Instructions to use pruna-test/test-save-tiny-random-llama4-smashed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pruna-test/test-save-tiny-random-llama4-smashed with Transformers:

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

pipe = pipeline("text-generation", model="pruna-test/test-save-tiny-random-llama4-smashed")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pruna-test/test-save-tiny-random-llama4-smashed")
model = AutoModelForCausalLM.from_pretrained("pruna-test/test-save-tiny-random-llama4-smashed")

Pruna AI

How to use pruna-test/test-save-tiny-random-llama4-smashed with Pruna AI:

# Use a pipeline as a high-level helper
from pruna import PrunaModel

pipe = PrunaModel.from_pretrained("pruna-test/test-save-tiny-random-llama4-smashed")

from pruna import PrunaModel
# Load model directly
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("pruna-test/test-save-tiny-random-llama4-smashed")
model = PrunaModel.from_pretrained("pruna-test/test-save-tiny-random-llama4-smashed")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pruna-test/test-save-tiny-random-llama4-smashed with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "pruna-test/test-save-tiny-random-llama4-smashed"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "pruna-test/test-save-tiny-random-llama4-smashed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pruna-test/test-save-tiny-random-llama4-smashed

SGLang

How to use pruna-test/test-save-tiny-random-llama4-smashed 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 "pruna-test/test-save-tiny-random-llama4-smashed" \
    --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": "pruna-test/test-save-tiny-random-llama4-smashed",
		"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 "pruna-test/test-save-tiny-random-llama4-smashed" \
        --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": "pruna-test/test-save-tiny-random-llama4-smashed",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pruna-test/test-save-tiny-random-llama4-smashed with Docker Model Runner:
```
docker model run hf.co/pruna-test/test-save-tiny-random-llama4-smashed
```

test-save-tiny-random-llama4-smashed / config.json

johnrachwanpruna

Add files using upload-large-folder tool

4870a21 verified 2 days ago

raw

history blame contribute delete

1.53 kB

	{
	"_attn_implementation_autoset": true,
	"architectures": [
	"Llama4ForCausalLM"
	],
	"attention_bias": false,
	"attention_chunk_size": 8192,
	"attention_dropout": 0.0,
	"attn_scale": 0.1,
	"attn_temperature_tuning": true,
	"bos_token_id": 200000,
	"dtype": "float32",
	"eos_token_id": [
	200001,
	200007,
	200008
	],
	"floor_scale": 8192,
	"for_llm_compressor": false,
	"head_dim": 8,
	"hidden_act": "silu",
	"hidden_size": 16,
	"initializer_range": 0.02,
	"interleave_moe_layer_step": 1,
	"intermediate_size": 32,
	"intermediate_size_mlp": 64,
	"layer_types": [
	"chunked_attention",
	"chunked_attention",
	"chunked_attention",
	"full_attention",
	"chunked_attention"
	],
	"max_position_embeddings": 10485760,
	"model_type": "llama4_text",
	"moe_layers": [
	0,
	1,
	2,
	3,
	4
	],
	"no_rope_layers": [
	1,
	1,
	1,
	0,
	1
	],
	"num_attention_heads": 10,
	"num_experts_per_tok": 1,
	"num_hidden_layers": 5,
	"num_key_value_heads": 2,
	"num_local_experts": 4,
	"output_router_logits": false,
	"pad_token_id": 200018,
	"rms_norm_eps": 1e-05,
	"rope_scaling": {
	"factor": 8.0,
	"high_freq_factor": 4.0,
	"low_freq_factor": 1.0,
	"original_max_position_embeddings": 8192,
	"rope_type": "llama3"
	},
	"rope_theta": 500000.0,
	"router_aux_loss_coef": 0.001,
	"router_jitter_noise": 0.0,
	"tie_word_embeddings": false,
	"transformers_version": "4.57.6",
	"use_cache": true,
	"use_qk_norm": true,
	"vocab_size": 202048
	}