Instructions to use apple/OpenELM-3B-Instruct with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use apple/OpenELM-3B-Instruct with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="apple/OpenELM-3B-Instruct", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("apple/OpenELM-3B-Instruct", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use apple/OpenELM-3B-Instruct with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "apple/OpenELM-3B-Instruct" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "apple/OpenELM-3B-Instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/apple/OpenELM-3B-Instruct
- SGLang
How to use apple/OpenELM-3B-Instruct 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 "apple/OpenELM-3B-Instruct" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "apple/OpenELM-3B-Instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'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 "apple/OpenELM-3B-Instruct" \ --host 0.0.0.0 \ --port 30000 # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:30000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "apple/OpenELM-3B-Instruct", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use apple/OpenELM-3B-Instruct with Docker Model Runner:
docker model run hf.co/apple/OpenELM-3B-Instruct
| { | |
| "metadata": { | |
| "total_size": 6073294848 | |
| }, | |
| "weight_map": { | |
| "transformer.layers.0.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.0.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.0.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.0.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.0.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.0.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.0.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.0.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.1.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.1.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.1.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.1.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.1.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.1.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.1.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.1.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.10.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.10.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.10.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.10.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.10.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.10.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.10.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.10.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.11.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.11.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.11.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.11.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.11.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.11.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.11.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.11.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.12.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.12.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.12.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.12.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.12.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.12.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.12.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.12.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.13.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.13.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.13.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.13.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.13.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.13.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.13.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.13.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.14.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.14.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.14.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.14.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.14.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.14.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.14.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.14.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.15.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.15.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.15.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.15.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.15.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.15.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.15.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.15.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.16.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.16.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.16.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.16.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.16.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.16.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.16.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.16.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.17.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.17.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.17.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.17.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.17.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.17.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.17.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.17.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.18.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.18.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.18.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.18.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.18.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.18.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.18.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.18.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.19.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.19.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.19.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.19.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.19.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.19.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.19.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.19.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.2.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.2.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.2.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.2.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.2.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.2.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.2.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.2.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.20.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.20.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.20.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.20.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.20.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.20.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.20.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.20.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.21.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.21.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.21.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.21.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.21.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.21.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.21.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.21.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.22.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.22.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.22.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.22.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.22.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.22.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.22.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.22.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.23.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.23.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.23.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.23.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.23.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.23.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.23.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.23.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.24.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.24.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.24.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.24.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.24.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.24.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.24.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.24.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.25.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.25.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.25.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.25.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.25.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.25.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.25.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.25.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.26.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.26.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.26.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.26.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.26.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.26.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.26.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.26.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.27.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.27.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.27.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.27.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.27.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.27.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.27.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.27.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.28.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.28.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.28.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.28.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.28.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.28.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.28.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.28.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.29.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.29.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.29.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.29.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.29.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.29.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.29.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.29.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.3.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.3.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.3.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.3.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.3.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.3.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.3.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.3.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.30.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.30.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.30.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.30.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.30.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.30.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.30.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.30.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.31.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.31.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.31.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.31.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.31.attn_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.31.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.31.ffn.proj_2.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.31.ffn_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.32.attn.k_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.32.attn.out_proj.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.32.attn.q_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.32.attn.qkv_proj.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.32.attn_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.32.ffn.proj_1.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.32.ffn.proj_2.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.32.ffn_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.33.attn.k_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.33.attn.out_proj.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.33.attn.q_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.33.attn.qkv_proj.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.33.attn_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.33.ffn.proj_1.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.33.ffn.proj_2.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.33.ffn_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.34.attn.k_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.34.attn.out_proj.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.34.attn.q_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.34.attn.qkv_proj.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.34.attn_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.34.ffn.proj_1.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.34.ffn.proj_2.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.34.ffn_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.35.attn.k_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.35.attn.out_proj.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.35.attn.q_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.35.attn.qkv_proj.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.35.attn_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.35.ffn.proj_1.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.35.ffn.proj_2.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.35.ffn_norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.layers.4.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.4.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.4.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.4.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.4.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.4.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.4.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.4.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.5.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.5.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.5.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.5.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.5.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.5.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.5.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.5.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.6.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.6.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.6.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.6.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.6.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.6.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.6.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.6.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.7.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.7.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.7.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.7.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.7.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.7.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.7.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.7.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.8.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.8.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.8.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.8.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.8.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.8.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.8.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.8.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.9.attn.k_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.9.attn.out_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.9.attn.q_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.9.attn.qkv_proj.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.9.attn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.9.ffn.proj_1.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.9.ffn.proj_2.weight": "model-00001-of-00002.safetensors", | |
| "transformer.layers.9.ffn_norm.weight": "model-00001-of-00002.safetensors", | |
| "transformer.norm.weight": "model-00002-of-00002.safetensors", | |
| "transformer.token_embeddings.weight": "model-00001-of-00002.safetensors" | |
| } | |
| } | |