Instructions to use xlr8harder/talkie-1930-13b-base-tf with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use xlr8harder/talkie-1930-13b-base-tf with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-generation", model="xlr8harder/talkie-1930-13b-base-tf", trust_remote_code=True)# Load model directly from transformers import AutoModelForCausalLM model = AutoModelForCausalLM.from_pretrained("xlr8harder/talkie-1930-13b-base-tf", trust_remote_code=True, dtype="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- vLLM
How to use xlr8harder/talkie-1930-13b-base-tf with vLLM:
Install from pip and serve model
# Install vLLM from pip: pip install vllm # Start the vLLM server: vllm serve "xlr8harder/talkie-1930-13b-base-tf" # Call the server using curl (OpenAI-compatible API): curl -X POST "http://localhost:8000/v1/completions" \ -H "Content-Type: application/json" \ --data '{ "model": "xlr8harder/talkie-1930-13b-base-tf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }'Use Docker
docker model run hf.co/xlr8harder/talkie-1930-13b-base-tf
- SGLang
How to use xlr8harder/talkie-1930-13b-base-tf 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 "xlr8harder/talkie-1930-13b-base-tf" \ --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": "xlr8harder/talkie-1930-13b-base-tf", "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 "xlr8harder/talkie-1930-13b-base-tf" \ --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": "xlr8harder/talkie-1930-13b-base-tf", "prompt": "Once upon a time,", "max_tokens": 512, "temperature": 0.5 }' - Docker Model Runner
How to use xlr8harder/talkie-1930-13b-base-tf with Docker Model Runner:
docker model run hf.co/xlr8harder/talkie-1930-13b-base-tf
| { | |
| "metadata": { | |
| "total_size": 26560433520 | |
| }, | |
| "weight_map": { | |
| "blocks.0.attn.attn_key.weight": "model-00001-of-00006.safetensors", | |
| "blocks.0.attn.attn_query.weight": "model-00001-of-00006.safetensors", | |
| "blocks.0.attn.attn_resid.weight": "model-00001-of-00006.safetensors", | |
| "blocks.0.attn.attn_value.weight": "model-00001-of-00006.safetensors", | |
| "blocks.0.attn.head_gain.head_g": "model-00001-of-00006.safetensors", | |
| "blocks.0.attn_gain.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.0.embed_skip.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.0.mlp.mlp_gate.weight": "model-00001-of-00006.safetensors", | |
| "blocks.0.mlp.mlp_linear.weight": "model-00001-of-00006.safetensors", | |
| "blocks.0.mlp.mlp_resid.weight": "model-00001-of-00006.safetensors", | |
| "blocks.0.mlp_gain.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.1.attn.attn_key.weight": "model-00001-of-00006.safetensors", | |
| "blocks.1.attn.attn_query.weight": "model-00001-of-00006.safetensors", | |
| "blocks.1.attn.attn_resid.weight": "model-00001-of-00006.safetensors", | |
| "blocks.1.attn.attn_value.weight": "model-00001-of-00006.safetensors", | |
| "blocks.1.attn.head_gain.head_g": "model-00001-of-00006.safetensors", | |
| "blocks.1.attn_gain.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.1.embed_skip.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.1.mlp.mlp_gate.weight": "model-00001-of-00006.safetensors", | |
| "blocks.1.mlp.mlp_linear.weight": "model-00001-of-00006.safetensors", | |
| "blocks.1.mlp.mlp_resid.weight": "model-00001-of-00006.safetensors", | |
| "blocks.1.mlp_gain.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.10.attn.attn_key.weight": "model-00002-of-00006.safetensors", | |
| "blocks.10.attn.attn_query.weight": "model-00002-of-00006.safetensors", | |
| "blocks.10.attn.attn_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.10.attn.attn_value.weight": "model-00002-of-00006.safetensors", | |
| "blocks.10.attn.head_gain.head_g": "model-00002-of-00006.safetensors", | |
| "blocks.10.attn_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.10.embed_skip.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.10.mlp.mlp_gate.weight": "model-00002-of-00006.safetensors", | |
| "blocks.10.mlp.mlp_linear.weight": "model-00002-of-00006.safetensors", | |
| "blocks.10.mlp.mlp_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.10.mlp_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.11.attn.attn_key.weight": "model-00002-of-00006.safetensors", | |
