Create README.md

README.md

@@ -0,0 +1,208 @@
+---
+pipeline_tag: text-generation
+tags:
+- int8
+- vllm
+license: gemma
+---
+
+# gemma-2-2b-it-quantized.w8a16
+
+## Model Overview
+- **Model Architecture:** Gemma 2
+  - **Input:** Text
+  - **Output:** Text
+- **Model Optimizations:**
+  - **Weight quantization:** INT8
+- **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [gemma-2-2b](https://huggingface.co/google/gemma-2-2b), this is a pre-trained base model that can be used as is or specialized to specific domains.
+- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English.
+- **Release Date:** 8/13/2024
+- **Version:** 1.0
+- **License(s):** [gemma](https://ai.google.dev/gemma/terms)
+- **Model Developers:** Neural Magic
+
+Quantized version of [gemma-2-2b](https://huggingface.co/google/gemma-2-2b).
+It achieves an average score of 52.03 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 52.16.
+
+### Model Optimizations
+
+This model was obtained by quantizing the weights of [gemma-2-2b](https://huggingface.co/google/gemma-2-2b) to INT8 data type.
+This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%.
+
+Only the weights of the linear operators within transformers blocks are quantized. Symmetric per-channel quantization is applied, in which a linear scaling per output dimension maps the INT8 and floating point representations of the quantized weights.
+The [GPTQ](https://arxiv.org/abs/2210.17323) algorithm is applied for quantization, as implemented in the [llm-compressor](https://github.com/vllm-project/llm-compressor) library. GPTQ used a 1% damping factor and 256 sequences of 8,192 random tokens.
+
+## Deployment
+
+### Use with vLLM
+
+This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.
+
+```python
+from vllm import LLM, SamplingParams
+from transformers import AutoTokenizer
+
+model_id = "neuralmagic/gemma-2-2b-quantized.w8a16"
+
+sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256)
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+messages = [
+    {"role": "user", "content": "Who are you? Please respond in pirate speak!"},
+]
+
+prompts = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+
+llm = LLM(model=model_id)
+
+outputs = llm.generate(prompts, sampling_params)
+
+generated_text = outputs[0].outputs[0].text
+print(generated_text)
+```
+
+vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
+
+## Creation
+
+This model was created by using the [llm-compressor](https://github.com/vllm-project/llm-compressor) library as presented in the code snipet below.
+
+```python
+from transformers import AutoTokenizer
+from datasets import Dataset
+from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot
+from llmcompressor.modifiers.quantization import GPTQModifier
+import random
+
+model_id = "google/gemma-2-2b"
+
+num_samples = 256
+max_seq_len = 8192
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+max_token_id = len(tokenizer.get_vocab()) - 1
+input_ids = [[random.randint(0, max_token_id) for _ in range(max_seq_len)] for _ in range(num_samples)]
+attention_mask = num_samples * [max_seq_len * [1]]
+ds = Dataset.from_dict({"input_ids": input_ids, "attention_mask": attention_mask})
+
+recipe = GPTQModifier(
+  targets="Linear",
+  scheme="W8A16",
+  ignore=["lm_head"],
+  dampening_frac=0.01,
+)
+
+model = SparseAutoModelForCausalLM.from_pretrained(
+  model_id,
+  device_map="auto",
+  trust_remote_code=True,
+)
+
+oneshot(
+  model=model,
+  dataset=ds,
+  recipe=recipe,
+  max_seq_length=max_seq_len,
+  num_calibration_samples=num_samples,
+)
+model.save_pretrained("gemma-2-2b-quantized.w8a16")
+```
+
+## Evaluation
+
+The model was evaluated on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) leaderboard tasks (version 1) with the [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness/tree/383bbd54bc621086e05aa1b030d8d4d5635b25e6) (commit 383bbd54bc621086e05aa1b030d8d4d5635b25e6) and the [vLLM](https://docs.vllm.ai/en/stable/) engine, using the following command:
+```
+lm_eval \
+  --model vllm \
+  --model_args pretrained="neuralmagic/gemma-2-2b-quantized.w8a16",dtype=auto,gpu_memory_utilization=0.4,add_bos_token=True,max_model_len=4096 \
+  --tasks openllm \
+  --batch_size auto
+```
+
+### Accuracy
+
+#### Open LLM Leaderboard evaluation scores
+<table>
+  <tr>
+   <td><strong>Benchmark</strong>
+   </td>
+   <td><strong>gemma-2-2b</strong>
+   </td>
+   <td><strong>gemma-2-2b-quantized.w8a16 (this model)</strong>
+   </td>
+   <td><strong>Recovery</strong>
+   </td>
+  </tr>
+  <tr>
+   <td>MMLU (5-shot)
+   </td>
+   <td>53.01
+   </td>
+   <td>52.86
+   </td>
+   <td>99.7%
+   </td>
+  </tr>
+  <tr>
+   <td>ARC Challenge (25-shot)
+   </td>
+   <td>53.92
+   </td>
+   <td>54.27
+   </td>
+   <td>100.6%
+   </td>
+  </tr>
+  <tr>
+   <td>GSM-8K (5-shot, strict-match)
+   </td>
+   <td>24.03
+   </td>
+   <td>23.81
+   </td>
+   <td>99.1%
+   </td>
+  </tr>
+  <tr>
+   <td>Hellaswag (10-shot)
+   </td>
+   <td>74.74
+   </td>
+   <td>74.56
+   </td>
+   <td>99.8%
+   </td>
+  </tr>
+  <tr>
+   <td>Winogrande (5-shot)
+   </td>
+   <td>70.96
+   </td>
+   <td>70.56
+   </td>
+   <td>99.4%
+   </td>
+  </tr>
+  <tr>
+   <td>TruthfulQA (0-shot)
+   </td>
+   <td>36.29
+   </td>
+   <td>36.15
+   </td>
+   <td>99.6%
+   </td>
+  </tr>
+  <tr>
+   <td><strong>Average</strong>
+   </td>
+   <td><strong>52.16</strong>
+   </td>
+   <td><strong>52.03</strong>
+   </td>
+   <td><strong>99.8%</strong>
+   </td>
+  </tr>
+</table>