Instructions to use mlboydaisuke/Falcon3-3B-Instruct-LiteRT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LiteRT-LM
How to use mlboydaisuke/Falcon3-3B-Instruct-LiteRT with LiteRT-LM:
# LiteRT-LM runs on various platforms (Android, iOS, Windows, Linux, macOS, IoT, Web/WASM) # and supports many APIs (C++, Python, Kotlin, Swift, JavaScript, Flutter). # For platform-specific integration guides, please refer to the official developer website: # https://ai.google.dev/edge/litert-lm # To try LiteRT-LM, the easiest way is to use our CLI tool. # 1. Install the LiteRT-LM CLI tool: pip install -U litert-lm # 2. Download and run this model locally: # See: https://ai.google.dev/edge/litert-lm/cli litert-lm run \ --from-huggingface-repo=mlboydaisuke/Falcon3-3B-Instruct-LiteRT \ --prompt="Write me a poem"
- LiteRT
How to use mlboydaisuke/Falcon3-3B-Instruct-LiteRT with LiteRT:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Add the blockwise-128 int4 recipe (reproduce with stock litert-torch)
Browse files- falcon_int4_block128.json +36 -0
falcon_int4_block128.json
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"regex": ".*",
|
| 4 |
+
"operation": "*",
|
| 5 |
+
"algorithm_key": "min_max_uniform_quantize",
|
| 6 |
+
"op_config": {
|
| 7 |
+
"weight_tensor_config": {
|
| 8 |
+
"num_bits": 4,
|
| 9 |
+
"symmetric": true,
|
| 10 |
+
"granularity": "BLOCKWISE_128",
|
| 11 |
+
"dtype": "INT"
|
| 12 |
+
},
|
| 13 |
+
"compute_precision": "INTEGER",
|
| 14 |
+
"explicit_dequantize": false,
|
| 15 |
+
"skip_checks": false,
|
| 16 |
+
"min_weight_elements": 0
|
| 17 |
+
}
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"regex": ".*",
|
| 21 |
+
"operation": "EMBEDDING_LOOKUP",
|
| 22 |
+
"algorithm_key": "min_max_uniform_quantize",
|
| 23 |
+
"op_config": {
|
| 24 |
+
"weight_tensor_config": {
|
| 25 |
+
"num_bits": 8,
|
| 26 |
+
"symmetric": true,
|
| 27 |
+
"granularity": "CHANNELWISE",
|
| 28 |
+
"dtype": "INT"
|
| 29 |
+
},
|
| 30 |
+
"compute_precision": "INTEGER",
|
| 31 |
+
"explicit_dequantize": false,
|
| 32 |
+
"skip_checks": false,
|
| 33 |
+
"min_weight_elements": 0
|
| 34 |
+
}
|
| 35 |
+
}
|
| 36 |
+
]
|