Upload folder using huggingface_hub (#6)
Browse files- 6034f36849f9adbc0f206e478ad13022e246443202df6955cc1d824a482c4883 (fe5002a478bd2db79e4a08bc0b495dd22c31a66d)
- README.md +5 -5
- config.json +26 -26
- model.safetensors +1 -1
- smash_config.json +1 -1
README.md
CHANGED
@@ -1,6 +1,6 @@
|
|
1 |
---
|
2 |
thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg"
|
3 |
-
base_model:
|
4 |
metrics:
|
5 |
- memory_disk
|
6 |
- memory_inference
|
@@ -52,7 +52,7 @@ tags:
|
|
52 |
|
53 |
You can run the smashed model with these steps:
|
54 |
|
55 |
-
0. Check requirements from the original repo
|
56 |
1. Make sure that you have installed quantization related packages.
|
57 |
```bash
|
58 |
pip install transformers accelerate bitsandbytes>0.37.0
|
@@ -63,7 +63,7 @@ You can run the smashed model with these steps:
|
|
63 |
|
64 |
|
65 |
model = AutoModelForCausalLM.from_pretrained("PrunaAI/distributed-optimized-gpt2-1b-bnb-8bit-smashed", trust_remote_code=True, device_map='auto')
|
66 |
-
tokenizer = AutoTokenizer.from_pretrained("
|
67 |
|
68 |
input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
|
69 |
|
@@ -77,9 +77,9 @@ The configuration info are in `smash_config.json`.
|
|
77 |
|
78 |
## Credits & License
|
79 |
|
80 |
-
The license of the smashed model follows the license of the original model. Please check the license of the original model
|
81 |
|
82 |
## Want to compress other models?
|
83 |
|
84 |
- Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
|
85 |
-
-
|
|
|
1 |
---
|
2 |
thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg"
|
3 |
+
base_model: distributed/optimized-gpt2-1b
|
4 |
metrics:
|
5 |
- memory_disk
|
6 |
- memory_inference
|
|
|
52 |
|
53 |
You can run the smashed model with these steps:
|
54 |
|
55 |
+
0. Check requirements from the original repo distributed/optimized-gpt2-1b installed. In particular, check python, cuda, and transformers versions.
|
56 |
1. Make sure that you have installed quantization related packages.
|
57 |
```bash
|
58 |
pip install transformers accelerate bitsandbytes>0.37.0
|
|
|
63 |
|
64 |
|
65 |
model = AutoModelForCausalLM.from_pretrained("PrunaAI/distributed-optimized-gpt2-1b-bnb-8bit-smashed", trust_remote_code=True, device_map='auto')
|
66 |
+
tokenizer = AutoTokenizer.from_pretrained("distributed/optimized-gpt2-1b")
|
67 |
|
68 |
input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
|
69 |
|
|
|
77 |
|
78 |
## Credits & License
|
79 |
|
80 |
+
The license of the smashed model follows the license of the original model. Please check the license of the original model distributed/optimized-gpt2-1b before using this model which provided the base model. The license of the `pruna-engine` is [here](https://pypi.org/project/pruna-engine/) on Pypi.
|
81 |
|
82 |
## Want to compress other models?
|
83 |
|
84 |
- Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
|
85 |
+
- Do it by yourself [here](https://docs.pruna.ai/en/latest/setup/pip.html).
