Instructions to use benjamin/Gemma2-2B-Distilled-Math with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use benjamin/Gemma2-2B-Distilled-Math with Transformers:

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

pipe = pipeline("text-generation", model="benjamin/Gemma2-2B-Distilled-Math")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("benjamin/Gemma2-2B-Distilled-Math")
model = AutoModelForCausalLM.from_pretrained("benjamin/Gemma2-2B-Distilled-Math")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use benjamin/Gemma2-2B-Distilled-Math with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "benjamin/Gemma2-2B-Distilled-Math"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "benjamin/Gemma2-2B-Distilled-Math",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/benjamin/Gemma2-2B-Distilled-Math

SGLang

How to use benjamin/Gemma2-2B-Distilled-Math 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 "benjamin/Gemma2-2B-Distilled-Math" \
    --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": "benjamin/Gemma2-2B-Distilled-Math",
		"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 "benjamin/Gemma2-2B-Distilled-Math" \
        --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": "benjamin/Gemma2-2B-Distilled-Math",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use benjamin/Gemma2-2B-Distilled-Math with Docker Model Runner:
```
docker model run hf.co/benjamin/Gemma2-2B-Distilled-Math
```

Gemma2-2B-Distilled-Math / flax_model.msgpack.index.json

benjamin

Upload FlaxGemma2ForCausalLM

4e7543e verified about 1 year ago

raw

history blame contribute delete

24.5 kB

	{
	"metadata": {
	"total_size": 10480094208
	},
	"weight_map": {
	"model/embed_tokens/embedding": "flax_model-00001-of-00003.msgpack",
	"model/layers/0/input_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/0/mlp/down_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/0/mlp/gate_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/0/mlp/up_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/0/post_attention_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/0/post_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/0/pre_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/0/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/0/self_attn/o_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/0/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/0/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/1/input_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/1/mlp/down_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/1/mlp/gate_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/1/mlp/up_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/1/post_attention_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/1/post_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/1/pre_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/1/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/1/self_attn/o_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/1/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/1/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/10/input_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/10/mlp/down_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/10/mlp/gate_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/10/mlp/up_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/10/post_attention_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/10/post_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/10/pre_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/10/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/10/self_attn/o_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/10/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/10/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/11/input_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/11/mlp/down_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/11/mlp/gate_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/11/mlp/up_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/11/post_attention_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/11/post_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/11/pre_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/11/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/11/self_attn/o_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/11/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/11/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/12/input_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/12/mlp/down_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/12/mlp/gate_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/12/mlp/up_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/12/post_attention_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/12/post_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/12/pre_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/12/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/12/self_attn/o_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/12/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/12/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/13/input_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/13/mlp/down_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/13/mlp/gate_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/13/mlp/up_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/13/post_attention_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/13/post_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/13/pre_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/13/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/13/self_attn/o_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/13/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/13/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/14/input_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/14/mlp/down_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/14/mlp/gate_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/14/mlp/up_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/14/post_attention_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/14/post_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/14/pre_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/14/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/14/self_attn/o_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/14/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/14/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/15/input_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/15/mlp/down_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/15/mlp/gate_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/15/mlp/up_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/15/post_attention_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/15/post_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/15/pre_feedforward_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/15/self_attn/k_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/15/self_attn/o_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/15/self_attn/q_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/15/self_attn/v_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/16/input_layernorm/weight": "flax_model-00001-of-00003.msgpack",
	"model/layers/16/mlp/down_proj/kernel": "flax_model-00001-of-00003.msgpack",
	"model/layers/16/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/16/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/16/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/16/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/16/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/16/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/16/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/16/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/16/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/17/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/17/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/17/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/17/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/17/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/17/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/17/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/17/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/17/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/17/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/17/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/18/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/18/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/18/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/18/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/18/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/18/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/18/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/18/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/18/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/18/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/18/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/19/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/19/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/19/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/19/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/19/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/19/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/19/