| "blocks.11.attn.attn_query.weight": "model-00002-of-00006.safetensors", | |
| "blocks.11.attn.attn_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.11.attn.attn_value.weight": "model-00002-of-00006.safetensors", | |
| "blocks.11.attn.head_gain.head_g": "model-00002-of-00006.safetensors", | |
| "blocks.11.attn_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.11.embed_skip.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.11.mlp.mlp_gate.weight": "model-00002-of-00006.safetensors", | |
| "blocks.11.mlp.mlp_linear.weight": "model-00002-of-00006.safetensors", | |
| "blocks.11.mlp.mlp_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.11.mlp_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.12.attn.attn_key.weight": "model-00002-of-00006.safetensors", | |
| "blocks.12.attn.attn_query.weight": "model-00002-of-00006.safetensors", | |
| "blocks.12.attn.attn_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.12.attn.attn_value.weight": "model-00002-of-00006.safetensors", | |
| "blocks.12.attn.head_gain.head_g": "model-00002-of-00006.safetensors", | |
| "blocks.12.attn_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.12.embed_skip.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.12.mlp.mlp_gate.weight": "model-00002-of-00006.safetensors", | |
| "blocks.12.mlp.mlp_linear.weight": "model-00002-of-00006.safetensors", | |
| "blocks.12.mlp.mlp_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.12.mlp_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.13.attn.attn_key.weight": "model-00002-of-00006.safetensors", | |
| "blocks.13.attn.attn_query.weight": "model-00002-of-00006.safetensors", | |
| "blocks.13.attn.attn_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.13.attn.attn_value.weight": "model-00002-of-00006.safetensors", | |
| "blocks.13.attn.head_gain.head_g": "model-00002-of-00006.safetensors", | |
| "blocks.13.attn_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.13.embed_skip.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.13.mlp.mlp_gate.weight": "model-00002-of-00006.safetensors", | |
| "blocks.13.mlp.mlp_linear.weight": "model-00003-of-00006.safetensors", | |
| "blocks.13.mlp.mlp_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.13.mlp_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.14.attn.attn_key.weight": "model-00003-of-00006.safetensors", | |
| "blocks.14.attn.attn_query.weight": "model-00003-of-00006.safetensors", | |
| "blocks.14.attn.attn_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.14.attn.attn_value.weight": "model-00003-of-00006.safetensors", | |
| "blocks.14.attn.head_gain.head_g": "model-00003-of-00006.safetensors", | |
| "blocks.14.attn_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.14.embed_skip.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.14.mlp.mlp_gate.weight": "model-00003-of-00006.safetensors", | |
| "blocks.14.mlp.mlp_linear.weight": "model-00003-of-00006.safetensors", | |
| "blocks.14.mlp.mlp_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.14.mlp_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.15.attn.attn_key.weight": "model-00003-of-00006.safetensors", | |
| "blocks.15.attn.attn_query.weight": "model-00003-of-00006.safetensors", | |
| "blocks.15.attn.attn_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.15.attn.attn_value.weight": "model-00003-of-00006.safetensors", | |
| "blocks.15.attn.head_gain.head_g": "model-00003-of-00006.safetensors", | |
| "blocks.15.attn_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.15.embed_skip.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.15.mlp.mlp_gate.weight": "model-00003-of-00006.safetensors", | |
| "blocks.15.mlp.mlp_linear.weight": "model-00003-of-00006.safetensors", | |
| "blocks.15.mlp.mlp_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.15.mlp_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.16.attn.attn_key.weight": "model-00003-of-00006.safetensors", | |
| "blocks.16.attn.attn_query.weight": "model-00003-of-00006.safetensors", | |
| "blocks.16.attn.attn_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.16.attn.attn_value.weight": "model-00003-of-00006.safetensors", | |
