Text Generation
Transformers
Safetensors
English
Chinese
glm5_next
image-text-to-text
conversational
4-bit precision
auto-round
Instructions to use Intel/GLM-5.3-Flash-W4A16-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Intel/GLM-5.3-Flash-W4A16-AutoRound with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="Intel/GLM-5.3-Flash-W4A16-AutoRound") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] pipe(text=messages)# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("Intel/GLM-5.3-Flash-W4A16-AutoRound") model = AutoModelForMultimodalLM.from_pretrained("Intel/GLM-5.3-Flash-W4A16-AutoRound", device_map="auto") messages = [ { "role": "user", "content": [ {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"}, {"type": "text", "text": "What animal is on the candy?"} ] }, ] inputs = processor.apply_chat_template( messages, add_generation_prompt=True, tokenize=True, return_dict=True, return_tensors="pt", ).to(model.device) outputs = model.generate(**inputs, max_new_tokens=40) print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use Intel/GLM-5.3-Flash-W4A16-AutoRound with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "Intel/GLM-5.3-Flash-W4A16-AutoRound" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Intel/GLM-5.3-Flash-W4A16-AutoRound", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/Intel/GLM-5.3-Flash-W4A16-AutoRound
- SGLang
How to use Intel/GLM-5.3-Flash-W4A16-AutoRound with SGLang:
Install from pip and serve model
# Install SGLang from pip: pip install sglang # Start the SGLang server: python3 -m sglang.launch_server \ --model-path "Intel/GLM-5.3-Flash-W4A16-AutoRound" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Intel/GLM-5.3-Flash-W4A16-AutoRound", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker images
docker run --gpus all \ --shm-size 32g \ -p 30000:30000 \ -v ~/.cache/huggingface:/root/.cache/huggingface \ --env "HF_TOKEN=<secret>" \ --ipc=host \ lmsysorg/sglang:latest \ python3 -m sglang.launch_server \ --model-path "Intel/GLM-5.3-Flash-W4A16-AutoRound" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "Intel/GLM-5.3-Flash-W4A16-AutoRound", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use Intel/GLM-5.3-Flash-W4A16-AutoRound with Docker Model Runner:
docker model run hf.co/Intel/GLM-5.3-Flash-W4A16-AutoRound
| { | |
| "bits": 4, | |
| "data_type": "int", | |
| "group_size": 128, | |
| "sym": true, | |
| "static_attention_granularity": "tensor", | |
| "static_kv_granularity": "tensor", | |
| "autoround_version": "0.15.0", | |
| "block_name_to_quantize": "model.language_model.layers", | |
| "quant_method": "auto-round", | |
| "packing_format": "auto_round:auto_gptq", | |
| "extra_config": { | |
| "model.visual.blocks.0.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.0.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.0.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.1.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.1.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.1.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.2.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.2.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.2.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.3.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.3.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.3.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.4.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.4.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.4.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.5.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.5.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.5.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.6.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.6.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.6.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.7.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.7.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.7.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.8.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.8.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.8.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.9.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.9.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.9.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.10.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.10.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.10.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.11.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.11.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.11.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.12.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.12.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.12.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.13.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.13.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.13.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.14.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.14.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.14.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.15.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.15.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.15.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.16.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.16.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.16.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.17.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.17.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.17.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.18.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.18.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.18.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.19.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.19.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.19.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.20.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.20.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.20.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.21.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.21.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.21.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.22.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.22.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.22.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.23.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.23.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.visual.blocks.23.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.3.self_attn.indexer.wq_b": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.3.self_attn.indexer.wk": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.3.self_attn.indexer.weights_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.7.self_attn.indexer.wq_b": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.7.self_attn.indexer.wk": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.7.self_attn.indexer.weights_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.11.self_attn.indexer.wq_b": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.11.self_attn.indexer.wk": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.11.self_attn.indexer.weights_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.15.self_attn.indexer.wq_b": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.15.self_attn.indexer.wk": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.15.self_attn.indexer.weights_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.19.self_attn.indexer.wq_b": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.19.self_attn.indexer.wk": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.19.self_attn.indexer.weights_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.23.self_attn.indexer.wq_b": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.23.self_attn.indexer.wk": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.23.self_attn.indexer.weights_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.27.self_attn.indexer.wq_b": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.27.self_attn.indexer.wk": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.27.self_attn.indexer.weights_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.31.self_attn.indexer.wq_b": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.31.self_attn.indexer.wk": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.31.self_attn.indexer.weights_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.35.self_attn.indexer.wq_b": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.35.self_attn.indexer.wk": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.35.self_attn.indexer.weights_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.39.self_attn.indexer.wq_b": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.39.self_attn.indexer.wk": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.39.self_attn.indexer.weights_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.43.self_attn.indexer.wq_b": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.43.self_attn.indexer.wk": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.43.self_attn.indexer.weights_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.0.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.0.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.0.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.0.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.0.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.0.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.0.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.0.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.0.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.1.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.1.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.1.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.1.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.1.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.1.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.1.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.1.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.1.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.2.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.2.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.2.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.2.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.2.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.2.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.2.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.2.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.2.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.3.self_attn.q_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.3.self_attn.q_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.3.self_attn.kv_a_proj_with_mqa": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.3.self_attn.kv_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.3.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.4.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.4.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.4.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.4.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.4.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.4.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.4.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.4.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.4.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.5.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.5.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.5.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.5.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.5.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.5.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.5.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.5.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.5.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.6.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.6.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.6.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.6.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.6.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.6.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.6.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.6.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.6.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.7.self_attn.q_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.7.self_attn.q_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.7.self_attn.kv_a_proj_with_mqa": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.7.self_attn.kv_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.7.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.8.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.8.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.8.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.8.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.8.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.8.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.8.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.8.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.8.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.9.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.9.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.9.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.9.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.9.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.9.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.9.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.9.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.9.