Instructions to use OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints", trust_remote_code=True)

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints", trust_remote_code=True, dtype="auto")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints

SGLang

How to use OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints 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 "OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints" \
    --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": "OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints",
		"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 "OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints" \
        --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": "OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints with Docker Model Runner:
```
docker model run hf.co/OpenNLPLab/TransNormerLLM3-15B-Intermediate-Checkpoints
```

TransNormerLLM3-15B-Intermediate-Checkpoints / pytorch_model.bin.index.json

OpenNLPLab

Upload 24 files

e8051e5 verified about 2 years ago

raw

history blame

25.7 kB

	{
	"metadata": {
	"total_size": 29666764800
	},
	"weight_map": {
	"lm_head.weight": "pytorch_model-00001-of-00011.bin",
	"model.embed_tokens.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.0.channel_mixer.l1.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.0.channel_mixer.l2.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.0.channel_mixer.l3.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.0.token_mixer.lrpe.theta": "pytorch_model-00001-of-00011.bin",
	"model.layers.0.token_mixer.out_proj.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.0.token_mixer.output_gate.0.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.0.token_mixer.output_gate.1.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.0.token_mixer.qkv_proj.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.1.channel_mixer.l1.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.1.channel_mixer.l2.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.1.channel_mixer.l3.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.1.token_mixer.out_proj.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.1.token_mixer.output_gate.0.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.1.token_mixer.output_gate.1.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.1.token_mixer.qkv_proj.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.10.channel_mixer.l1.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.10.channel_mixer.l2.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.10.channel_mixer.l3.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.10.token_mixer.out_proj.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.10.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.10.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.10.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.11.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.11.channel_mixer.l2.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.11.channel_mixer.l3.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.11.token_mixer.out_proj.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.11.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.11.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.11.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.12.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.12.channel_mixer.l2.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.12.channel_mixer.l3.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.12.token_mixer.out_proj.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.12.token_mixer.output_gate.0.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.12.token_mixer.output_gate.1.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.12.token_mixer.qkv_proj.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.13.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.13.channel_mixer.l2.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.13.channel_mixer.l3.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.13.token_mixer.out_proj.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.13.token_mixer.output_gate.0.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.13.token_mixer.output_gate.1.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.13.token_mixer.qkv_proj.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.14.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.14.channel_mixer.l2.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.14.channel_mixer.l3.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.14.token_mixer.out_proj.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.14.token_mixer.output_gate.0.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.14.token_mixer.output_gate.1.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.14.token_mixer.qkv_proj.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.15.channel_mixer.l1.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.15.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.15.channel_mixer.l3.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.15.token_mixer.out_proj.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.15.token_mixer.output_gate.0.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.15.token_mixer.output_gate.1.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.15.token_mixer.qkv_proj.weight": "pytorch_model-00004-of-00011.bin",
	"model.layers.16.channel_mixer.l1.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.16.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.16.channel_mixer.l3.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.16.token_mixer.out_proj.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.16.token_mixer.output_gate.0.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.16.token_mixer.output_gate.1.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.16.token_mixer.qkv_proj.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.17.channel_mixer.l1.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.17.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.17.channel_mixer.l3.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.17.token_mixer.out_proj.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.17.token_mixer.output_gate.0.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.17.token_mixer.output_gate.1.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.17.token_mixer.qkv_proj.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.18.channel_mixer.l1.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.18.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.18.channel_mixer.l3.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.18.token_mixer.out_proj.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.18.token_mixer.output_gate.0.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.18.token_mixer.output_gate.1.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.18.token_mixer.qkv_proj.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.19.channel_mixer.l1.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.19.channel_mixer.l2.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.19.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.19.token_mixer.out_proj.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.19.token_mixer.output_gate.0.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.19.token_mixer.output_gate.1.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.19.token_mixer.qkv_proj.weight": "pytorch_model-00005-of-00011.bin",