| "blocks.16.attn.head_gain.head_g": "model-00003-of-00006.safetensors", | |
| "blocks.16.attn_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.16.embed_skip.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.16.mlp.mlp_gate.weight": "model-00003-of-00006.safetensors", | |
| "blocks.16.mlp.mlp_linear.weight": "model-00003-of-00006.safetensors", | |
| "blocks.16.mlp.mlp_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.16.mlp_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.17.attn.attn_key.weight": "model-00003-of-00006.safetensors", | |
| "blocks.17.attn.attn_query.weight": "model-00003-of-00006.safetensors", | |
| "blocks.17.attn.attn_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.17.attn.attn_value.weight": "model-00003-of-00006.safetensors", | |
| "blocks.17.attn.head_gain.head_g": "model-00003-of-00006.safetensors", | |
| "blocks.17.attn_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.17.embed_skip.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.17.mlp.mlp_gate.weight": "model-00003-of-00006.safetensors", | |
| "blocks.17.mlp.mlp_linear.weight": "model-00003-of-00006.safetensors", | |
| "blocks.17.mlp.mlp_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.17.mlp_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.18.attn.attn_key.weight": "model-00003-of-00006.safetensors", | |
| "blocks.18.attn.attn_query.weight": "model-00003-of-00006.safetensors", | |
| "blocks.18.attn.attn_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.18.attn.attn_value.weight": "model-00003-of-00006.safetensors", | |
| "blocks.18.attn.head_gain.head_g": "model-00003-of-00006.safetensors", | |
| "blocks.18.attn_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.18.embed_skip.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.18.mlp.mlp_gate.weight": "model-00003-of-00006.safetensors", | |
| "blocks.18.mlp.mlp_linear.weight": "model-00003-of-00006.safetensors", | |
| "blocks.18.mlp.mlp_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.18.mlp_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.19.attn.attn_key.weight": "model-00003-of-00006.safetensors", | |
| "blocks.19.attn.attn_query.weight": "model-00003-of-00006.safetensors", | |
| "blocks.19.attn.attn_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.19.attn.attn_value.weight": "model-00003-of-00006.safetensors", | |
| "blocks.19.attn.head_gain.head_g": "model-00003-of-00006.safetensors", | |
| "blocks.19.attn_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.19.embed_skip.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.19.mlp.mlp_gate.weight": "model-00003-of-00006.safetensors", | |
| "blocks.19.mlp.mlp_linear.weight": "model-00003-of-00006.safetensors", | |
| "blocks.19.mlp.mlp_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.19.mlp_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.2.attn.attn_key.weight": "model-00001-of-00006.safetensors", | |
| "blocks.2.attn.attn_query.weight": "model-00001-of-00006.safetensors", | |
| "blocks.2.attn.attn_resid.weight": "model-00001-of-00006.safetensors", | |
| "blocks.2.attn.attn_value.weight": "model-00001-of-00006.safetensors", | |
| "blocks.2.attn.head_gain.head_g": "model-00001-of-00006.safetensors", | |
| "blocks.2.attn_gain.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.2.embed_skip.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.2.mlp.mlp_gate.weight": "model-00001-of-00006.safetensors", | |
| "blocks.2.mlp.mlp_linear.weight": "model-00001-of-00006.safetensors", | |
| "blocks.2.mlp.mlp_resid.weight": "model-00001-of-00006.safetensors", | |
| "blocks.2.mlp_gain.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.20.attn.attn_key.weight": "model-00003-of-00006.safetensors", | |
| "blocks.20.attn.attn_query.weight": "model-00003-of-00006.safetensors", | |
| "blocks.20.attn.attn_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.20.attn.attn_value.weight": "model-00003-of-00006.safetensors", | |
| "blocks.20.attn.head_gain.head_g": "model-00003-of-00006.safetensors", | |
| "blocks.20.attn_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.20.embed_skip.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.20.mlp.mlp_gate.weight": "model-00003-of-00006.safetensors", | |
