.weight": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.v_proj.lora_a": "model-00012-of-00016.safetensors",
"model.decoder.layers.22.self_attn.v_proj.lora_b": "model-00012-of-00016.safetensors",
"model.decoder.layers.23.experts.down_proj": "model-00012-of-00016.safetensors",
"model.decoder.layers.23.experts.gate_up_proj": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.experts.lora_down_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.experts.lora_down_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.experts.lora_gate_up_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.experts.lora_gate_up_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.input_layernorm.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.layer_scalar": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.mlp.down_proj.base.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.mlp.down_proj.lora_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.mlp.down_proj.lora_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.mlp.gate_proj.base.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.mlp.gate_proj.lora_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.mlp.gate_proj.lora_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.mlp.up_proj.base.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.mlp.up_proj.lora_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.mlp.up_proj.lora_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.post_feedforward_layernorm.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.post_feedforward_layernorm_1.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.post_feedforward_layernorm_2.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.pre_feedforward_layernorm.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.pre_feedforward_layernorm_2.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.router.per_expert_scale": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.router.proj.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.router.scale": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.self_attn.k_norm.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.self_attn.k_proj.base.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.self_attn.k_proj.lora_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.self_attn.k_proj.lora_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.self_attn.o_proj.base.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.self_attn.o_proj.lora_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.self_attn.o_proj.lora_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.self_attn.q_norm.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.self_attn.q_proj.base.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.self_attn.q_proj.lora_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.23.self_attn.q_proj.lora_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.experts.down_proj": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.experts.gate_up_proj": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.experts.lora_down_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.experts.lora_down_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.experts.lora_gate_up_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.experts.lora_gate_up_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.input_layernorm.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.layer_scalar": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.mlp.down_proj.base.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.mlp.down_proj.lora_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.mlp.down_proj.lora_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.mlp.gate_proj.base.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.mlp.gate_proj.lora_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.mlp.gate_proj.lora_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.mlp.up_proj.base.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.mlp.up_proj.lora_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.mlp.up_proj.lora_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.post_feedforward_layernorm.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.post_feedforward_layernorm_1.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.post_feedforward_layernorm_2.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.pre_feedforward_layernorm.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.pre_feedforward_layernorm_2.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.router.per_expert_scale": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.router.proj.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.router.scale": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.k_norm.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.k_proj.base.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.k_proj.lora_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.k_proj.lora_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.o_proj.base.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.o_proj.lora_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.o_proj.lora_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.q_norm.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.q_proj.base.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.q_proj.lora_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.q_proj.lora_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.v_proj.base.weight": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.v_proj.lora_a": "model-00013-of-00016.safetensors",
"model.decoder.layers.24.self_attn.v_proj.lora_b": "model-00013-of-00016.safetensors",
"model.decoder.layers.25.experts.down_proj": "model-00013-of-00016.safetensors",
"model.decoder.layers.25.experts.gate_up_proj": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.experts.lora_down_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.experts.lora_down_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.experts.lora_gate_up_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.experts.lora_gate_up_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.input_layernorm.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.layer_scalar": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.mlp.down_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.mlp.down_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.mlp.down_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.mlp.gate_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.mlp.gate_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.mlp.gate_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.mlp.up_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.mlp.up_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.mlp.up_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.post_feedforward_layernorm.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.post_feedforward_layernorm_1.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.post_feedforward_layernorm_2.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.pre_feedforward_layernorm.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.pre_feedforward_layernorm_2.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.router.per_expert_scale": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.router.proj.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.router.scale": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.k_norm.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.k_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.k_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.k_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.o_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.o_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.o_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.q_norm.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.q_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.q_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.q_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.v_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.v_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.25.self_attn.v_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.experts.down_proj": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.experts.gate_up_proj": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.experts.lora_down_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.experts.lora_down_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.experts.lora_gate_up_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.experts.lora_gate_up_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.input_layernorm.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.layer_scalar": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.mlp.down_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.mlp.down_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.mlp.down_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.mlp.gate_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.mlp.gate_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.mlp.gate_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.mlp.up_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.mlp.up_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.mlp.up_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.post_feedforward_layernorm.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.post_feedforward_layernorm_1.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.post_feedforward_layernorm_2.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.pre_feedforward_layernorm.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.pre_feedforward_layernorm_2.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.router.per_expert_scale": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.router.proj.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.router.scale": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.k_norm.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.k_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.k_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.k_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.o_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.o_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.o_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.q_norm.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.q_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.q_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.q_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.v_proj.base.weight": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.v_proj.lora_a": "model-00014-of-00016.safetensors",
"model.decoder.layers.26.self_attn.v_proj.lora_b": "model-00014-of-00016.safetensors",
"model.decoder.layers.27.experts.down_proj": "model-00014-of-00016.safetensors",