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.10.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.10.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.10.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.10.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.10.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.10.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.10.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.10.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.10.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.11.self_attn.q_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.11.self_attn.q_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.11.self_attn.kv_a_proj_with_mqa": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.11.self_attn.kv_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.11.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.12.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.12.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.12.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.12.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.12.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.12.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.12.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.12.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.12.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.13.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.13.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.13.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.13.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.13.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.13.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.13.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.13.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.13.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.14.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.14.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.14.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.14.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.14.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.14.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.14.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.14.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.14.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.15.self_attn.q_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.15.self_attn.q_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.15.self_attn.kv_a_proj_with_mqa": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.15.self_attn.kv_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.15.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.16.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.16.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.16.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.16.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.16.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.16.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.16.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.16.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.16.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.17.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.17.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.17.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.17.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.17.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.17.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.17.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.17.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.17.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.18.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.18.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.18.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.18.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.18.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.18.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.18.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.18.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.18.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.19.self_attn.q_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.19.self_attn.q_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.19.self_attn.kv_a_proj_with_mqa": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.19.self_attn.kv_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.19.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.20.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.20.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.20.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.20.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.20.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.20.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.20.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.20.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.20.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.21.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.21.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.21.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.21.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.21.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.21.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.21.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.21.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.21.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.22.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.22.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.22.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.22.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.22.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.22.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.22.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.22.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.22.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.23.self_attn.q_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.23.self_attn.q_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.23.self_attn.kv_a_proj_with_mqa": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.23.self_attn.kv_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.23.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.24.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.24.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.24.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.24.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.24.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.24.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.24.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.24.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.24.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.25.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.25.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.25.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.25.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.25.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.25.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.25.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.25.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.25.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.26.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.26.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.26.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.26.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.26.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.26.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.26.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.26.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.26.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.27.self_attn.q_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.27.self_attn.q_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.27.self_attn.kv_a_proj_with_mqa": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.27.self_attn.kv_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.27.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.28.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.28.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.28.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.28.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.28.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.28.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.28.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.28.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.28.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.29.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.29.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.29.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.29.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.29.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.29.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.29.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.29.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.29.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.30.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.30.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.30.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.30.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.30.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.30.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.30.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.30.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.30.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.31.self_attn.q_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.31.self_attn.q_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.31.self_attn.kv_a_proj_with_mqa": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.31.self_attn.kv_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.31.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.32.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.32.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.32.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.32.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.32.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.32.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.32.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.32.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.32.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.33.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.33.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.33.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.33.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.33.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.33.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.33.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.33.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.33.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.34.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.34.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.34.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.34.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.34.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.34.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.34.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.34.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.34.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.35.self_attn.q_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.35.self_attn.q_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.35.self_attn.kv_a_proj_with_mqa": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.35.self_attn.kv_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.35.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.36.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.36.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.36.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.36.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.36.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.36.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.36.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.36.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.36.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.37.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.37.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.37.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.37.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.37.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.37.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.37.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.37.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.37.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.38.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.38.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.38.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.38.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.38.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.38.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.38.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.38.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.38.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.39.self_attn.q_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.39.self_attn.q_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.39.self_attn.kv_a_proj_with_mqa": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.39.self_attn.kv_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.39.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.40.