Update README.md

README.md

@@ -2,30 +2,84 @@
 base_model: TinyLlama/TinyLlama-1.1B-Chat-v1.0
 inference: True
 model_type: Llama
+tags:
+- nm-vllm
+- sparse
 ---
-# TinyLlama-1.1B-Chat-v1.0
-This repo contains pruned model files for [TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0).
+## TinyLlama-1.1B-Chat-v1.0-pruned2.4
+This repo contains model files for [TinyLlama-1.1B-Chat-v1.0](https://huggingface.co/TinyLlama/TinyLlama-1.1B-Chat-v1.0) optimized for [NM-vLLM](https://github.com/neuralmagic/nm-vllm), a high-throughput serving engine for compressed LLMs.
 
 This model was pruned with [SparseGPT](https://arxiv.org/abs/2301.00774), using [SparseML](https://github.com/neuralmagic/sparseml).
+
+## Inference
+Install [NM-vLLM](https://github.com/neuralmagic/nm-vllm) for fast inference and low memory-usage: 
+```bash
+pip install nm-vllm[sparse]
+```
+Run in a Python pipeline for local inference:
 ```python
+from vllm import LLM, SamplingParams
 
-import torch
-from transformers import AutoTokenizer, AutoModelForCausalLM
+model = LLM("nm-testing/TinyLlama-1.1B-Chat-v1.0-pruned2.4", sparsity="sparse_w16a16")
 prompt = "How to make banana bread?"
 formatted_prompt =  f"<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n"
-model_id = "nm-testing/TinyLlama-1.1B-Chat-v1.0-pruned50-24"
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16)
-tokenizer = AutoTokenizer.from_pretrained(model_id)
-inputs = tokenizer(formatted_prompt, return_tensors="pt")
-outputs = model.generate(**inputs, max_new_tokens=200)
-print(tokenizer.batch_decode(outputs)[0])
 
+sampling_params = SamplingParams(max_tokens=100,temperature=0,repetition_penalty=1.3)
+outputs = model.generate(formatted_prompt, sampling_params=sampling_params)
+print(outputs[0].outputs[0].text)
 """
-<s> <|im_start|>user
-How to make banana bread?<|im_end|>
-<|im_start|>assistant
 Banana bread is a delicious dessert that is made with bananas. Here is how to make banana bread:
 
 1. Firstly, you need to cut bananas into small pieces.
+2. Then, you need to slice the bananas into small pieces
+"""
+```
+
+## Prompt template
+
+```
+<|im_start|>user
+{prompt}<|im_end|>
+<|im_start|>assistant
+
+```
+
+## Sparsification
+For details on how this model was sparsified, see the `recipe.yaml` in this repo and follow the instructions below.
+
+Install [SparseML](https://github.com/neuralmagic/sparseml):
+```bash
+git clone https://github.com/neuralmagic/sparseml
+pip install -e "sparseml[transformers]"
+```
+
+Replace the recipe as you like and run this one-shot compression script to apply SparseGPT:
+```python
+import sparseml.transformers
+
+original_model_name = "TinyLlama/TinyLlama-1.1B-Chat-v1.0"
+calibration_dataset = "open_platypus"
+output_directory = "output/"
+
+recipe = """
+test_stage:
+  obcq_modifiers:
+    SparseGPTModifier:
+      sparsity: 0.5
+      sequential_update: true
+      mask_structure: '2:4'
+      targets: ['re:model.layers.\d*$']
 """
-```
+
+# Apply SparseGPT to the model
+sparseml.transformers.oneshot(
+    model=original_model_name,
+    dataset=calibration_dataset,
+    recipe=recipe,
+    output_dir=output_directory,
+)
+```
+
+## Slack
+
+For further support, and discussions on these models and AI in general, join [Neural Magic's Slack Community](https://join.slack.com/t/discuss-neuralmagic/shared_invite/zt-q1a1cnvo-YBoICSIw3L1dmQpjBeDurQ)