|
config.json
CHANGED
@@ -1,5 +1,5 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/covalent/.cache/models/
|
3 |
"activation_function": "gelu_new",
|
4 |
"all_reduce_scores": {
|
5 |
"0": "NON_PARTICIPATING",
|
@@ -26,7 +26,7 @@
|
|
26 |
"117": "NON_PARTICIPATING",
|
27 |
"118": "NON_PARTICIPATING",
|
28 |
"119": "NON_PARTICIPATING",
|
29 |
-
"12": "
|
30 |
"120": "NON_PARTICIPATING",
|
31 |
"121": "NON_PARTICIPATING",
|
32 |
"122": "NON_PARTICIPATING",
|
@@ -36,7 +36,7 @@
|
|
36 |
"126": "NON_PARTICIPATING",
|
37 |
"127": "NON_PARTICIPATING",
|
38 |
"128": "NON_PARTICIPATING",
|
39 |
-
"129": "
|
40 |
"13": "NON_PARTICIPATING",
|
41 |
"130": "NON_PARTICIPATING",
|
42 |
"131": "NON_PARTICIPATING",
|
@@ -49,9 +49,9 @@
|
|
49 |
"138": "NON_PARTICIPATING",
|
50 |
"139": "NON_PARTICIPATING",
|
51 |
"14": "NON_PARTICIPATING",
|
52 |
-
"140": "
|
53 |
-
"141": "
|
54 |
-
"142": "
|
55 |
"143": "SUCCESS",
|
56 |
"144": "NON_PARTICIPATING",
|
57 |
"145": "NON_PARTICIPATING",
|
@@ -61,15 +61,15 @@
|
|
61 |
"149": "NON_PARTICIPATING",
|
62 |
"15": "NON_PARTICIPATING",
|
63 |
"150": "NON_PARTICIPATING",
|
64 |
-
"151": "
|
65 |
"152": "NON_PARTICIPATING",
|
66 |
"153": "NON_PARTICIPATING",
|
67 |
"154": "NON_PARTICIPATING",
|
68 |
"155": "NON_PARTICIPATING",
|
69 |
-
"156": "
|
70 |
"157": "NON_PARTICIPATING",
|
71 |
"158": "NON_PARTICIPATING",
|
72 |
-
"159": "
|
73 |
"16": "NON_PARTICIPATING",
|
74 |
"160": "NON_PARTICIPATING",
|
75 |
"161": "NON_PARTICIPATING",
|
@@ -80,7 +80,7 @@
|
|
80 |
"166": "NON_PARTICIPATING",
|
81 |
"167": "NON_PARTICIPATING",
|
82 |
"168": "NON_PARTICIPATING",
|
83 |
-
"169": "
|
84 |
"17": "NON_PARTICIPATING",
|
85 |
"170": "NON_PARTICIPATING",
|
86 |
"171": "NON_PARTICIPATING",
|
@@ -90,8 +90,8 @@
|
|
90 |
"175": "NON_PARTICIPATING",
|
91 |
"176": "NON_PARTICIPATING",
|
92 |
"177": "NON_PARTICIPATING",
|
93 |
-
"178": "
|
94 |
-
"179": "
|
95 |
"18": "NON_PARTICIPATING",
|
96 |
"180": "NON_PARTICIPATING",
|
97 |
"181": "NON_PARTICIPATING",
|
@@ -114,7 +114,7 @@
|
|
114 |
"197": "NON_PARTICIPATING",
|
115 |
"198": "NON_PARTICIPATING",
|
116 |
"199": "NON_PARTICIPATING",
|
117 |
-
"2": "
|
118 |
"20": "NON_PARTICIPATING",
|
119 |
"200": "NON_PARTICIPATING",
|
120 |
"201": "NON_PARTICIPATING",
|
@@ -130,7 +130,7 @@
|
|
130 |
"210": "NON_PARTICIPATING",
|
131 |
"211": "NON_PARTICIPATING",
|
132 |
"212": "NON_PARTICIPATING",
|
133 |
-
"213": "
|
134 |
"214": "NON_PARTICIPATING",
|
135 |
"215": "NON_PARTICIPATING",
|
136 |
"216": "SUCCESS",
|
@@ -179,7 +179,7 @@
|
|
179 |
"255": "NON_PARTICIPATING",
|
180 |
"26": "NON_PARTICIPATING",
|
181 |
"27": "NON_PARTICIPATING",
|
182 |
-
"28": "
|
183 |
"29": "NON_PARTICIPATING",
|
184 |
"3": "NON_PARTICIPATING",