"model.decoder.layers.27.experts.gate_up_proj": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.experts.lora_down_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.experts.lora_down_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.experts.lora_gate_up_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.experts.lora_gate_up_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.input_layernorm.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.layer_scalar": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.mlp.down_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.mlp.down_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.mlp.down_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.mlp.gate_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.mlp.gate_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.mlp.gate_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.mlp.up_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.mlp.up_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.mlp.up_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.post_feedforward_layernorm.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.post_feedforward_layernorm_1.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.post_feedforward_layernorm_2.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.pre_feedforward_layernorm.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.pre_feedforward_layernorm_2.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.router.per_expert_scale": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.router.proj.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.router.scale": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.k_norm.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.k_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.k_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.k_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.o_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.o_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.o_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.q_norm.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.q_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.q_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.q_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.v_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.v_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.27.self_attn.v_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.experts.down_proj": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.experts.gate_up_proj": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.experts.lora_down_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.experts.lora_down_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.experts.lora_gate_up_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.experts.lora_gate_up_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.input_layernorm.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.layer_scalar": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.mlp.down_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.mlp.down_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.mlp.down_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.mlp.gate_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.mlp.gate_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.mlp.gate_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.mlp.up_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.mlp.up_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.mlp.up_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.post_attention_layernorm.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.post_feedforward_layernorm.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.post_feedforward_layernorm_1.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.post_feedforward_layernorm_2.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.pre_feedforward_layernorm.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.pre_feedforward_layernorm_2.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.router.per_expert_scale": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.router.proj.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.router.scale": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.k_norm.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.k_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.k_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.k_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.o_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.o_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.o_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.q_norm.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.q_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.q_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.q_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.v_proj.base.weight": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.v_proj.lora_a": "model-00015-of-00016.safetensors",
"model.decoder.layers.28.self_attn.v_proj.lora_b": "model-00015-of-00016.safetensors",
"model.decoder.layers.29.experts.down_proj": "model-00015-of-00016.safetensors",
"model.decoder.layers.29.experts.gate_up_proj": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.experts.lora_down_a": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.experts.lora_down_b": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.experts.lora_gate_up_a": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.experts.lora_gate_up_b": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.input_layernorm.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.layer_scalar": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.mlp.down_proj.base.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.mlp.down_proj.lora_a": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.mlp.down_proj.lora_b": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.mlp.gate_proj.base.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.mlp.gate_proj.lora_a": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.mlp.gate_proj.lora_b": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.mlp.up_proj.base.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.mlp.up_proj.lora_a": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.mlp.up_proj.lora_b": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.post_attention_layernorm.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.post_feedforward_layernorm.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.post_feedforward_layernorm_1.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.post_feedforward_layernorm_2.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.pre_feedforward_layernorm.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.pre_feedforward_layernorm_2.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.router.per_expert_scale": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.router.proj.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.router.scale": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.self_attn.k_norm.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.self_attn.k_proj.base.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.self_attn.k_proj.lora_a": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.self_attn.k_proj.lora_b": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.self_attn.o_proj.base.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.self_attn.o_proj.lora_a": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.self_attn.o_proj.lora_b": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.self_attn.q_norm.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.self_attn.q_proj.base.weight": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.self_attn.q_proj.lora_a": "model-00016-of-00016.safetensors",
"model.decoder.layers.29.self_attn.q_proj.lora_b": "model-00016-of-00016.safetensors",
"model.decoder.layers.3.experts.down_proj": "model-00002-of-00016.safetensors",
"model.decoder.layers.3.experts.gate_up_proj": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.experts.lora_down_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.experts.lora_down_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.experts.lora_gate_up_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.experts.lora_gate_up_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.input_layernorm.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.layer_scalar": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.mlp.down_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.mlp.down_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.mlp.down_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.mlp.gate_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.mlp.gate_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.mlp.gate_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.mlp.up_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.mlp.up_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.mlp.up_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.post_feedforward_layernorm.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.post_feedforward_layernorm_1.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.post_feedforward_layernorm_2.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.pre_feedforward_layernorm.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.pre_feedforward_layernorm_2.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.router.per_expert_scale": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.router.proj.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.router.scale": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.k_norm.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.k_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.k_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.k_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.o_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.o_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.o_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.q_norm.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.q_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.q_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.q_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.v_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.v_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.3.self_attn.v_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.experts.down_proj": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.experts.gate_up_proj": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.experts.lora_down_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.experts.lora_down_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.experts.lora_gate_up_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.experts.lora_gate_up_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.input_layernorm.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.layer_scalar": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.mlp.down_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.mlp.down_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.mlp.down_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.mlp.gate_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.mlp.gate_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.mlp.gate_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.mlp.up_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.mlp.up_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.mlp.up_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.post_feedforward_layernorm.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.post_feedforward_layernorm_1.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.post_feedforward_layernorm_2.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.pre_feedforward_layernorm.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.pre_feedforward_layernorm_2.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.router.per_expert_scale": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.router.proj.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.router.scale": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.k_norm.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.k_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.k_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.k_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.o_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.o_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.o_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.q_norm.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.q_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.q_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.q_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.v_proj.base.weight": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.v_proj.lora_a": "model-00003-of-00016.safetensors",