	"model.layers.2.channel_mixer.l1.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.2.channel_mixer.l2.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.2.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.2.token_mixer.out_proj.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.2.token_mixer.output_gate.0.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.2.token_mixer.output_gate.1.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.2.token_mixer.qkv_proj.weight": "pytorch_model-00001-of-00011.bin",
	"model.layers.20.channel_mixer.l1.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.20.channel_mixer.l2.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.20.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.20.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.20.token_mixer.output_gate.0.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.20.token_mixer.output_gate.1.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.20.token_mixer.qkv_proj.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.21.channel_mixer.l1.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.21.channel_mixer.l2.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.21.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.21.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.21.token_mixer.output_gate.0.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.21.token_mixer.output_gate.1.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.21.token_mixer.qkv_proj.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.22.channel_mixer.l1.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.22.channel_mixer.l2.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.22.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.22.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.22.token_mixer.output_gate.0.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.22.token_mixer.output_gate.1.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.22.token_mixer.qkv_proj.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.23.channel_mixer.l1.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.23.channel_mixer.l2.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.23.channel_mixer.l3.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.23.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.23.token_mixer.output_gate.0.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.23.token_mixer.output_gate.1.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.23.token_mixer.qkv_proj.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.24.channel_mixer.l1.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.24.channel_mixer.l2.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.24.channel_mixer.l3.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.24.token_mixer.out_proj.weight": "pytorch_model-00006-of-00011.bin",
	"model.layers.24.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.24.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.24.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.25.channel_mixer.l1.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.25.channel_mixer.l2.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.25.channel_mixer.l3.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.25.token_mixer.out_proj.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.25.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.25.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.25.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.26.channel_mixer.l1.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.26.channel_mixer.l2.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.26.channel_mixer.l3.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.26.token_mixer.out_proj.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.26.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.26.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.26.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.27.channel_mixer.l1.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.27.channel_mixer.l2.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.27.channel_mixer.l3.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.27.token_mixer.out_proj.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.27.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.27.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.27.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.28.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.28.channel_mixer.l2.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.28.channel_mixer.l3.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.28.token_mixer.out_proj.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.28.token_mixer.output_gate.0.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.28.token_mixer.output_gate.1.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.28.token_mixer.qkv_proj.weight": "pytorch_model-00007-of-00011.bin",
	"model.layers.29.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.29.channel_mixer.l2.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.29.channel_mixer.l3.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.29.token_mixer.out_proj.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.29.token_mixer.output_gate.0.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.29.token_mixer.output_gate.1.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.29.token_mixer.qkv_proj.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.3.channel_mixer.l1.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.3.channel_mixer.l2.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.3.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.3.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.3.token_mixer.output_gate.0.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.3.token_mixer.output_gate.1.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.3.token_mixer.qkv_proj.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.30.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.30.channel_mixer.l2.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.30.channel_mixer.l3.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.30.token_mixer.out_proj.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.30.token_mixer.output_gate.0.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.30.token_mixer.output_gate.1.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.30.token_mixer.qkv_proj.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.31.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.31.channel_mixer.l2.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.31.channel_mixer.l3.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.31.token_mixer.out_proj.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.31.token_mixer.output_gate.0.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.31.token_mixer.output_gate.1.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.31.token_mixer.qkv_proj.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.32.channel_mixer.l1.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.32.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.32.channel_mixer.l3.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.32.token_mixer.out_proj.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.32.token_mixer.output_gate.0.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.32.token_mixer.output_gate.1.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.32.token_mixer.qkv_proj.weight": "pytorch_model-00008-of-00011.bin",
