Update README.md

README.md

@@ -43,6 +43,96 @@ This optimization reduces the number of bits used to represent weights and activ
 Weight quantization also reduces disk size requirements by approximately 50%.
 
 
+## Creation
+<details>
+  This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below.
+
+  ```bash
+python quantize.py --mdoel_path mistralai/Devstral-Small-2507 --calib_size 512 --dampening_frac 0.05
+```
+
+  ```python
+import argparse
+import os
+from datasets import load_dataset
+from transformers import AutoModelForCausalLM
+from llmcompressor.modifiers.quantization import GPTQModifier
+from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
+from llmcompressor.transformers import oneshot
+from mistral_common.tokens.tokenizers.mistral import MistralTokenizer
+from mistral_common.protocol.instruct.request import ChatCompletionRequest
+from mistral_common.protocol.instruct.messages import (
+    SystemMessage, UserMessage
+)
+
+def load_system_prompt(repo_id: str, filename: str) -> str:
+    file_path = os.path.join(repo_id, filename)
+    with open(file_path, "r") as file:
+        system_prompt = file.read()
+    return system_prompt
+
+parser = argparse.ArgumentParser()
+parser.add_argument('--model_path', type=str)
+parser.add_argument('--calib_size', type=int, default=256)
+parser.add_argument('--dampening_frac', type=float, default=0.1)
+args = parser.parse_args()
+
+model = AutoModelForCausalLM.from_pretrained(
+    args.model_path,
+    device_map="auto",
+    torch_dtype="auto",
+    use_cache=False,
+    trust_remote_code=True,
+)
+
+ds = load_dataset("garage-bAInd/Open-Platypus", split="train")
+ds = ds.shuffle(seed=42).select(range(args.calib_size))
+
+SYSTEM_PROMPT = load_system_prompt(args.model_path, "SYSTEM_PROMPT.txt")
+tokenizer = MistralTokenizer.from_hf_hub("mistralai/Devstral-Small-2507")
+
+def tokenize(sample):
+    tmp = tokenizer.encode_chat_completion(
+        ChatCompletionRequest(
+            messages=[
+                SystemMessage(content=SYSTEM_PROMPT),
+                UserMessage(content=sample['instruction']),
+            ],
+        )
+    )
+    return {'input_ids': tmp.tokens}
+
+ds = ds.map(tokenize, remove_columns=ds.column_names)
+
+recipe = [
+    SmoothQuantModifier(
+      smoothing_strength=0.8,
+      mappings=[
+          [["re:.*q_proj", "re:.*k_proj", "re:.*v_proj"], "re:.*input_layernorm"],
+          [["re:.*gate_proj", "re:.*up_proj"], "re:.*post_attention_layernorm"],
+          [["re:.*down_proj"], "re:.*up_proj"],
+      ],
+    ),
+    GPTQModifier(
+        targets=["Linear"],
+        ignore=["lm_head"],
+        scheme="W8A8",
+        dampening_frac=args.dampening_frac,
+    )
+]
+oneshot(
+    model=model,
+    dataset=ds,
+    recipe=recipe,
+    num_calibration_samples=args.calib_size,
+    max_seq_length=8192,
+)
+
+save_path = args.model_path + "-quantized.w8a8"
+model.save_pretrained(save_path)
+```
+</details>
+
 ## Deployment
 
 This model can be deployed efficiently using the [vLLM](https://docs.vllm.ai/en/latest/) backend, as shown in the example below.