初始化项目，由ModelHub XC社区提供模型
Model: RedHatAI/gemma-3-1b-it-quantized.w8a8 Source: Original Platform
This commit is contained in:
ModelHub XC
37
.gitattributes
vendored
Normal file
37
.gitattributes
vendored
Normal file
@@ -0,0 +1,37 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
236
README.md
Normal file
236
README.md
Normal file
@@ -0,0 +1,236 @@
|
||||
---
|
||||
tags:
|
||||
- vllm
|
||||
- vision
|
||||
- w8a8
|
||||
license: gemma
|
||||
base_model: google/gemma-3-1b-it
|
||||
library_name: transformers
|
||||
---
|
||||
|
||||
# gemma-3-1b-it-quantized.w8a8
|
||||
|
||||
## Model Overview
|
||||
- **Model Architecture:** google/gemma-3-1b-it
|
||||
- **Input:** Vision-Text
|
||||
- **Output:** Text
|
||||
- **Model Optimizations:**
|
||||
- **Weight quantization:** INT8
|
||||
- **Activation quantization:** INT8
|
||||
- **Release Date:** 6/4/2025
|
||||
- **Version:** 1.0
|
||||
- **Model Developers:** RedHatAI
|
||||
|
||||
Quantized version of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it).
|
||||
|
||||
### Model Optimizations
|
||||
|
||||
This model was obtained by quantizing the weights of [google/gemma-3-1b-it](https://huggingface.co/google/gemma-3-1b-it) to INT8 data type, ready for inference with vLLM >= 0.8.0.
|
||||
|
||||
## 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.assets.image import ImageAsset
|
||||
from vllm import LLM, SamplingParams
|
||||
|
||||
# prepare model
|
||||
llm = LLM(
|
||||
model="RedHatAI/gemma-3-1b-it-quantized.w8a8",
|
||||
trust_remote_code=True,
|
||||
max_model_len=4096,
|
||||
max_num_seqs=2,
|
||||
)
|
||||
|
||||
# prepare inputs
|
||||
question = "What is the content of this image?"
|
||||
inputs = {
|
||||
"prompt": f"<|user|>\n<|image_1|>\n{question}<|end|>\n<|assistant|>\n",
|
||||
"multi_modal_data": {
|
||||
"image": ImageAsset("cherry_blossom").pil_image.convert("RGB")
|
||||
},
|
||||
}
|
||||
|
||||
# generate response
|
||||
print("========== SAMPLE GENERATION ==============")
|
||||
outputs = llm.generate(inputs, SamplingParams(temperature=0.2, max_tokens=64))
|
||||
print(f"PROMPT : {outputs[0].prompt}")
|
||||
print(f"RESPONSE: {outputs[0].outputs[0].text}")
|
||||
print("==========================================")
|
||||
```
|
||||
|
||||
vLLM also supports OpenAI-compatible serving. See the [documentation](https://docs.vllm.ai/en/latest/) for more details.
|
||||
|
||||
## Creation
|
||||
|
||||
This model was created with [llm-compressor](https://github.com/vllm-project/llm-compressor) by running the code snippet below:
|
||||
|
||||
<details>
|
||||
<summary>Model Creation Code</summary>
|
||||
|
||||
```python
|
||||
import base64
|
||||
from io import BytesIO
|
||||
import torch
|
||||
from datasets import load_dataset
|
||||
from transformers import AutoProcessor, Gemma3ForCausalLM
|
||||
from llmcompressor.modifiers.quantization import GPTQModifier
|
||||
from llmcompressor.transformers import oneshot
|
||||
|
||||
|
||||
# Load model.
|
||||
model_id = "google/gemma-3-1b-it"
|
||||
model = Gemma3ForCausalLM.from_pretrained(
|
||||
model_id,
|
||||
device_map="auto",
|
||||
torch_dtype="auto",
|
||||
)
|
||||
processor = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
|
||||
|
||||
# Oneshot arguments
|
||||
DATASET_ID = "neuralmagic/calibration"
|
||||
DATASET_SPLIT = {"LLM": "train[:512]"}
|
||||
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)
|
||||
|
||||
dampening_frac=0.01
|
||||
|
||||
def data_collator(batch):
|
||||
assert len(batch) == 1, "Only batch size of 1 is supported for calibration"
|
||||
item = batch[0]
|
||||
collated = {}
|
||||
import torch
|
||||
|
||||
|
||||
for key, value in item.items():
|
||||
if isinstance(value, torch.Tensor):
|
||||
collated[key] = value.unsqueeze(0)
|
||||
elif isinstance(value, list) and isinstance(value[0][0], int):
|
||||
# Handle tokenized inputs like input_ids, attention_mask
|
||||
collated[key] = torch.tensor(value)
|
||||
elif isinstance(value, list) and isinstance(value[0][0], float):
|
||||
# Handle possible float sequences
|
||||
collated[key] = torch.tensor(value)
|
||||
elif isinstance(value, list) and isinstance(value[0][0], torch.Tensor):
|
||||
# Handle batched image data (e.g., pixel_values as [C, H, W])
|
||||
collated[key] = torch.stack(value) # -> [1, C, H, W]
|
||||
elif isinstance(value, torch.Tensor):
|
||||
collated[key] = value
|
||||
else:
|
||||
print(f"[WARN] Unrecognized type in collator for key={key}, type={type(value)}")
|
||||
|
||||
return collated
|
||||
|
||||
|
||||
|
||||
# Recipe
|
||||
recipe = [
|
||||
GPTQModifier(
|
||||
targets="Linear",
|
||||
ignore=["re:.*lm_head.*", "re:.*embed_tokens.*", "re:vision_tower.*", "re:multi_modal_projector.*"],
|
||||
sequential_update=True,
|
||||
sequential_targets=["Gemma3DecoderLayer"],
|
||||
dampening_frac=dampening_frac,
|
||||
)
|
||||
]
|
||||
|
||||
SAVE_DIR=f"{model_id.split('/')[1]}-quantized.w8a8"
|
||||
|
||||
# Perform oneshot
|
||||
oneshot(
|
||||
model=model,
|
||||
tokenizer=model_id,
|
||||
dataset=ds,
|
||||
recipe=recipe,
|
||||
max_seq_length=MAX_SEQUENCE_LENGTH,
|
||||
num_calibration_samples=NUM_CALIBRATION_SAMPLES,
|
||||
trust_remote_code_model=True,
|
||||
data_collator=data_collator,
|
||||
output_dir=SAVE_DIR
|
||||
)
|
||||
```
|
||||
</details>
|
||||
|
||||
## Evaluation
|
||||
|
||||
The model was evaluated using [lm_evaluation_harness](https://github.com/neuralmagic/lm-evaluation-harness) for OpenLLM v1 text benchmark. The evaluations were conducted using the following commands:
|
||||
|
||||
<details>
|
||||
<summary>Evaluation Commands</summary>
|
||||
|
||||
### OpenLLM v1
|
||||
```
|
||||
lm_eval \
|
||||
--model vllm \
|
||||
--model_args pretrained="<model_name>",dtype=auto,add_bos_token=True,max_model_len=4096,tensor_parallel_size=<n>,gpu_memory_utilization=0.8,enable_chunked_prefill=True,trust_remote_code=True,enforce_eager=True \
|
||||
--tasks openllm \
|
||||
--batch_size auto
|
||||
```
|
||||
</details>
|
||||
|
||||
|
||||
### Accuracy
|
||||
|
||||
<table>
|
||||
<thead>
|
||||
<tr>
|
||||
<th>Category</th>
|
||||
<th>Metric</th>