| "blocks.20.mlp.mlp_linear.weight": "model-00003-of-00006.safetensors", | |
| "blocks.20.mlp.mlp_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.20.mlp_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.21.attn.attn_key.weight": "model-00003-of-00006.safetensors", | |
| "blocks.21.attn.attn_query.weight": "model-00003-of-00006.safetensors", | |
| "blocks.21.attn.attn_resid.weight": "model-00003-of-00006.safetensors", | |
| "blocks.21.attn.attn_value.weight": "model-00003-of-00006.safetensors", | |
| "blocks.21.attn.head_gain.head_g": "model-00003-of-00006.safetensors", | |
| "blocks.21.attn_gain.a_g": "model-00003-of-00006.safetensors", | |
| "blocks.21.embed_skip.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.21.mlp.mlp_gate.weight": "model-00004-of-00006.safetensors", | |
| "blocks.21.mlp.mlp_linear.weight": "model-00004-of-00006.safetensors", | |
| "blocks.21.mlp.mlp_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.21.mlp_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.22.attn.attn_key.weight": "model-00004-of-00006.safetensors", | |
| "blocks.22.attn.attn_query.weight": "model-00004-of-00006.safetensors", | |
| "blocks.22.attn.attn_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.22.attn.attn_value.weight": "model-00004-of-00006.safetensors", | |
| "blocks.22.attn.head_gain.head_g": "model-00004-of-00006.safetensors", | |
| "blocks.22.attn_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.22.embed_skip.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.22.mlp.mlp_gate.weight": "model-00004-of-00006.safetensors", | |
| "blocks.22.mlp.mlp_linear.weight": "model-00004-of-00006.safetensors", | |
| "blocks.22.mlp.mlp_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.22.mlp_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.23.attn.attn_key.weight": "model-00004-of-00006.safetensors", | |
| "blocks.23.attn.attn_query.weight": "model-00004-of-00006.safetensors", | |
| "blocks.23.attn.attn_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.23.attn.attn_value.weight": "model-00004-of-00006.safetensors", | |
| "blocks.23.attn.head_gain.head_g": "model-00004-of-00006.safetensors", | |
| "blocks.23.attn_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.23.embed_skip.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.23.mlp.mlp_gate.weight": "model-00004-of-00006.safetensors", | |
| "blocks.23.mlp.mlp_linear.weight": "model-00004-of-00006.safetensors", | |
| "blocks.23.mlp.mlp_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.23.mlp_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.24.attn.attn_key.weight": "model-00004-of-00006.safetensors", | |
| "blocks.24.attn.attn_query.weight": "model-00004-of-00006.safetensors", | |
| "blocks.24.attn.attn_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.24.attn.attn_value.weight": "model-00004-of-00006.safetensors", | |
| "blocks.24.attn.head_gain.head_g": "model-00004-of-00006.safetensors", | |
| "blocks.24.attn_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.24.embed_skip.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.24.mlp.mlp_gate.weight": "model-00004-of-00006.safetensors", | |
| "blocks.24.mlp.mlp_linear.weight": "model-00004-of-00006.safetensors", | |
| "blocks.24.mlp.mlp_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.24.mlp_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.25.attn.attn_key.weight": "model-00004-of-00006.safetensors", | |
| "blocks.25.attn.attn_query.weight": "model-00004-of-00006.safetensors", | |
| "blocks.25.attn.attn_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.25.attn.attn_value.weight": "model-00004-of-00006.safetensors", | |
| "blocks.25.attn.head_gain.head_g": "model-00004-of-00006.safetensors", | |
| "blocks.25.attn_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.25.embed_skip.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.25.mlp.mlp_gate.weight": "model-00004-of-00006.safetensors", | |
| "blocks.25.mlp.mlp_linear.weight": "model-00004-of-00006.safetensors", | |
| "blocks.25.mlp.mlp_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.25.mlp_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.26.attn.attn_key.weight": "model-00004-of-00006.safetensors", | |
