Text Generation
Transformers
Safetensors
English
granitemoehybrid
security
vulnerability-detection
agentic
terminal-agent
reinforcement-learning
granite
conversational
Instructions to use edwardcapriolo/antares-350m-JQ4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use edwardcapriolo/antares-350m-JQ4 with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="edwardcapriolo/antares-350m-JQ4") messages = [ {"role": "user", "content": "Who are you?"}, ] pipe(messages)# Load model directly from transformers import AutoTokenizer, AutoModelForCausalLM tokenizer = AutoTokenizer.from_pretrained("edwardcapriolo/antares-350m-JQ4") model = AutoModelForCausalLM.from_pretrained("edwardcapriolo/antares-350m-JQ4", device_map="auto") messages = [ {"role": "user", "content": "Who are you?"}, ] inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:])) - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use edwardcapriolo/antares-350m-JQ4 with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "edwardcapriolo/antares-350m-JQ4" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/chat/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "edwardcapriolo/antares-350m-JQ4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }'Use Docker
docker model run hf.co/edwardcapriolo/antares-350m-JQ4
- SGLang
How to use edwardcapriolo/antares-350m-JQ4 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 "edwardcapriolo/antares-350m-JQ4" \ --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": "edwardcapriolo/antares-350m-JQ4", "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 "edwardcapriolo/antares-350m-JQ4" \ --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": "edwardcapriolo/antares-350m-JQ4", "messages": [ { "role": "user", "content": "What is the capital of France?" } ] }' - Docker Model Runner
How to use edwardcapriolo/antares-350m-JQ4 with Docker Model Runner:
docker model run hf.co/edwardcapriolo/antares-350m-JQ4
| { | |
| "schemaVersion" : 1, | |
| "createdAt" : "2026-07-23T03:30:07.313881Z", | |
| "sourceDirectory" : "/Users/edward.capriolo/.deliverance/fdtn-ai_antares-350m", | |
| "outputDirectory" : "/Users/edward.capriolo/.deliverance/fdtn-ai_antares-350m-JQ4.tmp-db43e2fb-ca81-4762-990d-02b68ca0229e", | |
| "targetType" : "Q4", | |
| "sourceSizeBytes" : 711967865, | |
| "outputSizeBytes" : 368870074, | |
| "tensorTransforms" : [ { | |
| "name" : "model.embed_tokens.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 100352, 1024 ], | |
| "outputShape" : [ 100352, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.0.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.0.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.0.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.0.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.0.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.0.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.0.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.0.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.0.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.0.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.0.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.0.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.0.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.0.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.1.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.1.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.1.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.1.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.1.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.1.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.1.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.1.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.1.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.1.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.1.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.1.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.1.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.1.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.10.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.10.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.10.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.10.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.10.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.10.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.10.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.10.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.10.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.10.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.10.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.10.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.10.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.10.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.11.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.11.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.11.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.11.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.11.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.11.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.11.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.11.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.11.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.11.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.11.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.11.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.11.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.11.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.12.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.12.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.12.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.12.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.12.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.12.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.12.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.12.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.12.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.12.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.12.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.12.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.12.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.12.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.13.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.13.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.13.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.13.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.13.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.13.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.13.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.13.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.13.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.13.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.13.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.13.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.13.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.13.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.14.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.14.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.14.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.14.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.14.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.14.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.14.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.14.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.14.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.14.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.14.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.14.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.14.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.14.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.15.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.15.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.15.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.15.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.15.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.15.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.15.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.15.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.15.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.15.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.15.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.15.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.15.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.15.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.16.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.16.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.16.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.16.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.16.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.16.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.16.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.16.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.16.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.16.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.16.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.16.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.16.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.16.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.17.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.17.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.17.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.17.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.17.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.17.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.17.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.17.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.17.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.17.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.17.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.17.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.17.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.17.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.18.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.18.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.18.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.18.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.18.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.18.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.18.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.18.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.18.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.18.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.18.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.18.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.18.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.18.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.19.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.19.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.19.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.19.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.19.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.19.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.19.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.19.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.19.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.19.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.19.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.19.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.19.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.19.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.2.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.2.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.2.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.2.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.2.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.2.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.2.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.2.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.2.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.2.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.2.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.2.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.2.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.2.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.20.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.20.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.20.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.20.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.20.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.20.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.20.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.20.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.20.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.20.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.20.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.20.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.20.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.20.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.21.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.21.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.21.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.21.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.21.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.21.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.21.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.21.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.21.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.21.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.21.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.21.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.21.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.21.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.22.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.22.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.22.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.22.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.22.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.22.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.22.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.22.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.22.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.22.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.22.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.22.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.22.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.22.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.23.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.23.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.23.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.23.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.23.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.23.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.23.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.23.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.23.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.23.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.23.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.23.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.23.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.23.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.24.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.24.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.24.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.24.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.24.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.24.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.24.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.24.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.24.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.24.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.24.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.24.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.24.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.24.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.25.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.25.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.25.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.25.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.25.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.25.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.25.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.25.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.25.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.25.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.25.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.25.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.25.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.25.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.26.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.26.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.26.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.26.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.26.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.26.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.26.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.26.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.26.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.26.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.26.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.26.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.26.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.26.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.27.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.27.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.27.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.27.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.27.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.27.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.27.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.27.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.27.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.27.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.27.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.27.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.27.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.27.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.3.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.3.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.3.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.3.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.3.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.3.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.3.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.3.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.3.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.3.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.3.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.3.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.3.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.3.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.4.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.4.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.4.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.4.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.4.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.4.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.4.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.4.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.4.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.4.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.4.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.4.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.4.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.4.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.5.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.5.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.5.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.5.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.5.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.5.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.5.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.5.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.5.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.5.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.5.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.5.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.5.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.5.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.6.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.6.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.6.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.6.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.6.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.6.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.6.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.6.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.6.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.6.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.6.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.6.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.6.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.6.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.7.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.7.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.7.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.7.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.7.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.7.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.7.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.7.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.7.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.7.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.7.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.7.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.7.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.7.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.8.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.8.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.8.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.8.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.8.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.8.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.8.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.8.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.8.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.8.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.8.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.8.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.8.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.8.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.9.input_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.9.post_attention_layernorm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.9.self_attn.k_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.9.self_attn.k_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.9.self_attn.o_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.9.self_attn.o_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.9.self_attn.q_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 1024 ], | |
| "outputShape" : [ 1024, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.9.self_attn.q_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.9.self_attn.v_proj.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 256, 1024 ], | |
| "outputShape" : [ 256, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.9.self_attn.v_proj.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.9.shared_mlp.input_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 4096, 1024 ], | |
| "outputShape" : [ 4096, 1024 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.9.shared_mlp.input_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.layers.9.shared_mlp.output_linear.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "Q4", | |
| "sourceShape" : [ 1024, 2048 ], | |
| "outputShape" : [ 1024, 2048 ], | |
| "quantized" : true, | |
| "sidecars" : [ "model.layers.9.shared_mlp.output_linear.weight.qb" ], | |
| "oneDimensionalToRowVector" : false | |
| }, { | |
| "name" : "model.norm.weight", | |
| "sourceDType" : "BF16", | |
| "outputDType" : "BF16", | |
| "sourceShape" : [ 1, 1024 ], | |
| "outputShape" : [ 1, 1024 ], | |
| "quantized" : false, | |
| "sidecars" : [ ], | |
| "oneDimensionalToRowVector" : false | |
| } ] | |
| } |