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/19/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/19/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/19/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/19/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/2/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/2/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/2/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/2/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/2/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/2/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/2/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/2/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/2/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/2/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/2/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/20/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/20/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/20/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/20/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/20/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/20/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/20/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/20/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/20/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/20/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/20/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/21/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/21/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/21/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/21/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/21/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/21/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/21/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/21/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/21/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/21/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/21/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/22/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/22/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/22/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/22/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/22/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/22/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/22/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/22/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/22/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/22/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/22/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/23/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/23/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/23/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/23/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/23/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/23/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/23/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/23/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/23/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/23/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/23/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/24/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/24/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/24/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/24/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/24/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/24/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/24/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/24/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/24/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/24/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/24/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/25/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/25/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/25/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/25/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/25/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/25/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/25/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/25/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/25/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/25/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/25/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/3/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/3/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/3/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/3/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/3/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/3/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/3/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/3/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/3/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/3/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/3/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/4/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/4/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/4/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/4/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/4/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/4/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/4/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/4/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/4/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/4/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/4/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/5/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/5/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/5/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/5/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/5/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/5/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/5/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/5/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/5/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/5/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/5/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/6/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/6/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/6/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/6/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/6/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/6/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/6/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/6/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/6/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/6/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/6/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/7/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/7/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/7/mlp/gate_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/7/mlp/up_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/7/post_attention_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/7/post_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/7/pre_feedforward_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/7/self_attn/k_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/7/self_attn/o_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/7/self_attn/q_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/7/self_attn/v_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/8/input_layernorm/weight": "flax_model-00002-of-00003.msgpack",
	"model/layers/8/mlp/down_proj/kernel": "flax_model-00002-of-00003.msgpack",
	"model/layers/8/mlp/gate_proj/kernel": "flax_model-00003-of-00003.msgpack",
	"model/layers/8/mlp/up_proj/kernel": "flax_model-00003-of-00003.msgpack",
	"model/layers/8/post_attention_layernorm/weight": "flax_model-00003-of-00003.msgpack",
	"model/layers/8/post_feedforward_layernorm/weight": "flax_model-00003-of-00003.msgpack",
	"model/layers/8/pre_feedforward_layernorm/weight": "flax_model-00003-of-00003.msgpack",
	"model/layers/8/self_attn/k_proj/kernel": "flax_model-00003-of-00003.msgpack",
	"model/layers/8/self_attn/o_proj/kernel": "flax_model-00003-of-00003.msgpack",
	"model/layers/8/self_attn/q_proj/kernel": "flax_model-00003-of-00003.msgpack",
	"model/layers/8/self_attn/v_proj/kernel": "flax_model-00003-of-00003.msgpack",
	"model/layers/9/input_layernorm/weight": "flax_model-00003-of-00003.msgpack",
	"model/layers/9/mlp/down_proj/kernel": "flax_model-00003-of-00003.msgpack",
	"model/layers/9/mlp/gate_proj/kernel": "flax_model-00003-of-00003.msgpack",
	"model/layers/9/mlp/up_proj/kernel": "flax_model-00003-of-00003.msgpack",
	"model/layers/9/post_attention_layernorm/weight": "flax_model-00003-of-00003.msgpack",
	"model/layers/9/post_feedforward_layernorm/weight": "flax_model-00003-of-00003.msgpack",
	"model/layers/9/pre_feedforward_layernorm/weight": "flax_model-00003-of-00003.msgpack",
	"model/layers/9/self_attn/k_proj/kernel": "flax_model-00003-of-00003.msgpack",
	"model/layers/9/self_attn/o_proj/kernel": "flax_model-00003-of-00003.msgpack",
	"model/layers/9/self_attn/q_proj/kernel": "flax_model-00003-of-00003.msgpack",
	"model/layers/9/self_attn/v_proj/kernel": "flax_model-00003-of-00003.msgpack",
	"model/norm/weight": "flax_model-00003-of-00003.msgpack"
	}
	}