| "blocks.26.attn.attn_query.weight": "model-00004-of-00006.safetensors", | |
| "blocks.26.attn.attn_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.26.attn.attn_value.weight": "model-00004-of-00006.safetensors", | |
| "blocks.26.attn.head_gain.head_g": "model-00004-of-00006.safetensors", | |
| "blocks.26.attn_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.26.embed_skip.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.26.mlp.mlp_gate.weight": "model-00004-of-00006.safetensors", | |
| "blocks.26.mlp.mlp_linear.weight": "model-00004-of-00006.safetensors", | |
| "blocks.26.mlp.mlp_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.26.mlp_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.27.attn.attn_key.weight": "model-00004-of-00006.safetensors", | |
| "blocks.27.attn.attn_query.weight": "model-00004-of-00006.safetensors", | |
| "blocks.27.attn.attn_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.27.attn.attn_value.weight": "model-00004-of-00006.safetensors", | |
| "blocks.27.attn.head_gain.head_g": "model-00004-of-00006.safetensors", | |
| "blocks.27.attn_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.27.embed_skip.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.27.mlp.mlp_gate.weight": "model-00004-of-00006.safetensors", | |
| "blocks.27.mlp.mlp_linear.weight": "model-00004-of-00006.safetensors", | |
| "blocks.27.mlp.mlp_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.27.mlp_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.28.attn.attn_key.weight": "model-00004-of-00006.safetensors", | |
| "blocks.28.attn.attn_query.weight": "model-00004-of-00006.safetensors", | |
| "blocks.28.attn.attn_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.28.attn.attn_value.weight": "model-00004-of-00006.safetensors", | |
| "blocks.28.attn.head_gain.head_g": "model-00004-of-00006.safetensors", | |
| "blocks.28.attn_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.28.embed_skip.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.28.mlp.mlp_gate.weight": "model-00004-of-00006.safetensors", | |
| "blocks.28.mlp.mlp_linear.weight": "model-00004-of-00006.safetensors", | |
| "blocks.28.mlp.mlp_resid.weight": "model-00004-of-00006.safetensors", | |
| "blocks.28.mlp_gain.a_g": "model-00004-of-00006.safetensors", | |
| "blocks.29.attn.attn_key.weight": "model-00004-of-00006.safetensors", | |
| "blocks.29.attn.attn_query.weight": "model-00004-of-00006.safetensors", | |
| "blocks.29.attn.attn_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.29.attn.attn_value.weight": "model-00004-of-00006.safetensors", | |
| "blocks.29.attn.head_gain.head_g": "model-00005-of-00006.safetensors", | |
| "blocks.29.attn_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.29.embed_skip.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.29.mlp.mlp_gate.weight": "model-00005-of-00006.safetensors", | |
| "blocks.29.mlp.mlp_linear.weight": "model-00005-of-00006.safetensors", | |
| "blocks.29.mlp.mlp_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.29.mlp_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.3.attn.attn_key.weight": "model-00001-of-00006.safetensors", | |
| "blocks.3.attn.attn_query.weight": "model-00001-of-00006.safetensors", | |
| "blocks.3.attn.attn_resid.weight": "model-00001-of-00006.safetensors", | |
| "blocks.3.attn.attn_value.weight": "model-00001-of-00006.safetensors", | |
| "blocks.3.attn.head_gain.head_g": "model-00001-of-00006.safetensors", | |
| "blocks.3.attn_gain.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.3.embed_skip.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.3.mlp.mlp_gate.weight": "model-00001-of-00006.safetensors", | |
| "blocks.3.mlp.mlp_linear.weight": "model-00001-of-00006.safetensors", | |
| "blocks.3.mlp.mlp_resid.weight": "model-00001-of-00006.safetensors", | |
| "blocks.3.mlp_gain.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.30.attn.attn_key.weight": "model-00005-of-00006.safetensors", | |
| "blocks.30.attn.attn_query.weight": "model-00005-of-00006.safetensors", | |
| "blocks.30.attn.attn_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.30.attn.attn_value.weight": "model-00005-of-00006.safetensors", | |
