sharpenb commited on
Commit
085f570
1 Parent(s): 5471e49

2196c1bef651aa4b43b2a7f6dd5d7056aecc22e192b0ddfbab778f2b6b580eec

Browse files
README.md ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ library_name: pruna-engine
4
+ thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg"
5
+ metrics:
6
+ - memory_disk
7
+ - memory_inference
8
+ - inference_latency
9
+ - inference_throughput
10
+ - inference_CO2_emissions
11
+ - inference_energy_consumption
12
+ ---
13
+ <!-- header start -->
14
+ <!-- 200823 -->
15
+ <div style="width: auto; margin-left: auto; margin-right: auto">
16
+ <a href="https://www.pruna.ai/" target="_blank" rel="noopener noreferrer">
17
+ <img src="https://i.imgur.com/eDAlcgk.png" alt="PrunaAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
18
+ </a>
19
+ </div>
20
+ <!-- header end -->
21
+
22
+ # Simply make AI models cheaper, smaller, faster, and greener!
23
+
24
+ ## Results
25
+
26
+ ![image info](./plots.png)
27
+
28
+ ## Setup
29
+
30
+ You can run the smashed model by:
31
+ 1. Installing and importing the `pruna-engine` (version 0.2.6) package. Use `pip install pruna --extra-index-url https://pypi.nvidia.com --extra-index-url https://pypi.ngc.nvidia.com` for installation. See [Pypi](https://pypi.org/project/pruna-engine/) for detailed on the package.
32
+ 2. Downloading the model files at `model_path`. This can be done using huggingface with this repository name or with manual downloading.
33
+ 3. Loading the model
34
+ 4. Running the model.
35
+
36
+ You can achieve this by running the following code:
37
+
38
+ ```python
39
+ from transformers.utils.hub import cached_file
40
+ from pruna_engine.PrunaModel import PrunaModel # Step (1): install and import `pruna-engine` package.
41
+
42
+ ...
43
+ model_path = cached_file("PrunaAI/REPO", "model") # Step (2): download the model files at `model_path`.
44
+ smashed_model = PrunaModel.load_model(model_path) # Step (3): load the model.
45
+ y = smashed_model(x) # Step (4): run the model.
46
+ ```
47
+
48
+ ## Configurations
49
+
50
+ The configuration info are in `config.json`.
51
+
52
+ ## License
53
+
54
+ We follow the same license as the original model. Please check the license of the original model before using this model.
55
+
56
+ ## Want to compress other models?
57
+
58
+ - Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
59
+ - Request access to easily compress your own AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"pruner": "None", "pruning_ratio": 0.0, "factorizer": "None", "quantizer": "None", "n_quantization_bits": 8, "output_deviation": 0.005, "compiler": "ctranslate2_generation", "static_batch": true, "static_shape": true, "controlnet": "None", "unet_dim": 4, "device": "cuda", "cache_dir": "/ceph/hdd/staff/charpent/.cache/models", "max_batch_size": 1, "image_height": "None", "image_width": "None", "version": "None", "tokenizer_name": "placeholder"}
model/config.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "eos_token": "</s>",
4
+ "layer_norm_epsilon": 1e-06,
5
+ "unk_token": "<unk>"
6
+ }
model/smasher_config.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"load_function": "ctranslate2", "api_key": "pruna_c4c77860c62a2965f6bc281841ee1d7bd3", "verify_url": "http://johnrachwan.pythonanywhere.com", "model_specific": {}}
model/special_tokens_map.json ADDED
@@ -0,0 +1,23 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "unk_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ }
23
+ }
model/tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
model/tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91b289e85fa20fd375d8b33dc12f77616f18abc6359804471d1fafcb425fecb8
3
+ size 511574
model/tokenizer_config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 2048,
35
+ "pad_token": null,
36
+ "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false
41
+ }
model/vocabulary.json ADDED
The diff for this file is too large to render. See raw diff
 
plots.png ADDED