	"model.layers.33.channel_mixer.l1.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.33.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.33.channel_mixer.l3.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.33.token_mixer.out_proj.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.33.token_mixer.output_gate.0.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.33.token_mixer.output_gate.1.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.33.token_mixer.qkv_proj.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.34.channel_mixer.l1.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.34.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.34.channel_mixer.l3.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.34.token_mixer.out_proj.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.34.token_mixer.output_gate.0.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.34.token_mixer.output_gate.1.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.34.token_mixer.qkv_proj.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.35.channel_mixer.l1.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.35.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.35.channel_mixer.l3.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.35.token_mixer.out_proj.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.35.token_mixer.output_gate.0.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.35.token_mixer.output_gate.1.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.35.token_mixer.qkv_proj.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.36.channel_mixer.l1.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.36.channel_mixer.l2.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.36.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.36.token_mixer.out_proj.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.36.token_mixer.output_gate.0.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.36.token_mixer.output_gate.1.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.36.token_mixer.qkv_proj.weight": "pytorch_model-00009-of-00011.bin",
	"model.layers.37.channel_mixer.l1.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.37.channel_mixer.l2.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.37.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.37.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.37.token_mixer.output_gate.0.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.37.token_mixer.output_gate.1.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.37.token_mixer.qkv_proj.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.38.channel_mixer.l1.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.38.channel_mixer.l2.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.38.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.38.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.38.token_mixer.output_gate.0.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.38.token_mixer.output_gate.1.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.38.token_mixer.qkv_proj.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.39.channel_mixer.l1.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.39.channel_mixer.l2.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.39.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.39.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.39.token_mixer.output_gate.0.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.39.token_mixer.output_gate.1.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.39.token_mixer.qkv_proj.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.4.channel_mixer.l1.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.4.channel_mixer.l2.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.4.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.4.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.4.token_mixer.output_gate.0.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.4.token_mixer.output_gate.1.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.4.token_mixer.qkv_proj.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.40.channel_mixer.l1.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.40.channel_mixer.l2.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.40.channel_mixer.l3.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.40.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.40.token_mixer.output_gate.0.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.40.token_mixer.output_gate.1.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.40.token_mixer.qkv_proj.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.41.channel_mixer.l1.weight": "pytorch_model-00011-of-00011.bin",
	"model.layers.41.channel_mixer.l2.weight": "pytorch_model-00011-of-00011.bin",
	"model.layers.41.channel_mixer.l3.weight": "pytorch_model-00011-of-00011.bin",
	"model.layers.41.token_mixer.out_proj.weight": "pytorch_model-00010-of-00011.bin",
	"model.layers.41.token_mixer.output_gate.0.weight": "pytorch_model-00011-of-00011.bin",
	"model.layers.41.token_mixer.output_gate.1.weight": "pytorch_model-00011-of-00011.bin",
	"model.layers.41.token_mixer.qkv_proj.weight": "pytorch_model-00011-of-00011.bin",
	"model.layers.5.channel_mixer.l1.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.5.channel_mixer.l2.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.5.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.5.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.5.token_mixer.output_gate.0.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.5.token_mixer.output_gate.1.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.5.token_mixer.qkv_proj.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.6.channel_mixer.l1.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.6.channel_mixer.l2.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.6.channel_mixer.l3.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.6.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.6.token_mixer.output_gate.0.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.6.token_mixer.output_gate.1.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.6.token_mixer.qkv_proj.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.7.channel_mixer.l1.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.7.channel_mixer.l2.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.7.channel_mixer.l3.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.7.token_mixer.out_proj.weight": "pytorch_model-00002-of-00011.bin",
	"model.layers.7.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.7.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.7.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.8.channel_mixer.l1.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.8.channel_mixer.l2.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.8.channel_mixer.l3.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.8.token_mixer.out_proj.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.8.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.8.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.8.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.9.channel_mixer.l1.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.9.channel_mixer.l2.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.9.channel_mixer.l3.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.9.token_mixer.out_proj.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.9.token_mixer.output_gate.0.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.9.token_mixer.output_gate.1.weight": "pytorch_model-00003-of-00011.bin",
	"model.layers.9.token_mixer.qkv_proj.weight": "pytorch_model-00003-of-00011.bin"
	}
	}