| "blocks.30.attn.head_gain.head_g": "model-00005-of-00006.safetensors", | |
| "blocks.30.attn_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.30.embed_skip.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.30.mlp.mlp_gate.weight": "model-00005-of-00006.safetensors", | |
| "blocks.30.mlp.mlp_linear.weight": "model-00005-of-00006.safetensors", | |
| "blocks.30.mlp.mlp_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.30.mlp_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.31.attn.attn_key.weight": "model-00005-of-00006.safetensors", | |
| "blocks.31.attn.attn_query.weight": "model-00005-of-00006.safetensors", | |
| "blocks.31.attn.attn_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.31.attn.attn_value.weight": "model-00005-of-00006.safetensors", | |
| "blocks.31.attn.head_gain.head_g": "model-00005-of-00006.safetensors", | |
| "blocks.31.attn_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.31.embed_skip.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.31.mlp.mlp_gate.weight": "model-00005-of-00006.safetensors", | |
| "blocks.31.mlp.mlp_linear.weight": "model-00005-of-00006.safetensors", | |
| "blocks.31.mlp.mlp_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.31.mlp_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.32.attn.attn_key.weight": "model-00005-of-00006.safetensors", | |
| "blocks.32.attn.attn_query.weight": "model-00005-of-00006.safetensors", | |
| "blocks.32.attn.attn_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.32.attn.attn_value.weight": "model-00005-of-00006.safetensors", | |
| "blocks.32.attn.head_gain.head_g": "model-00005-of-00006.safetensors", | |
| "blocks.32.attn_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.32.embed_skip.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.32.mlp.mlp_gate.weight": "model-00005-of-00006.safetensors", | |
| "blocks.32.mlp.mlp_linear.weight": "model-00005-of-00006.safetensors", | |
| "blocks.32.mlp.mlp_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.32.mlp_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.33.attn.attn_key.weight": "model-00005-of-00006.safetensors", | |
| "blocks.33.attn.attn_query.weight": "model-00005-of-00006.safetensors", | |
| "blocks.33.attn.attn_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.33.attn.attn_value.weight": "model-00005-of-00006.safetensors", | |
| "blocks.33.attn.head_gain.head_g": "model-00005-of-00006.safetensors", | |
| "blocks.33.attn_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.33.embed_skip.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.33.mlp.mlp_gate.weight": "model-00005-of-00006.safetensors", | |
| "blocks.33.mlp.mlp_linear.weight": "model-00005-of-00006.safetensors", | |
| "blocks.33.mlp.mlp_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.33.mlp_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.34.attn.attn_key.weight": "model-00005-of-00006.safetensors", | |
| "blocks.34.attn.attn_query.weight": "model-00005-of-00006.safetensors", | |
| "blocks.34.attn.attn_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.34.attn.attn_value.weight": "model-00005-of-00006.safetensors", | |
| "blocks.34.attn.head_gain.head_g": "model-00005-of-00006.safetensors", | |
| "blocks.34.attn_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.34.embed_skip.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.34.mlp.mlp_gate.weight": "model-00005-of-00006.safetensors", | |
| "blocks.34.mlp.mlp_linear.weight": "model-00005-of-00006.safetensors", | |
| "blocks.34.mlp.mlp_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.34.mlp_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.35.attn.attn_key.weight": "model-00005-of-00006.safetensors", | |
| "blocks.35.attn.attn_query.weight": "model-00005-of-00006.safetensors", | |
| "blocks.35.attn.attn_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.35.attn.attn_value.weight": "model-00005-of-00006.safetensors", | |
| "blocks.35.attn.head_gain.head_g": "model-00005-of-00006.safetensors", | |
| "blocks.35.attn_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.35.embed_skip.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.35.mlp.mlp_gate.weight": "model-00005-of-00006.safetensors", | |
