Use llama-1b for faster and more accessible examples

examples/quantization_kv_cache/llama3.2_small_fp8_kv_example.py

@@ -0,0 +1,95 @@
+from datasets import load_dataset
+from transformers import AutoModelForCausalLM, AutoTokenizer
+
+from llmcompressor.transformers import oneshot
+
+# Select model and load it.
+MODEL_ID = "meta-llama/Llama-3.2-1B-Instruct"
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    device_map="auto",
+    torch_dtype="auto",
+)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+
+# Select calibration dataset.
+DATASET_ID = "HuggingFaceH4/ultrachat_200k"
+DATASET_SPLIT = "train_sft"
+
+# Select number of samples. 512 samples is a good place to start.
+# Increasing the number of samples can improve accuracy.
+NUM_CALIBRATION_SAMPLES = 512
+MAX_SEQUENCE_LENGTH = 2048
+
+# Load dataset and preprocess.
+ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
+ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES))
+
+
+def process_and_tokenize(example):
+    text = tokenizer.apply_chat_template(example["messages"], tokenize=False)
+    return tokenizer(
+        text,
+        padding=False,
+        max_length=MAX_SEQUENCE_LENGTH,
+        truncation=True,
+        add_special_tokens=False,
+    )
+
+
+ds = ds.map(process_and_tokenize, remove_columns=ds.column_names)
+
+# Configure the quantization algorithm and scheme.
+# In this case, we:
+#   * quantize the weights to fp8 with per-tensor scales
+#   * quantize the activations to fp8 with per-tensor scales
+#   * quantize the kv cache to fp8 with per-tensor scales
+recipe = """
+quant_stage:
+    quant_modifiers:
+        QuantizationModifier:
+            ignore: ["lm_head"]
+            config_groups:
+                group_0:
+                    weights:
+                        num_bits: 8
+                        type: float
+                        strategy: tensor
+                        dynamic: false
+                        symmetric: true
+                    input_activations:
+                        num_bits: 8
+                        type: float
+                        strategy: tensor
+                        dynamic: false
+                        symmetric: true
+                    targets: ["Linear"]
+            kv_cache_scheme:
+                num_bits: 8
+                type: float
+                strategy: tensor
+                dynamic: false
+                symmetric: true
+"""
+
+# Apply algorithms.
+oneshot(
+    model=model,
+    dataset=ds,
+    recipe=recipe,
+    max_seq_length=MAX_SEQUENCE_LENGTH,
+    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
+)
+
+# Confirm generations of the quantized model look sane.
+print("\n\n")
+print("========== SAMPLE GENERATION ==============")
+input_ids = tokenizer("Hello my name is", return_tensors="pt").input_ids.to("cuda")
+output = model.generate(input_ids, max_new_tokens=100)
+print(tokenizer.decode(output[0]))
+print("==========================================\n\n")
+
+# Save to disk compressed.
+SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-KV"
+model.save_pretrained(SAVE_DIR, save_compressed=True)
+tokenizer.save_pretrained(SAVE_DIR)

examples/quantization_w4a16/llama3.2_small_example.py

@@ -0,0 +1,80 @@
+from datasets import load_dataset
+from transformers import AutoTokenizer
+
+from llmcompressor.modifiers.quantization import GPTQModifier
+from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot
+
+# Select model and load it.
+MODEL_ID = "meta-llama/Llama-3.2-1B-Instruct"
+
+model = SparseAutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    device_map="auto",
+    torch_dtype="auto",
+)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+
+# Select calibration dataset.
+DATASET_ID = "HuggingFaceH4/ultrachat_200k"
+DATASET_SPLIT = "train_sft"
+
+# Select number of samples. 512 samples is a good place to start.
+# Increasing the number of samples can improve accuracy.
+NUM_CALIBRATION_SAMPLES = 512
+MAX_SEQUENCE_LENGTH = 2048
+
+# Load dataset and preprocess.
+ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
+ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES))
+
+
+def preprocess(example):
+    return {
+        "text": tokenizer.apply_chat_template(
+            example["messages"],
+            tokenize=False,
+        )
+    }
+
+
+ds = ds.map(preprocess)
+
+
+# Tokenize inputs.
+def tokenize(sample):
+    return tokenizer(
+        sample["text"],
+        padding=False,
+        max_length=MAX_SEQUENCE_LENGTH,
+        truncation=True,
+        add_special_tokens=False,
+    )
+
+
+ds = ds.map(tokenize, remove_columns=ds.column_names)
+
+# Configure the quantization algorithm to run.
+#   * quantize the weights to 4 bit with GPTQ with a group size 128
+recipe = GPTQModifier(targets="Linear", scheme="W4A16", ignore=["lm_head"])
+
+# Apply algorithms.
+oneshot(
+    model=model,
+    dataset=ds,
+    recipe=recipe,
+    max_seq_length=MAX_SEQUENCE_LENGTH,
+    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
+)
+
+# Confirm generations of the quantized model look sane.
+print("\n\n")
+print("========== SAMPLE GENERATION ==============")
+input_ids = tokenizer("Hello my name is", return_tensors="pt").input_ids.to("cuda")
+output = model.generate(input_ids, max_new_tokens=100)
+print(tokenizer.decode(output[0]))
+print("==========================================\n\n")
+
+# Save to disk compressed.
+SAVE_DIR = MODEL_ID.split("/")[1] + "-W4A16-G128"
+model.save_pretrained(SAVE_DIR, save_compressed=True)
+tokenizer.save_pretrained(SAVE_DIR)

