Instructions to use nm-testing/tinyllama-one-shot-dynamic-test with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use nm-testing/tinyllama-one-shot-dynamic-test with Transformers:

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

pipe = pipeline("text-generation", model="nm-testing/tinyllama-one-shot-dynamic-test")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("nm-testing/tinyllama-one-shot-dynamic-test")
model = AutoModelForCausalLM.from_pretrained("nm-testing/tinyllama-one-shot-dynamic-test")
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

vLLM

How to use nm-testing/tinyllama-one-shot-dynamic-test with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "nm-testing/tinyllama-one-shot-dynamic-test"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "nm-testing/tinyllama-one-shot-dynamic-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/nm-testing/tinyllama-one-shot-dynamic-test

SGLang

How to use nm-testing/tinyllama-one-shot-dynamic-test 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 "nm-testing/tinyllama-one-shot-dynamic-test" \
    --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": "nm-testing/tinyllama-one-shot-dynamic-test",
		"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 "nm-testing/tinyllama-one-shot-dynamic-test" \
        --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": "nm-testing/tinyllama-one-shot-dynamic-test",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use nm-testing/tinyllama-one-shot-dynamic-test with Docker Model Runner:
```
docker model run hf.co/nm-testing/tinyllama-one-shot-dynamic-test
```

sadkins65 commited on May 3, 2024

Commit

01d7326

verified ·

1 Parent(s): bfe8310

Upload folder using huggingface_hub

Browse files

Files changed (3) hide show

config.json +6 -0
model.safetensors +1 -1
recipe.yaml +6 -0

config.json CHANGED Viewed

@@ -46,6 +46,12 @@
       ],
       "quant_method": "sparseml",
       "quantization_status": "frozen"
     }
   },
   "eos_token_id": 2,

       ],
       "quant_method": "sparseml",
       "quantization_status": "frozen"
+    },
+    "sparsity_config": {
+      "format": "dense",
+      "global_sparsity": 7.700428565876607,
+      "registry_requires_subclass": false,
+      "sparsity_structure": "0:0"
     }
   },
   "eos_token_id": 2,

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0966eef7b6292b59aeedc6a484e8886cbeb064ab0c29037804200c1e51105f2c
 size 1528201733

 version https://git-lfs.github.com/spec/v1
+oid sha256:f1413b4a713469abe8b3261fa9aa36d54712fdaa94ef5be5f0ab71b435714735
 size 1528201733

recipe.yaml CHANGED Viewed

@@ -8,3 +8,9 @@ test_stage:
           input_activations: {num_bits: 8, type: int, symmetric: true, strategy: token, dynamic: true}
           output_activations: null
           targets: [Linear]

           input_activations: {num_bits: 8, type: int, symmetric: true, strategy: token, dynamic: true}
           output_activations: null
           targets: [Linear]
+    SparseGPTModifier:
+      sparsity: 0.0
+      block_size: 128
+      sequential_update: false
+      quantize: true
+      targets: ['re:model.layers.\d+$']