| "blocks.35.mlp.mlp_linear.weight": "model-00005-of-00006.safetensors", | |
| "blocks.35.mlp.mlp_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.35.mlp_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.36.attn.attn_key.weight": "model-00005-of-00006.safetensors", | |
| "blocks.36.attn.attn_query.weight": "model-00005-of-00006.safetensors", | |
| "blocks.36.attn.attn_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.36.attn.attn_value.weight": "model-00005-of-00006.safetensors", | |
| "blocks.36.attn.head_gain.head_g": "model-00005-of-00006.safetensors", | |
| "blocks.36.attn_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.36.embed_skip.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.36.mlp.mlp_gate.weight": "model-00005-of-00006.safetensors", | |
| "blocks.36.mlp.mlp_linear.weight": "model-00005-of-00006.safetensors", | |
| "blocks.36.mlp.mlp_resid.weight": "model-00005-of-00006.safetensors", | |
| "blocks.36.mlp_gain.a_g": "model-00005-of-00006.safetensors", | |
| "blocks.37.attn.attn_key.weight": "model-00005-of-00006.safetensors", | |
| "blocks.37.attn.attn_query.weight": "model-00005-of-00006.safetensors", | |
| "blocks.37.attn.attn_resid.weight": "model-00006-of-00006.safetensors", | |
| "blocks.37.attn.attn_value.weight": "model-00006-of-00006.safetensors", | |
| "blocks.37.attn.head_gain.head_g": "model-00006-of-00006.safetensors", | |
| "blocks.37.attn_gain.a_g": "model-00006-of-00006.safetensors", | |
| "blocks.37.embed_skip.a_g": "model-00006-of-00006.safetensors", | |
| "blocks.37.mlp.mlp_gate.weight": "model-00006-of-00006.safetensors", | |
| "blocks.37.mlp.mlp_linear.weight": "model-00006-of-00006.safetensors", | |
| "blocks.37.mlp.mlp_resid.weight": "model-00006-of-00006.safetensors", | |
| "blocks.37.mlp_gain.a_g": "model-00006-of-00006.safetensors", | |
| "blocks.38.attn.attn_key.weight": "model-00006-of-00006.safetensors", | |
| "blocks.38.attn.attn_query.weight": "model-00006-of-00006.safetensors", | |
| "blocks.38.attn.attn_resid.weight": "model-00006-of-00006.safetensors", | |
| "blocks.38.attn.attn_value.weight": "model-00006-of-00006.safetensors", | |
| "blocks.38.attn.head_gain.head_g": "model-00006-of-00006.safetensors", | |
| "blocks.38.attn_gain.a_g": "model-00006-of-00006.safetensors", | |
| "blocks.38.embed_skip.a_g": "model-00006-of-00006.safetensors", | |
| "blocks.38.mlp.mlp_gate.weight": "model-00006-of-00006.safetensors", | |
| "blocks.38.mlp.mlp_linear.weight": "model-00006-of-00006.safetensors", | |
| "blocks.38.mlp.mlp_resid.weight": "model-00006-of-00006.safetensors", | |
| "blocks.38.mlp_gain.a_g": "model-00006-of-00006.safetensors", | |
| "blocks.39.attn.attn_key.weight": "model-00006-of-00006.safetensors", | |
| "blocks.39.attn.attn_query.weight": "model-00006-of-00006.safetensors", | |
| "blocks.39.attn.attn_resid.weight": "model-00006-of-00006.safetensors", | |
| "blocks.39.attn.attn_value.weight": "model-00006-of-00006.safetensors", | |
| "blocks.39.attn.head_gain.head_g": "model-00006-of-00006.safetensors", | |
| "blocks.39.attn_gain.a_g": "model-00006-of-00006.safetensors", | |
| "blocks.39.embed_skip.a_g": "model-00006-of-00006.safetensors", | |
| "blocks.39.mlp.mlp_gate.weight": "model-00006-of-00006.safetensors", | |
| "blocks.39.mlp.mlp_linear.weight": "model-00006-of-00006.safetensors", | |
| "blocks.39.mlp.mlp_resid.weight": "model-00006-of-00006.safetensors", | |
| "blocks.39.mlp_gain.a_g": "model-00006-of-00006.safetensors", | |
| "blocks.4.attn.attn_key.weight": "model-00001-of-00006.safetensors", | |
| "blocks.4.attn.attn_query.weight": "model-00001-of-00006.safetensors", | |
| "blocks.4.attn.attn_resid.weight": "model-00001-of-00006.safetensors", | |
| "blocks.4.attn.attn_value.weight": "model-00001-of-00006.safetensors", | |
| "blocks.4.attn.head_gain.head_g": "model-00001-of-00006.safetensors", | |
| "blocks.4.attn_gain.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.4.embed_skip.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.4.mlp.mlp_gate.weight": "model-00001-of-00006.safetensors", | |
| "blocks.4.mlp.mlp_linear.weight": "model-00001-of-00006.safetensors", | |