"model.decoder.layers.4.self_attn.v_proj.lora_b": "model-00003-of-00016.safetensors",
"model.decoder.layers.5.experts.down_proj": "model-00003-of-00016.safetensors",
"model.decoder.layers.5.experts.gate_up_proj": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.experts.lora_down_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.experts.lora_down_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.experts.lora_gate_up_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.experts.lora_gate_up_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.input_layernorm.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.layer_scalar": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.mlp.down_proj.base.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.mlp.down_proj.lora_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.mlp.down_proj.lora_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.mlp.gate_proj.base.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.mlp.gate_proj.lora_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.mlp.gate_proj.lora_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.mlp.up_proj.base.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.mlp.up_proj.lora_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.mlp.up_proj.lora_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.post_feedforward_layernorm.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.post_feedforward_layernorm_1.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.post_feedforward_layernorm_2.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.pre_feedforward_layernorm.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.pre_feedforward_layernorm_2.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.router.per_expert_scale": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.router.proj.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.router.scale": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.self_attn.k_norm.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.self_attn.k_proj.base.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.self_attn.k_proj.lora_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.self_attn.k_proj.lora_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.self_attn.o_proj.base.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.self_attn.o_proj.lora_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.self_attn.o_proj.lora_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.self_attn.q_norm.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.self_attn.q_proj.base.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.self_attn.q_proj.lora_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.5.self_attn.q_proj.lora_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.experts.down_proj": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.experts.gate_up_proj": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.experts.lora_down_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.experts.lora_down_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.experts.lora_gate_up_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.experts.lora_gate_up_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.input_layernorm.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.layer_scalar": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.mlp.down_proj.base.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.mlp.down_proj.lora_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.mlp.down_proj.lora_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.mlp.gate_proj.base.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.mlp.gate_proj.lora_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.mlp.gate_proj.lora_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.mlp.up_proj.base.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.mlp.up_proj.lora_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.mlp.up_proj.lora_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.post_feedforward_layernorm.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.post_feedforward_layernorm_1.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.post_feedforward_layernorm_2.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.pre_feedforward_layernorm.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.pre_feedforward_layernorm_2.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.router.per_expert_scale": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.router.proj.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.router.scale": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.k_norm.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.k_proj.base.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.k_proj.lora_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.k_proj.lora_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.o_proj.base.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.o_proj.lora_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.o_proj.lora_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.q_norm.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.q_proj.base.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.q_proj.lora_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.q_proj.lora_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.v_proj.base.weight": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.v_proj.lora_a": "model-00004-of-00016.safetensors",
"model.decoder.layers.6.self_attn.v_proj.lora_b": "model-00004-of-00016.safetensors",
"model.decoder.layers.7.experts.down_proj": "model-00004-of-00016.safetensors",
"model.decoder.layers.7.experts.gate_up_proj": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.experts.lora_down_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.experts.lora_down_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.experts.lora_gate_up_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.experts.lora_gate_up_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.input_layernorm.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.layer_scalar": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.mlp.down_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.mlp.down_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.mlp.down_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.mlp.gate_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.mlp.gate_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.mlp.gate_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.mlp.up_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.mlp.up_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.mlp.up_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.post_feedforward_layernorm.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.post_feedforward_layernorm_1.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.post_feedforward_layernorm_2.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.pre_feedforward_layernorm.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.pre_feedforward_layernorm_2.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.router.per_expert_scale": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.router.proj.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.router.scale": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.k_norm.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.k_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.k_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.k_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.o_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.o_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.o_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.q_norm.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.q_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.q_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.q_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.v_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.v_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.7.self_attn.v_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.experts.down_proj": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.experts.gate_up_proj": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.experts.lora_down_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.experts.lora_down_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.experts.lora_gate_up_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.experts.lora_gate_up_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.input_layernorm.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.layer_scalar": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.mlp.down_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.mlp.down_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.mlp.down_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.mlp.gate_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.mlp.gate_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.mlp.gate_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.mlp.up_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.mlp.up_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.mlp.up_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.post_feedforward_layernorm.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.post_feedforward_layernorm_1.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.post_feedforward_layernorm_2.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.pre_feedforward_layernorm.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.pre_feedforward_layernorm_2.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.router.per_expert_scale": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.router.proj.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.router.scale": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.k_norm.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.k_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.k_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.k_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.o_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.o_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.o_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.q_norm.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.q_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.q_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.q_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.v_proj.base.weight": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.v_proj.lora_a": "model-00005-of-00016.safetensors",
