Update README.md

README.md

@@ -17,29 +17,223 @@ pipeline_tag: text-generation
 - **Model Developers:** Neural Magic
 
 Quantized version of [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct).
-It achieves an average score of 68.69% on the OpenLLM benchmark (version 1), whereas the unquantized model achieves 68.54%.
+It achieves an average score of 68.69% on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 68.54%.
 
-## Model Optimizations
+### Model Optimizations
 
 This model was obtained by quantizing the weights of [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) to INT8 data type.
-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.
-[AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) is used for quantization.
 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.
+[AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) is used for quantization with 1% damping factor and 256 sequences of 8,192 random tokens.
+
+
+## Usage and Creation
+
+- **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct), this models is intended for assistant-like chat.
+- **Out-of-scope:** Use in any manner that violates applicable laws or regulations (including trade compliance laws). Use in languages other than English.
+
+### Use with transformers
+
+This model is supported by Transformers leveraging the integration with the [AutoGPTQ](https://github.com/AutoGPTQ/AutoGPTQ) data format.
+The following examples contemplate how the model can be used as part of a Transformers pipeline or using the `generate()` function.
+
+#### Transformers pipeline
+
+```python
+import transformers
+import torch
+
+model_id = "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a16"
+
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model_id,
+    model_kwargs={"torch_dtype": "auto"},
+    device_map="auto",
+)
+
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+
+terminators = [
+    pipeline.tokenizer.eos_token_id,
+    pipeline.tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+outputs = pipeline(
+    messages,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+print(outputs[0]["generated_text"][-1])
+```
+
+#### Transformers AutoModelForCausalLM
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+import torch
+
+model_id = "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a16"
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model = AutoModelForCausalLM.from_pretrained(
+    model_id,
+    torch_dtype="auto",
+    device_map="auto",
+)
+
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+
+input_ids = tokenizer.apply_chat_template(
+    messages,
+    add_generation_prompt=True,
+    return_tensors="pt"
+).to(model.device)
+
+terminators = [
+    tokenizer.eos_token_id,
+    tokenizer.convert_tokens_to_ids("<|eot_id|>")
+]
+
+outputs = model.generate(
+    input_ids,
+    max_new_tokens=256,
+    eos_token_id=terminators,
+    do_sample=True,
+    temperature=0.6,
+    top_p=0.9,
+)
+response = outputs[0][input_ids.shape[-1]:]
+print(tokenizer.decode(response, skip_special_tokens=True))
+```
+
+### vLLM Deployment
+
+This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.
+
+```
+from vllm import LLM, SamplingParams
+from transformers import AutoTokenizer
+
+model_id = "neuralmagic/Meta-Llama-3-8B-Instruct-quantized.w8a16"
+
+sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=300)
+
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+messages = [
+    {"role": "system", "content": "You are a pirate chatbot who always responds in pirate speak!"},
+    {"role": "user", "content": "Who are you?"},
+]
+
+prompts = tokenizer.apply_chat_template(messages, tokenize=False)
+
+llm = LLM(model=model_id)
+
+outputs = llm.generate(prompts, sampling_params)
+
+generated_text = outputs[0].outputs[0].text
+print(generated_text)
+```
+
+vLLM aslo supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
+
 ## Evaluation
 
-The model was evaluated with the [lm-evaluation-harness](https://github.com/EleutherAI/lm-evaluation-harness) using the [vLLM](https://docs.vllm.ai/en/stable/) engine.
-
-## Accuracy
-
-### Open LLM Leaderboard evaluation scores
-|                      | [Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct) | Meta-Llama-3-8B-Instruct-quantized.w8a16<br>(this model) |
-| :------------------: | :----------------------: | :------------------------------------------------: |
-| arc-c<br>25-shot     | 62.63%                    | 61.52%                                          |
-| hellaswag<br>10-shot | 78.81%                    | 78.69%                                              |
-| mmlu<br>5-shot       | 66.54%                    | 66.55%                                              |
-| truthfulqa<br>0-shot | 52.49%                    | 52.60%                                              |
-| winogrande<br>5-shot | 76.48%                    | 76.01%                                              |
-| gsm8k<br>5-shot      | 75.21%                    | 75.89%                                              |
-| **Average<br>Accuracy**  | **68.69%**                    |              **68.54%**                                     |
-| **Recovery**             | **100%**                     |              **99.78%**                                     |
+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) using the [vLLM](https://docs.vllm.ai/en/stable/) engine.
+
+### Accuracy
+
+#### Open LLM Leaderboard evaluation scores
+<table>
+  <tr>
+   <td><strong>Benchmark</strong>
+   </td>
+   <td><strong>Meta-Llama-3-8B-Instruct </strong>
+   </td>
+   <td><strong>Meta-Llama-3-8B-Instruct-quantized.w8a16(this model)</strong>
+   </td>
+   <td><strong>Recovery</strong>
+   </td>
+  </tr>
+  <tr>
+   <td>MMLU (5-shot)
+   </td>
+   <td>66.54
+   </td>
+   <td>66.55
+   </td>
+   <td>100.0%
+   </td>
+  </tr>
+  <tr>
+   <td>ARC Challenge (25-shot)
+   </td>
+   <td>62.63
+   </td>
+   <td>61.52
+   </td>
+   <td>98.2%
+   </td>
+  </tr>
+  <tr>
+   <td>GSM-8K (5-shot, strict-match)
+   </td>
+   <td>75.21
+   </td>
+   <td>75.89
+   </td>
+   <td>100.9%
+   </td>
+  </tr>
+  <tr>
+   <td>Hellaswag (10-shot)
+   </td>
+   <td>78.81
+   </td>
+   <td>78.69
+   </td>
+   <td>99.8%
+   </td>
+  </tr>
+  <tr>
+   <td>Winogrande (5-shot)
+   </td>
+   <td>76.48
+   </td>
+   <td>76.01
+   </td>
+   <td>98.2%
+   </td>
+  </tr>
+  <tr>
+   <td>TruthfulQA (0-shot)
+   </td>
+   <td>52.49
+   </td>
+   <td>52.60
+   </td>
+   <td>100.2%
+   </td>
+  </tr>
+  <tr>
+   <td><strong>Average</strong>
+   </td>
+   <td><strong>68.69</strong>
+   </td>
+   <td><strong>68.54</strong>
+   </td>
+   <td><strong>99.8%</strong>
+   </td>
+  </tr>
+</table>