examples/quantization_w8a8_fp8/llama3.2_small_example.py

@@ -0,0 +1,35 @@
+from transformers import AutoTokenizer
+
+from llmcompressor.modifiers.quantization import QuantizationModifier
+from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot
+
+MODEL_ID = "meta-llama/Llama-3.2-1B-Instruct"
+
+# Load model.
+model = SparseAutoModelForCausalLM.from_pretrained(
+    MODEL_ID, device_map="auto", torch_dtype="auto"
+)
+tokenizer = AutoTokenizer.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=["lm_head"]
+)
+
+# Apply quantization.
+oneshot(model=model, recipe=recipe)
+
+# Confirm generations of the quantized model look sane.
+print("========== SAMPLE GENERATION ==============")
+input_ids = tokenizer("Hello my name is", return_tensors="pt").input_ids.to("cuda")
+output = model.generate(input_ids, max_new_tokens=20)
+print(tokenizer.decode(output[0]))
+print("==========================================")
+
+# Save to disk in compressed-tensors format.
+SAVE_DIR = MODEL_ID.split("/")[1] + "-FP8-Dynamic"
+model.save_pretrained(SAVE_DIR)
+tokenizer.save_pretrained(SAVE_DIR)

examples/quantization_w8a8_int8/llama3.2_small_example.py

@@ -0,0 +1,85 @@
+from datasets import load_dataset
+from transformers import AutoTokenizer
+
+from llmcompressor.modifiers.quantization import GPTQModifier
+from llmcompressor.modifiers.smoothquant import SmoothQuantModifier
+from llmcompressor.transformers import SparseAutoModelForCausalLM, oneshot
+
+# Select model and load it.
+MODEL_ID = "meta-llama/Llama-3.2-1B-Instruct"
+model = SparseAutoModelForCausalLM.from_pretrained(
+    MODEL_ID,
+    device_map="auto",
+    torch_dtype="auto",
+)
+tokenizer = AutoTokenizer.from_pretrained(MODEL_ID)
+
+# Select calibration dataset.
+DATASET_ID = "HuggingFaceH4/ultrachat_200k"
+DATASET_SPLIT = "train_sft"
+
+# Select number of samples. 512 samples is a good place to start.
+# Increasing the number of samples can improve accuracy.
+NUM_CALIBRATION_SAMPLES = 512
+MAX_SEQUENCE_LENGTH = 2048
+
+# Load dataset and preprocess.
+ds = load_dataset(DATASET_ID, split=DATASET_SPLIT)
+ds = ds.shuffle(seed=42).select(range(NUM_CALIBRATION_SAMPLES))
+
+
+def preprocess(example):
+    return {
+        "text": tokenizer.apply_chat_template(
+            example["messages"],
+            tokenize=False,
+        )
+    }
+
+
+ds = ds.map(preprocess)
+
+
+# Tokenize inputs.
+def tokenize(sample):
+    return tokenizer(
+        sample["text"],
+        padding=False,
+        max_length=MAX_SEQUENCE_LENGTH,
+        truncation=True,
+        add_special_tokens=False,
+    )
+
+
+ds = ds.map(tokenize, remove_columns=ds.column_names)
+
+# Configure algorithms. In this case, we:
+#   * apply SmoothQuant to make the activations easier to quantize
+#   * quantize the weights to int8 with GPTQ (static per channel)
+#   * quantize the activations to int8 (dynamic per token)
+recipe = [
+    SmoothQuantModifier(smoothing_strength=0.8),
+    GPTQModifier(targets="Linear", scheme="W8A8", ignore=["lm_head"]),
+]
+
+# Apply algorithms.
+oneshot(
+    model=model,
+    dataset=ds,
+    recipe=recipe,
+    max_seq_length=MAX_SEQUENCE_LENGTH,
+    num_calibration_samples=NUM_CALIBRATION_SAMPLES,
+)
+
+# Confirm generations of the quantized model look sane.
+print("\n\n")
+print("========== SAMPLE GENERATION ==============")
+input_ids = tokenizer("Hello my name is", return_tensors="pt").input_ids.to("cuda")
+output = model.generate(input_ids, max_new_tokens=100)
+print(tokenizer.decode(output[0]))
+print("==========================================\n\n")
+
+# Save to disk compressed.
+SAVE_DIR = MODEL_ID.split("/")[1] + "-W8A8-Dynamic-Per-Token"
+model.save_pretrained(SAVE_DIR, save_compressed=True)
+tokenizer.save_pretrained(SAVE_DIR)