|
||||
<th>google/gemma-3-1b-it</th>
|
||||
<th>RedHatAI/gemma-3-1b-it-quantized.w8a8</th>
|
||||
<th>Recovery (%)</th>
|
||||
</tr>
|
||||
</thead>
|
||||
<tbody>
|
||||
<tr>
|
||||
<td rowspan="7"><b>OpenLLM V1</b></td>
|
||||
<td>ARC Challenge</td>
|
||||
<td>36.86%</td>
|
||||
<td>36.43%</td>
|
||||
<td>98.84%<td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>GSM8K</td>
|
||||
<td>25.17%</td>
|
||||
<td>24.87%</td>
|
||||
<td>98.80%</%</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Hellaswag</td>
|
||||
<td>56.03%</td>
|
||||
<td>55.62%</td>
|
||||
<td>99.25%</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>MMLU</td>
|
||||
<td>39.99%</td>
|
||||
<td>39.35%</td>
|
||||
<td>98.38%</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Truthfulqa (mc2)</td>
|
||||
<td>38.54%</td>
|
||||
<td>38.22%</td>
|
||||
<td>99.17%</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td>Winogrande</td>
|
||||
<td>58.88%</td>
|
||||
<td>58.96%</td>
|
||||
<td>100.13%</td>
|
||||
</tr>
|
||||
<tr>
|
||||
<td><b>Average Score</b></td>
|
||||
<td><b>42.58%</b></td>
|
||||
<td><b>42.24%</b></td>
|
||||
<td><b>99.20%</b></td>
|
||||
</tr>
|
||||
</tbody>
|
||||
</table>
|
||||
3
added_tokens.json
Normal file
3
added_tokens.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"<image_soft_token>": 262144
|
||||
}
|
||||
3
config.json
Normal file
3
config.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:eec4001992e7b04e5d27e6d6d72d7a015ba2df3187e1883aae7e2faa885d4a12
|
||||
size 1945
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
13
generation_config.json
Normal file
13
generation_config.json
Normal file
@@ -0,0 +1,13 @@
|
||||
{
|
||||
"bos_token_id": 2,
|
||||
"cache_implementation": "hybrid",
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
1,
|
||||
106
|
||||
],
|
||||
"pad_token_id": 0,
|
||||
"top_k": 64,
|
||||
"top_p": 0.95,
|
||||
"transformers_version": "4.51.3"
|
||||
}
|
||||
3
model.safetensors
Normal file
3
model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8cc0227db20ae63a50c9c1edd6dda3fa0b92a4efca9ad9ca7dbb396b35cae5c1
|
||||
size 1906969248
|
||||
12
recipe.yaml
Normal file
12
recipe.yaml
Normal file
@@ -0,0 +1,12 @@
|
||||
quant_stage:
|
||||
quant_modifiers:
|
||||
GPTQModifier:
|
||||
dampening_frac: 0.01
|
||||
ignore: ['re:.*lm_head.*', 're:.*embed_tokens.*', 're:vision_tower.*', 're:multi_modal_projector.*']
|
||||
sequential_update: true
|
||||
config_groups:
|
||||
group_0:
|
||||
targets: [Linear]
|
||||
weights: {num_bits: 8, type: int, symmetric: true, strategy: channel, observer: mse}
|
||||
input_activations: {num_bits: 8, type: int, symmetric: true, strategy: token, dynamic: true,
|
||||
observer: memoryless}
|
||||
33
special_tokens_map.json
Normal file
33
special_tokens_map.json
Normal file
@@ -0,0 +1,33 @@
|
||||
{
|
||||
"boi_token": "<start_of_image>",
|
||||
"bos_token": {
|
||||
"content": "<bos>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eoi_token": "<end_of_image>",
|
||||
"eos_token": {
|
||||
"content": "<eos>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"image_token": "<image_soft_token>",
|
||||
"pad_token": {
|
||||
"content": "<pad>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
|
||||
size 33384568
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
|
||||
size 4689074
|
||||
3
tokenizer_config.json
Normal file
3
tokenizer_config.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bfe25c2735e395407beb78456ea9a6984a1f00d8c16fa04a8b75f2a614cf53e1
|
||||
size 1156999
|
||||
Reference in New Issue
Block a user