File size: 3,848 Bytes
74aa515 ac158c1 ec77984 ac158c1 ec77984 ac158c1 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 |
---
base_model:
- mistralai/Mistral-Small-3.1-24B-Instruct-2503
---
## Evaluation
Server command:
```
vllm serve nm-testing/Mistral-Small-3.1-24B-Instruct-2503-FP8-dynamic
```
Eval command:
```
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("==========================================")
``` |