Instructions to use pruna-test/test-save-tiny-random-llama3-smashed-pro with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pruna-test/test-save-tiny-random-llama3-smashed-pro 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-llama3-smashed-pro")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("pruna-test/test-save-tiny-random-llama3-smashed-pro")
model = AutoModelForCausalLM.from_pretrained("pruna-test/test-save-tiny-random-llama3-smashed-pro")

Pruna AI

How to use pruna-test/test-save-tiny-random-llama3-smashed-pro with Pruna AI:

# Use a pipeline as a high-level helper
from pruna_pro import PrunaProModel

pipe = PrunaProModel.from_pretrained("pruna_pro-test/test-save-tiny-random-llama3-smashed-pro")

from pruna_pro import PrunaProModel
# Load model directly
from transformers import AutoTokenizer

tokenizer = AutoTokenizer.from_pretrained("pruna_pro-test/test-save-tiny-random-llama3-smashed-pro")
model = PrunaProModel.from_pretrained("pruna_pro-test/test-save-tiny-random-llama3-smashed-pro")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use pruna-test/test-save-tiny-random-llama3-smashed-pro 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-llama3-smashed-pro"
# 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-llama3-smashed-pro",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/pruna-test/test-save-tiny-random-llama3-smashed-pro

SGLang

How to use pruna-test/test-save-tiny-random-llama3-smashed-pro 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-llama3-smashed-pro" \
    --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-llama3-smashed-pro",
		"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-llama3-smashed-pro" \
        --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-llama3-smashed-pro",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use pruna-test/test-save-tiny-random-llama3-smashed-pro with Docker Model Runner:
```
docker model run hf.co/pruna-test/test-save-tiny-random-llama3-smashed-pro
```

johnrachwanpruna commited on 20 days ago

Commit

cae4125

verified ·

1 Parent(s): a0eff08

Add files using upload-large-folder tool

Browse files

Files changed (4) hide show

README.md +2 -2
config.json +6 -3
generation_config.json +1 -1
smash_config.json +1 -1

README.md CHANGED Viewed

@@ -2,8 +2,8 @@
 library_name: transformers
 tags:
 - pruna_pro-ai
-- safetensors
 - pruna-ai
 ---
 # Model Card for pruna-test/test-save-tiny-random-llama3-smashed-pro
@@ -66,6 +66,7 @@ The compression configuration of the model is stored in the `smash_config.json`
     "ifw": false,
     "img2img_denoise": false,
     "kvpress": false,
     "llm_int8": false,
     "moe_kernel_tuner": false,
     "pab": false,
@@ -98,7 +99,6 @@ The compression configuration of the model is stored in the `smash_config.json`
     "torch_unstructured": false,
     "torchao": false,
     "torchao_autoquant": false,
-    "whisper_s2t": false,
     "x_fast": false,
     "zipar": false,
     "batch_size": 1,

 library_name: transformers
 tags:
 - pruna_pro-ai
 - pruna-ai
+- safetensors
 ---
 # Model Card for pruna-test/test-save-tiny-random-llama3-smashed-pro
     "ifw": false,
     "img2img_denoise": false,
     "kvpress": false,
+    "llama_cpp": false,
     "llm_int8": false,
     "moe_kernel_tuner": false,
     "pab": false,
     "torch_unstructured": false,
     "torchao": false,
     "torchao_autoquant": false,
     "x_fast": false,
     "zipar": false,
     "batch_size": 1,

config.json CHANGED Viewed

@@ -18,12 +18,15 @@
   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "num_key_value_heads": 1,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
-  "rope_scaling": null,
-  "rope_theta": 10000.0,
   "tie_word_embeddings": false,
-  "transformers_version": "4.57.6",
   "use_cache": true,
   "vocab_size": 128256
 }

   "num_attention_heads": 4,
   "num_hidden_layers": 2,
   "num_key_value_heads": 1,
+  "pad_token_id": null,
   "pretraining_tp": 1,
   "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
   "tie_word_embeddings": false,
+  "transformers_version": "5.11.0",
   "use_cache": true,
   "vocab_size": 128256
 }

generation_config.json CHANGED Viewed

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.57.6"
 }

   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
+  "transformers_version": "5.11.0"
 }

smash_config.json CHANGED Viewed

@@ -24,6 +24,7 @@
     "ifw": false,
     "img2img_denoise": false,
     "kvpress": false,
     "llm_int8": false,
     "moe_kernel_tuner": false,
     "pab": false,
@@ -56,7 +57,6 @@
     "torch_unstructured": false,
     "torchao": false,
     "torchao_autoquant": false,
-    "whisper_s2t": false,
     "x_fast": false,
     "zipar": false,
     "batch_size": 1,

     "ifw": false,
     "img2img_denoise": false,
     "kvpress": false,
+    "llama_cpp": false,
     "llm_int8": false,
     "moe_kernel_tuner": false,
     "pab": false,
     "torch_unstructured": false,
     "torchao": false,
     "torchao_autoquant": false,
     "x_fast": false,
     "zipar": false,
     "batch_size": 1,