Instructions to use benjamin/Qwen2.5-Math-1.5B-flax with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use benjamin/Qwen2.5-Math-1.5B-flax with Transformers:

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

pipe = pipeline("text-generation", model="benjamin/Qwen2.5-Math-1.5B-flax")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("benjamin/Qwen2.5-Math-1.5B-flax")
model = AutoModelForCausalLM.from_pretrained("benjamin/Qwen2.5-Math-1.5B-flax", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use benjamin/Qwen2.5-Math-1.5B-flax with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "benjamin/Qwen2.5-Math-1.5B-flax"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "benjamin/Qwen2.5-Math-1.5B-flax",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/benjamin/Qwen2.5-Math-1.5B-flax

SGLang

How to use benjamin/Qwen2.5-Math-1.5B-flax 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/Qwen2.5-Math-1.5B-flax" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "benjamin/Qwen2.5-Math-1.5B-flax",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "benjamin/Qwen2.5-Math-1.5B-flax" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "benjamin/Qwen2.5-Math-1.5B-flax",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use benjamin/Qwen2.5-Math-1.5B-flax with Docker Model Runner:
```
docker model run hf.co/benjamin/Qwen2.5-Math-1.5B-flax
```

Qwen2.5-Math-1.5B-flax / flax_model.msgpack.index.json

benjamin

Upload FlaxLlamaForCausalLM

61ddb66 verified over 1 year ago

Raw

History Blame Contribute Delete

30.3 kB

	{
	"metadata": {
	"total_size": 6175029248
	},
	"weight_map": {
	"model/embed_tokens/embedding": "flax_model-00001-of-00002.msgpack",
	"model/layers/0/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/0/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/0/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/0/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/0/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/0/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/0/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/0/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/0/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/0/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/0/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/0/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/0/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/1/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/1/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/1/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/1/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/1/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/1/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/1/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/1/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/1/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/1/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/1/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/1/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/1/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/10/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/10/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/10/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/10/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/10/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/10/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/10/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/10/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/10/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/10/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/10/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/10/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/10/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/11/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/11/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/11/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/11/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/11/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/11/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/11/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/11/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/11/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/11/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/11/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/11/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/11/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/12/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/12/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/12/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/12/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/12/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/12/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/12/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/12/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/12/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/12/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/12/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/12/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/12/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/13/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/13/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/13/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/13/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/13/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/13/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/13/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/13/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/13/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/13/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/13/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/13/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/13/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/14/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/14/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/14/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/14/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/14/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/14/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/14/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/14/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/14/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/14/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/14/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/14/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/14/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/15/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/15/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/15/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/15/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/15/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/15/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/15/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/15/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/15/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/15/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/15/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/15/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/15/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/16/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/16/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/16/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/16/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/16/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/16/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/16/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/16/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/16/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/16/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/16/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/16/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/16/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/17/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/17/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/17/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/17/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/17/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/17/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/17/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/17/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/17/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/17/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/17/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/17/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/17/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/18/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/18/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/18/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/18/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/18/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/18/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/18/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/18/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/18/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/18/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/18/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/18/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/18/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/19/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/19/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/19/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/19/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/19/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/19/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/19/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/19/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/19/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/19/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/19/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/19/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/19/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/2/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/2/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/2/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/2/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/2/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/2/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/2/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/2/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/2/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/2/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/2/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/2/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/2/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/20/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/20/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/20/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/20/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/20/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/20/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/20/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/20/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/20/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/20/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/20/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/20/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/20/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/21/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/21/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/21/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/21/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/21/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/21/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/21/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/21/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/21/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/21/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/21/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/21/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/21/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/22/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/22/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/22/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/22/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/22/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/22/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/22/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/22/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/22/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/22/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/22/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/22/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/22/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/23/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/23/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/23/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/23/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/23/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/23/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/23/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/23/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/23/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/23/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/23/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/23/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/23/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/24/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/24/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/24/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/24/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/24/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/24/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/24/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/24/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/24/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/24/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/24/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/24/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/24/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/25/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/25/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/25/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/25/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/25/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/25/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/25/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/25/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/25/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/25/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/25/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/25/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/25/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/26/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/26/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/26/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/26/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/26/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/26/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/26/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/26/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/26/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/26/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/26/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/26/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/26/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/27/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/27/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/27/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/27/mlp/up_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/27/post_attention_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/27/self_attn/k_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/27/self_attn/k_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/27/self_attn/o_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/27/self_attn/o_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/27/self_attn/q_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/27/self_attn/q_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/27/self_attn/v_proj/bias": "flax_model-00001-of-00002.msgpack",
	"model/layers/27/self_attn/v_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/3/input_layernorm/weight": "flax_model-00001-of-00002.msgpack",
	"model/layers/3/mlp/down_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/3/mlp/gate_proj/kernel": "flax_model-00001-of-00002.msgpack",
	"model/layers/3/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/3/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
	"model/layers/3/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/3/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/3/self_attn/o_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/3/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/3/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/3/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/3/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/3/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/4/input_layernorm/weight": "flax_model-00002-of-00002.msgpack",
	"model/layers/4/mlp/down_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/4/mlp/gate_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/4/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/4/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
	"model/layers/4/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/4/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/4/self_attn/o_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/4/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/4/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/4/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/4/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/4/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/5/input_layernorm/weight": "flax_model-00002-of-00002.msgpack",
	"model/layers/5/mlp/down_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/5/mlp/gate_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/5/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/5/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
	"model/layers/5/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/5/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/5/self_attn/o_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/5/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/5/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/5/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/5/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/5/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/6/input_layernorm/weight": "flax_model-00002-of-00002.msgpack",
	"model/layers/6/mlp/down_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/6/mlp/gate_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/6/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/6/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
	"model/layers/6/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/6/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/6/self_attn/o_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/6/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/6/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/6/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/6/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/6/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/7/input_layernorm/weight": "flax_model-00002-of-00002.msgpack",
	"model/layers/7/mlp/down_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/7/mlp/gate_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/7/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/7/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
	"model/layers/7/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/7/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/7/self_attn/o_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/7/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/7/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/7/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/7/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/7/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/8/input_layernorm/weight": "flax_model-00002-of-00002.msgpack",
	"model/layers/8/mlp/down_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/8/mlp/gate_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/8/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/8/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
	"model/layers/8/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/8/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/8/self_attn/o_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/8/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/8/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/8/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/8/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/8/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/9/input_layernorm/weight": "flax_model-00002-of-00002.msgpack",
	"model/layers/9/mlp/down_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/9/mlp/gate_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/9/mlp/up_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/9/post_attention_layernorm/weight": "flax_model-00002-of-00002.msgpack",
	"model/layers/9/self_attn/k_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/9/self_attn/k_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/9/self_attn/o_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/9/self_attn/o_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/9/self_attn/q_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/9/self_attn/q_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/layers/9/self_attn/v_proj/bias": "flax_model-00002-of-00002.msgpack",
	"model/layers/9/self_attn/v_proj/kernel": "flax_model-00002-of-00002.msgpack",
	"model/norm/weight": "flax_model-00002-of-00002.msgpack"
	}
	}