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.40.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.40.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.40.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.40.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.40.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.40.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.40.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.40.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.41.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.41.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.41.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.41.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.41.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.41.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.41.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.41.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.41.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.42.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.42.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.42.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.42.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.42.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.42.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.42.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.42.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.42.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.43.self_attn.q_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.43.self_attn.q_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.43.self_attn.kv_a_proj_with_mqa": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.43.self_attn.kv_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.43.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.44.self_attn.q_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.44.self_attn.k_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.44.self_attn.v_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.44.self_attn.forget_gate.f_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.44.self_attn.forget_gate.f_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.44.self_attn.b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.44.self_attn.g_a_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.44.self_attn.g_b_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.44.self_attn.o_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.0.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.1.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.2.mlp.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.3.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.3.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.3.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.4.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.4.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.4.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.5.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.5.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.5.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.6.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.6.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.6.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.7.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.7.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.7.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.8.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.8.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.8.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.9.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.9.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.9.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.10.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.10.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.10.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.11.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.11.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.11.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.12.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.12.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.12.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.13.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.13.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.13.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.14.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.14.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.14.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.15.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.15.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.15.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.16.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.16.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.16.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.17.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.17.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.17.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.18.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.18.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.18.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.19.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.19.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.19.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.20.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.20.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.20.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.21.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.21.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.21.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.22.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.22.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.22.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.23.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.23.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.23.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.24.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.24.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.24.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.25.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.25.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.25.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.26.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.26.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.26.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.27.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.27.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.27.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.28.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.28.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.28.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.29.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.29.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.29.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.30.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.30.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.30.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.31.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.31.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.31.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.32.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.32.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.32.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.33.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.33.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.33.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.34.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.34.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.34.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.35.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.35.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.35.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.36.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.36.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.36.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.37.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.37.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.37.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.38.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.38.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.38.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.39.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.39.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.39.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.40.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.40.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.40.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.41.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.41.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.41.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.42.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.42.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.42.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.43.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.43.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.43.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.44.mlp.shared_experts.gate_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.44.mlp.shared_experts.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.44.mlp.shared_experts.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.0.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.1.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.2.mlp.up_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.0.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.1.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| "model.language_model.layers.2.mlp.down_proj": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*embed_tokens.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*visual.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*hc_.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*indexer.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*self_attn.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*shared_experts.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*eh_proj.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*enorm.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*hnorm.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*shared_head.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*norm.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*A_log.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*dt_bias.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*b_proj.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*f_a_proj.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*f_b_proj.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*g_a_proj.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*g_b_proj.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*conv1d.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*mlp\\.gate_proj.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*mlp\\.up_proj.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*mlp\\.down_proj.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.3\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.4\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.5\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.6\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.7\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.8\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.9\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.10\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.11\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.12\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.13\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.14\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.15\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.16\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.17\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.18\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.19\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.20\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.21\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.22\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.23\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.24\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.25\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.26\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.27\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.28\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.29\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.30\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.31\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.32\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.33\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.34\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.35\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.36\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.37\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.38\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.39\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.40\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.41\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.42\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.43\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| }, | |
| ".*model\\.language_model\\.layers\\.44\\.mlp\\.gate.*": { | |
| "bits": 16, | |
| "data_type": "float" | |
| } | |
| } | |
| } |