Skip to content

feat(florence2): add native Florence-2 image-to-text support #1258

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
ssss141414 wants to merge 1 commit into
base: main
Choose a base branch
from
Draft

feat(florence2): add native Florence-2 image-to-text support #1258

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 2 additions & 0 deletions docs/reference/index.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,6 +68,7 @@ stages based on the target device and precision.
| `dtype` | `str \| null` | Data type (e.g., `float32`, `int64`). |
| `shape` | `list[int \| str] \| null` | Tensor shape (e.g., `[1, 3, 224, 224]`). String entries declare symbolic dynamic axes and use size `1` for dummy inputs. |
| `value_range` | `[float, float] \| null` | Min/max for dummy tensor generation. |
| `dummy_value_runs` | `list[[int, int \| float]] \| null` | Run-length encoded semantic dummy values as `[count, value]` pairs. Counts must exactly fill the concrete tensor shape. |

---

Expand Down Expand Up @@ -137,6 +138,7 @@ Set to `null` (default) to skip evaluation.
| `model_id` | `str \| null` | `null` | HuggingFace model ID for config resolution. |
| `model_path` | `str \| dict[str, str] \| null` | `null` | Path to .onnx file, or a `{role: path}` dict for composite models. |
| `task` | `str \| null` | `null` | Task type. |
| `prompt` | `str \| null` | `null` | Optional text prompt passed with each image for prompt-conditioned image-to-text models. |
| `device` | `str` | `"auto"` | Inference device. |
| `precision` | `str` | `"auto"` | Precision (`fp32`, `fp16`, `w8a16`, etc.). |
| `ep` | `str \| null` | `null` | EP override. |
Expand Down
299 changes: 299 additions & 0 deletions examples/recipes/microsoft_Florence-2-base/cpu/cpu/image-to-text_fp16_config_decoder.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,299 @@
{
"precision": "fp16",
"export": {
"opset_version": 17,
"batch_size": 1,
"export_params": true,
"do_constant_folding": true,
"verbose": false,
"dynamo": false,
"enable_hierarchy_tags": true,
"clean_onnx": false,
"hierarchy_tag_format": "full",
"input_tensors": [
{
"name": "decoder_input_ids",
"dtype": "int32",
"shape": [
1,
1
],
"value_range": [
0,
51289
]
},
{
"name": "encoder_hidden_states",
"dtype": "float32",
"shape": [
1,
585,
768
],
"value_range": [
0,
1
]
},
{
"name": "decoder_attention_mask",
"dtype": "int64",
"shape": [
1,
1024
]
},
{
"name": "cache_position",
"dtype": "int64",
"shape": [
1
]
},
{
"name": "past_0_key",
"dtype": "float32",
"shape": [
1,
12,
1024,
64
],
"value_range": [
0,
1
]
},
{
"name": "past_0_value",
"dtype": "float32",
"shape": [
1,
12,
1024,
64
],
"value_range": [
0,
1
]
},
{
"name": "past_1_key",
"dtype": "float32",
"shape": [
1,
12,
1024,
64
],
"value_range": [
0,
1
]
},
{
"name": "past_1_value",
"dtype": "float32",
"shape": [
1,
12,
1024,
64
],
"value_range": [
0,
1
]
},
{
"name": "past_2_key",
"dtype": "float32",
"shape": [
1,
12,
1024,
64
],
"value_range": [
0,
1
]
},
{
"name": "past_2_value",
"dtype": "float32",
"shape": [
1,
12,
1024,
64
],
"value_range": [
0,
1
]
},
{
"name": "past_3_key",
"dtype": "float32",
"shape": [
1,
12,
1024,
64
],
"value_range": [
0,
1
]
},
{
"name": "past_3_value",
"dtype": "float32",
"shape": [
1,
12,
1024,
64
],
"value_range": [
0,
1
]
},
{
"name": "past_4_key",
"dtype": "float32",
"shape": [
1,
12,
1024,
64
],
"value_range": [
0,
1
]
},
{
"name": "past_4_value",
"dtype": "float32",
"shape": [
1,
12,
1024,
64
],
"value_range": [
0,
1
]
},
{
"name": "past_5_key",
"dtype": "float32",
"shape": [
1,
12,
1024,
64
],
"value_range": [
0,
1
]
},
{
"name": "past_5_value",
"dtype": "float32",
"shape": [
1,
12,
1024,
64
],
"value_range": [
0,
1
]
}
],
"output_tensors": [
{
"name": "logits"
},
{
"name": "present_0_key"
},
{
"name": "present_0_value"
},
{
"name": "present_1_key"
},
{
"name": "present_1_value"
},
{
"name": "present_2_key"
},
{
"name": "present_2_value"
},
{
"name": "present_3_key"
},
{
"name": "present_3_value"
},
{
"name": "present_4_key"
},
{
"name": "present_4_value"
},
{
"name": "present_5_key"
},
{
"name": "present_5_value"
}
]
},
"optim": {
"gelu_fusion": true,
"layer_norm_fusion": true,
"matmul_add_fusion": true
},
"quant": {
"mode": "fp16",
"samples": 10,
"calibration_method": "minmax",
"weight_type": "uint8",
"activation_type": "uint8",
"per_channel": false,
"symmetric": false,
"weight_symmetric": null,
"activation_symmetric": null,
"save_calibration": false,
"distribution": "uniform",
"seed": null,
"calibration_load_path": null,
"calibration_save_path": null,
"op_types_to_quantize": null,
"nodes_to_exclude": null,
"task": "text2text-generation",
"model_id": "microsoft/Florence-2-base",
"model_type": "florence2",
"fp16_keep_io_types": true,
"fp16_op_block_list": null
},
"compile": null,
"loader": {
"task": "text2text-generation",
"model_class": "Florence2DecoderWrapper",
"model_type": "florence2"
}
}
Loading
Loading