|
185 |
"30": "NON_PARTICIPATING",
|
@@ -206,7 +206,7 @@
|
|
206 |
"5": "NON_PARTICIPATING",
|
207 |
"50": "NON_PARTICIPATING",
|
208 |
"51": "NON_PARTICIPATING",
|
209 |
-
"52": "
|
210 |
"53": "NON_PARTICIPATING",
|
211 |
"54": "NON_PARTICIPATING",
|
212 |
"55": "NON_PARTICIPATING",
|
@@ -222,41 +222,41 @@
|
|
222 |
"64": "NON_PARTICIPATING",
|
223 |
"65": "NON_PARTICIPATING",
|
224 |
"66": "NON_PARTICIPATING",
|
225 |
-
"67": "
|
226 |
"68": "NON_PARTICIPATING",
|
227 |
"69": "NON_PARTICIPATING",
|
228 |
"7": "SUCCESS",
|
229 |
"70": "NON_PARTICIPATING",
|
230 |
"71": "NON_PARTICIPATING",
|
231 |
"72": "NON_PARTICIPATING",
|
232 |
-
"73": "
|
233 |
-
"74": "
|
234 |
-
"75": "
|
235 |
"76": "NON_PARTICIPATING",
|
236 |
"77": "NON_PARTICIPATING",
|
237 |
-
"78": "
|
238 |
"79": "NON_PARTICIPATING",
|
239 |
"8": "NON_PARTICIPATING",
|
240 |
"80": "NON_PARTICIPATING",
|
241 |
"81": "NON_PARTICIPATING",
|
242 |
"82": "NON_PARTICIPATING",
|
243 |
"83": "NON_PARTICIPATING",
|
244 |
-
"84": "
|
245 |
"85": "NON_PARTICIPATING",
|
246 |
-
"86": "
|
247 |
"87": "NON_PARTICIPATING",
|
248 |
-
"88": "
|
249 |
"89": "NON_PARTICIPATING",
|
250 |
"9": "NON_PARTICIPATING",
|
251 |
"90": "NON_PARTICIPATING",
|
252 |
"91": "NON_PARTICIPATING",
|
253 |
"92": "NON_PARTICIPATING",
|
254 |
"93": "NON_PARTICIPATING",
|
255 |
-
"94": "
|
256 |
"95": "SUCCESS",
|
257 |
"96": "NON_PARTICIPATING",
|
258 |
"97": "NON_PARTICIPATING",
|
259 |
-
"98": "
|
260 |
"99": "NON_PARTICIPATING"
|
261 |
},
|
262 |
"architectures": [
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/covalent/.cache/models/tmpg_8jo7a30wplyaho",
|
3 |
"activation_function": "gelu_new",
|
4 |
"all_reduce_scores": {
|
5 |
"0": "NON_PARTICIPATING",
|
|
|
26 |
"117": "NON_PARTICIPATING",
|
27 |
"118": "NON_PARTICIPATING",
|
28 |
"119": "NON_PARTICIPATING",
|
29 |
+
"12": "NON_PARTICIPATING",
|
30 |
"120": "NON_PARTICIPATING",
|
31 |
"121": "NON_PARTICIPATING",
|
32 |
"122": "NON_PARTICIPATING",
|
|
|
36 |
"126": "NON_PARTICIPATING",
|
37 |
"127": "NON_PARTICIPATING",
|
38 |
"128": "NON_PARTICIPATING",
|
39 |
+
"129": "NON_PARTICIPATING",
|
40 |
"13": "NON_PARTICIPATING",
|
41 |
"130": "NON_PARTICIPATING",
|
42 |
"131": "NON_PARTICIPATING",
|
|
|
49 |
"138": "NON_PARTICIPATING",
|
50 |
"139": "NON_PARTICIPATING",
|
51 |
"14": "NON_PARTICIPATING",
|
52 |
+
"140": "NON_PARTICIPATING",
|
53 |
+
"141": "SUCCESS",
|
54 |
+
"142": "NON_PARTICIPATING",
|
55 |
"143": "SUCCESS",
|
56 |
"144": "NON_PARTICIPATING",
|
57 |
"145": "NON_PARTICIPATING",
|
|
|
61 |
"149": "NON_PARTICIPATING",
|
62 |
"15": "NON_PARTICIPATING",
|
63 |
"150": "NON_PARTICIPATING",
|
64 |
+
"151": "NON_PARTICIPATING",
|
65 |
"152": "NON_PARTICIPATING",
|
66 |
