Create README.md

README.md

@@ -0,0 +1,189 @@
+---
+tags:
+- fp8
+- vllm
+license: other
+license_name: deepseek-license
+license_link: https://github.com/deepseek-ai/DeepSeek-Coder-V2/blob/main/LICENSE-MODEL
+---
+
+# DeepSeek-Coder-V2-Instruct-FP8
+
+## Model Overview
+- **Model Architecture:** DeepSeek-Coder-V2-Instruct
+  - **Input:** Text
+  - **Output:** Text
+- **Model Optimizations:**
+  - **Weight quantization:** FP8
+  - **Activation quantization:** FP8
+- **Intended Use Cases:** Intended for commercial and research use in English. Similarly to [Meta-Llama-3-7B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-7B-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.
+- **Release Date:** 7/22/2024
+- **Version:** 1.0
+- **License(s):** [deepseek-license](https://github.com/deepseek-ai/DeepSeek-Coder-V2/blob/main/LICENSE-MODEL)
+- **Model Developers:** Neural Magic
+
+Quantized version of [DeepSeek-Coder-V2-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct).
+<!-- It achieves an average score of 73.19 on the [OpenLLM](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard) benchmark (version 1), whereas the unquantized model achieves 73.48. -->
+It achieves an average score of 88.98 on the [HumanEval+](https://github.com/openai/human-eval?tab=readme-ov-file) benchmark, whereas the unquantized model achieves 87.63.
+
+### Model Optimizations
+
+This model was obtained by quantizing the weights and activations of [DeepSeek-Coder-V2-Instruct](https://huggingface.co/deepseek-ai/DeepSeek-Coder-V2-Instruct) to FP8 data type, ready for inference with vLLM >= 0.5.2.
+This optimization reduces the number of bits per parameter from 16 to 8, reducing the disk size and GPU memory requirements by approximately 50%. In particular, this model can now be loaded and evaluated with only 4xH100 GPUs, as opposed to 8.
+
+Only the weights and activations of the linear operators within transformers blocks are quantized. Symmetric per-tensor quantization is applied, in which a single linear scaling maps the FP8 representations of the quantized weights and activations.
+[AutoFP8](https://github.com/neuralmagic/AutoFP8) is used for quantization with 512 sequences of UltraChat.
+
+## 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/DeepSeek-Coder-V2-Instruct-FP8"
+
+sampling_params = SamplingParams(temperature=0.6, top_p=0.9, max_tokens=256)
+
+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, add_generation_prompt=True)
+
+llm = LLM(model=model_id, trust_remote_code=True, max_model_len=4096)
+
+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.
+
+## Creation
+
+This model was created by applying [AutoFP8 with calibration samples from ultrachat](https://github.com/neuralmagic/AutoFP8/blob/147fa4d9e1a90ef8a93f96fc7d9c33056ddc017a/example_dataset.py) with expert gates kept at original precision, as presented in the code snipet below.
+Notably, a custom device map had to be used, as the model was being incorrectly loaded otherwise.
+Although AutoFP8 was used for this particular model, Neural Magic is transitioning to using [llm-compressor](https://github.com/vllm-project/llm-compressor) which supports several quantization schemes and models not supported by AutoFP8.
+
+```python
+from datasets import load_dataset
+from transformers import AutoTokenizer
+
+from auto_fp8 import AutoFP8ForCausalLM, BaseQuantizeConfig
+
+pretrained_model_dir = "deepseek-ai/DeepSeek-Coder-V2-Instruct"
+quantized_model_dir = "DeepSeek-Coder-V2-Instruct-FP8"
+
+tokenizer = AutoTokenizer.from_pretrained(pretrained_model_dir, use_fast=True, model_max_length=4096)
+tokenizer.pad_token = tokenizer.eos_token
+
+ds = load_dataset("mgoin/ultrachat_2k", split="train_sft").select(range(512))
+examples = [tokenizer.apply_chat_template(batch["messages"], tokenize=False) for batch in ds]
+examples = tokenizer(examples, padding=True, truncation=True, return_tensors="pt").to("cuda")
+
+quantize_config = BaseQuantizeConfig(
+    quant_method="fp8",
+    activation_scheme="static"
+    ignore_patterns=["re:.*lm_head"],
+)
+
+device_map = {
+    "model.embed_tokens": 0,
+    "model.layers.0": 0,
+}
+for i in range(1, 60):
+    device_map[f"model.layers.{i}"] = i//8
+
+device_map["model.norm"] = 7
+device_map["lm_head"] = 7
+
+model = AutoFP8ForCausalLM.from_pretrained(
+    pretrained_model_dir, quantize_config=quantize_config, device_map = device_map
+)
+model.quantize(examples)
+model.save_quantized(quantized_model_dir)
+```
+
+## Evaluation
+
+The model was evaluated on the [HumanEval+](https://github.com/openai/human-eval?tab=readme-ov-file) benchmark with the [Neural Magic fork](https://github.com/neuralmagic/evalplus) of the [EvalPlus implementation of HumanEval+](https://github.com/evalplus/evalplus) and the [vLLM](https://docs.vllm.ai/en/stable/) engine, using the following command:
+```
+python codegen/generate.py --model neuralmagic/DeepSeek-Coder-V2-Instruct-FP8 --temperature 0.2 --n_samples 50 --resume --root ~ --dataset humaneval
+python evalplus/sanitize.py ~/humaneval/neuralmagic--DeepSeek-Coder-V2-Instruct-FP8_vllm_temp_0.2
+evalplus.evaluate --dataset humaneval --samples ~/humaneval/neuralmagic--DeepSeek-Coder-V2-Instruct-FP8_vllm_temp_0.2-sanitized
+```
+
+### Accuracy
+
+#### HumanEval+ evaluation scores
+<table>
+  <tr>
+   <td><strong>Benchmark</strong>
+   </td>
+   <td><strong>DeepSeek-Coder-V2-Instruct</strong>
+   </td>
+   <td><strong>DeepSeek-Coder-V2-Instruct-FP8(this model)</strong>
+   </td>
+   <td><strong>Recovery</strong>
+   </td>
+  </tr>
+  <tr>
+   <td>base pass@1
+   </td>
+   <td>88.2
+   </td>
+   <td>87.6
+   </td>
+   <td>99.32%
+   </td>
+  </tr>
+  <tr>
+   <td>base pass@10
+   </td>
+   <td>92.3
+   </td>
+   <td>94.7
+   </td>
+   <td>102.60%
+   </td>
+  </tr>
+  <tr>
+   <td>base+extra pass@1
+   </td>
+   <td>83.3
+   </td>
+   <td>83.2
+   </td>
+   <td>99.88%
+   </td>
+  </tr>
+  <tr>
+   <td>base+extra pass@10
+   </td>
+   <td>86.7
+   </td>
+   <td>90.4
+   </td>
+   <td>104.27%
+   </td>
+  </tr>
+  <tr>
+   <td><strong>Average</strong>
+   </td>
+   <td><strong>87.63</strong>
+   </td>
+   <td><strong>88.98</strong>
+   </td>
+   <td><strong>101.5%</strong>
+   </td>
+  </tr>
+</table>