| "blocks.4.mlp.mlp_resid.weight": "model-00001-of-00006.safetensors", | |
| "blocks.4.mlp_gain.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.5.attn.attn_key.weight": "model-00001-of-00006.safetensors", | |
| "blocks.5.attn.attn_query.weight": "model-00001-of-00006.safetensors", | |
| "blocks.5.attn.attn_resid.weight": "model-00001-of-00006.safetensors", | |
| "blocks.5.attn.attn_value.weight": "model-00001-of-00006.safetensors", | |
| "blocks.5.attn.head_gain.head_g": "model-00001-of-00006.safetensors", | |
| "blocks.5.attn_gain.a_g": "model-00001-of-00006.safetensors", | |
| "blocks.5.embed_skip.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.5.mlp.mlp_gate.weight": "model-00001-of-00006.safetensors", | |
| "blocks.5.mlp.mlp_linear.weight": "model-00001-of-00006.safetensors", | |
| "blocks.5.mlp.mlp_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.5.mlp_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.6.attn.attn_key.weight": "model-00002-of-00006.safetensors", | |
| "blocks.6.attn.attn_query.weight": "model-00002-of-00006.safetensors", | |
| "blocks.6.attn.attn_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.6.attn.attn_value.weight": "model-00002-of-00006.safetensors", | |
| "blocks.6.attn.head_gain.head_g": "model-00002-of-00006.safetensors", | |
| "blocks.6.attn_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.6.embed_skip.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.6.mlp.mlp_gate.weight": "model-00002-of-00006.safetensors", | |
| "blocks.6.mlp.mlp_linear.weight": "model-00002-of-00006.safetensors", | |
| "blocks.6.mlp.mlp_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.6.mlp_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.7.attn.attn_key.weight": "model-00002-of-00006.safetensors", | |
| "blocks.7.attn.attn_query.weight": "model-00002-of-00006.safetensors", | |
| "blocks.7.attn.attn_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.7.attn.attn_value.weight": "model-00002-of-00006.safetensors", | |
| "blocks.7.attn.head_gain.head_g": "model-00002-of-00006.safetensors", | |
| "blocks.7.attn_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.7.embed_skip.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.7.mlp.mlp_gate.weight": "model-00002-of-00006.safetensors", | |
| "blocks.7.mlp.mlp_linear.weight": "model-00002-of-00006.safetensors", | |
| "blocks.7.mlp.mlp_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.7.mlp_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.8.attn.attn_key.weight": "model-00002-of-00006.safetensors", | |
| "blocks.8.attn.attn_query.weight": "model-00002-of-00006.safetensors", | |
| "blocks.8.attn.attn_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.8.attn.attn_value.weight": "model-00002-of-00006.safetensors", | |
| "blocks.8.attn.head_gain.head_g": "model-00002-of-00006.safetensors", | |
| "blocks.8.attn_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.8.embed_skip.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.8.mlp.mlp_gate.weight": "model-00002-of-00006.safetensors", | |
| "blocks.8.mlp.mlp_linear.weight": "model-00002-of-00006.safetensors", | |
| "blocks.8.mlp.mlp_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.8.mlp_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.9.attn.attn_key.weight": "model-00002-of-00006.safetensors", | |
| "blocks.9.attn.attn_query.weight": "model-00002-of-00006.safetensors", | |
| "blocks.9.attn.attn_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.9.attn.attn_value.weight": "model-00002-of-00006.safetensors", | |
| "blocks.9.attn.head_gain.head_g": "model-00002-of-00006.safetensors", | |
| "blocks.9.attn_gain.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.9.embed_skip.a_g": "model-00002-of-00006.safetensors", | |
| "blocks.9.mlp.mlp_gate.weight": "model-00002-of-00006.safetensors", | |
| "blocks.9.mlp.mlp_linear.weight": "model-00002-of-00006.safetensors", | |
| "blocks.9.mlp.mlp_resid.weight": "model-00002-of-00006.safetensors", | |
| "blocks.9.mlp_gain.a_g": "model-00002-of-00006.safetensors", | |
| "embed.weight": "model-00001-of-00006.safetensors", | |
| "lm_head.weight": "model-00001-of-00006.safetensors" | |
| } | |
| } | |