"model.decoder.layers.8.self_attn.v_proj.lora_b": "model-00005-of-00016.safetensors",
"model.decoder.layers.9.experts.down_proj": "model-00005-of-00016.safetensors",
"model.decoder.layers.9.experts.gate_up_proj": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.experts.lora_down_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.experts.lora_down_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.experts.lora_gate_up_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.experts.lora_gate_up_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.input_layernorm.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.layer_scalar": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.mlp.down_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.mlp.down_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.mlp.down_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.mlp.gate_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.mlp.gate_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.mlp.gate_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.mlp.up_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.mlp.up_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.mlp.up_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.post_feedforward_layernorm.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.post_feedforward_layernorm_1.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.post_feedforward_layernorm_2.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.pre_feedforward_layernorm.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.pre_feedforward_layernorm_2.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.router.per_expert_scale": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.router.proj.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.router.scale": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.k_norm.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.k_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.k_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.k_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.o_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.o_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.o_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.q_norm.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.q_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.q_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.q_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.v_proj.base.weight": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.v_proj.lora_a": "model-00006-of-00016.safetensors",
"model.decoder.layers.9.self_attn.v_proj.lora_b": "model-00006-of-00016.safetensors",
"model.decoder.norm.weight": "model-00016-of-00016.safetensors",
"model.decoder.self_conditioning.down_proj.weight": "model-00016-of-00016.safetensors",
"model.decoder.self_conditioning.gate_proj.weight": "model-00016-of-00016.safetensors",
"model.decoder.self_conditioning.pre_norm.weight": "model-00016-of-00016.safetensors",
"model.decoder.self_conditioning.up_proj.weight": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.0.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.1.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.10.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.11.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.12.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.13.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.14.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.15.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.16.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.17.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.18.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.19.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.2.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.20.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.21.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.22.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.23.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.24.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.25.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.26.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.27.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.28.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.29.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.3.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.4.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.5.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.6.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.7.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.8.layer_scalar": "model-00016-of-00016.safetensors",
"model.encoder.language_model.layers.9.layer_scalar": "model-00016-of-00016.safetensors"
}
}
{
"metadata": {
"total_parameters": 25895691125,
"total_size": 51791503298
},
"weight_map": {
"latent_deliberation.blocks.0.attn.k_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.attn.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.attn.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.attn.q_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.attn.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.attn.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.ff.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.ff.gate.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.ff.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.ff_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.0.norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.attn.k_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.attn.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.attn.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.attn.q_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.attn.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.attn.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.ff.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.ff.gate.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.ff.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.ff_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.1.norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.attn.k_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.attn.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.attn.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.attn.q_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.attn.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.attn.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.ff.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.ff.gate.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.ff.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.ff_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.2.norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.attn.k_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.attn.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.attn.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.attn.q_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.attn.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.attn.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.ff.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.ff.gate.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.ff.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.ff_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.blocks.3.norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.experience_in.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.output_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.persistent_memory_bus.alpha": "model-00001-of-00016.safetensors",
"latent_deliberation.reason_embed.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.a_log": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.b_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.dt_bias": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.f_proj.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.f_proj.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.g_proj.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.g_proj.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.cell.w_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.a_log": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.b_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.dt_bias": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.f_proj.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.f_proj.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.g_proj.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.g_proj.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.persistent.w_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.probe_embed.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.a_log": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.b_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.dt_bias": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.f_proj.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.f_proj.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.g_proj.down.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.g_proj.up.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.o_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.q_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.v_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.trajectory.row.w_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.address_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.alpha": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.k_proj.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.memory_norm.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.o_proj.0.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.o_proj.1.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.o_proj.2.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.o_proj.3.weight": "model-00001-of-00016.safetensors",
"latent_deliberation.working_memory_bus.o_proj.4.weight": "model-00001-of-00016.safetensors",