Update README.md

README.md

@@ -1,4 +1,69 @@
 ---
 base_model:
 - mistralai/Mistral-Small-3.1-24B-Instruct-2503
----
+---
+
+## Evaluation
+
+Server:
+```
+vllm serve nm-testing/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic
+```
+
+Eval:
+```
+python -m eval.run eval_vllm --model_name nm-testing/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic --url http://0.0.0.0:9000 --output_dir output/ --eval_name "chartqa"
+Waiting for VLLM server to come online at http://0.0.0.0:9000/health ...
+Timeout is 120s
+Waiting for server (0s) ...
+Server is up!
+Loading lmms-lab/ChartQA [test]: 100%|██████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2500/2500 [00:11<00:00, 210.68it/s]
+Querying model: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2500/2500 [06:53<00:00,  6.05it/s]
+100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2500/2500 [00:00<00:00, 22477.08it/s]
+================================================================================
+Metrics:
+{
+    "explicit_prompt_relaxed_correctness": 0.8136,
+    "anywhere_in_answer_relaxed_correctness": 0.8144
+}
+================================================================================
+```
+
+## Creation
+
+```python
+from transformers import AutoProcessor, AutoModelForImageTextToText
+
+from llmcompressor.modifiers.quantization import QuantizationModifier
+from llmcompressor.transformers import oneshot
+
+MODEL_ID = "mistralai/Mistral-Small-3.1-24B-Instruct-2503"
+
+# Load model.
+model = AutoModelForImageTextToText.from_pretrained(
+    MODEL_ID, device_map="auto", torch_dtype="auto"
+)
+processor = AutoProcessor.from_pretrained(MODEL_ID)
+
+# Configure the quantization algorithm and scheme.
+# In this case, we:
+#   * quantize the weights to fp8 with per channel via ptq
+#   * quantize the activations to fp8 with dynamic per token
+recipe = QuantizationModifier(
+    targets="Linear",
+    scheme="FP8_DYNAMIC",
+    ignore=["re:.*lm_head", "re:multi_modal_projector.*", "re:vision_tower.*"],
+)
+
+# Apply quantization and save to disk in compressed-tensors format.
+SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-dynamic"
+oneshot(model=model, recipe=recipe, output_dir=SAVE_DIR)
+processor.save_pretrained(SAVE_DIR)
+
+# Confirm generations of the quantized model look sane.
+print("========== SAMPLE GENERATION ==============")
+input_ids = processor(text="Hello my name is", return_tensors="pt").input_ids.to("cuda")
+output = model.generate(input_ids, max_new_tokens=20)
+print(processor.decode(output[0]))
+print("==========================================")
+```