"153": "NON_PARTICIPATING",
|
67 |
"154": "NON_PARTICIPATING",
|
68 |
"155": "NON_PARTICIPATING",
|
69 |
+
"156": "SUCCESS",
|
70 |
"157": "NON_PARTICIPATING",
|
71 |
"158": "NON_PARTICIPATING",
|
72 |
+
"159": "NON_PARTICIPATING",
|
73 |
"16": "NON_PARTICIPATING",
|
74 |
"160": "NON_PARTICIPATING",
|
75 |
"161": "NON_PARTICIPATING",
|
|
|
80 |
"166": "NON_PARTICIPATING",
|
81 |
"167": "NON_PARTICIPATING",
|
82 |
"168": "NON_PARTICIPATING",
|
83 |
+
"169": "SUCCESS",
|
84 |
"17": "NON_PARTICIPATING",
|
85 |
"170": "NON_PARTICIPATING",
|
86 |
"171": "NON_PARTICIPATING",
|
|
|
90 |
"175": "NON_PARTICIPATING",
|
91 |
"176": "NON_PARTICIPATING",
|
92 |
"177": "NON_PARTICIPATING",
|
93 |
+
"178": "NON_PARTICIPATING",
|
94 |
+
"179": "SUCCESS",
|
95 |
"18": "NON_PARTICIPATING",
|
96 |
"180": "NON_PARTICIPATING",
|
97 |
"181": "NON_PARTICIPATING",
|
|
|
114 |
"197": "NON_PARTICIPATING",
|
115 |
"198": "NON_PARTICIPATING",
|
116 |
"199": "NON_PARTICIPATING",
|
117 |
+
"2": "SUCCESS",
|
118 |
"20": "NON_PARTICIPATING",
|
119 |
"200": "NON_PARTICIPATING",
|
120 |
"201": "NON_PARTICIPATING",
|
|
|
130 |
"210": "NON_PARTICIPATING",
|
131 |
"211": "NON_PARTICIPATING",
|
132 |
"212": "NON_PARTICIPATING",
|
133 |
+
"213": "SUCCESS",
|
134 |
"214": "NON_PARTICIPATING",
|
135 |
"215": "NON_PARTICIPATING",
|
136 |
"216": "SUCCESS",
|
|
|
179 |
"255": "NON_PARTICIPATING",
|
180 |
"26": "NON_PARTICIPATING",
|
181 |
"27": "NON_PARTICIPATING",
|
182 |
+
"28": "SUCCESS",
|
183 |
"29": "NON_PARTICIPATING",
|
184 |
"3": "NON_PARTICIPATING",
|
185 |
"30": "NON_PARTICIPATING",
|
|
|
206 |
"5": "NON_PARTICIPATING",
|
207 |
"50": "NON_PARTICIPATING",
|
208 |
"51": "NON_PARTICIPATING",
|
209 |
+
"52": "SUCCESS",
|
210 |
"53": "NON_PARTICIPATING",
|
211 |
"54": "NON_PARTICIPATING",
|
212 |
"55": "NON_PARTICIPATING",
|
|
|
222 |
"64": "NON_PARTICIPATING",
|
223 |
"65": "NON_PARTICIPATING",
|
224 |
"66": "NON_PARTICIPATING",
|
225 |
+
"67": "NON_PARTICIPATING",
|
226 |
"68": "NON_PARTICIPATING",
|
227 |
"69": "NON_PARTICIPATING",
|
228 |
"7": "SUCCESS",
|
229 |
"70": "NON_PARTICIPATING",
|
230 |
"71": "NON_PARTICIPATING",
|
231 |
"72": "NON_PARTICIPATING",
|
232 |
+
"73": "NON_PARTICIPATING",
|
233 |
+
"74": "SUCCESS",
|
234 |
+
"75": "NON_PARTICIPATING",
|
235 |
"76": "NON_PARTICIPATING",
|
236 |
"77": "NON_PARTICIPATING",
|
237 |
+
"78": "NON_PARTICIPATING",
|
238 |
"79": "NON_PARTICIPATING",
|
239 |
"8": "NON_PARTICIPATING",
|
240 |
"80": "NON_PARTICIPATING",
|
241 |
"81": "NON_PARTICIPATING",
|
242 |
"82": "NON_PARTICIPATING",
|
243 |
"83": "NON_PARTICIPATING",
|
244 |
+
"84": "NON_PARTICIPATING",
|
245 |
"85": "NON_PARTICIPATING",
|
246 |
+
"86": "NON_PARTICIPATING",
|
247 |
"87": "NON_PARTICIPATING",
|
248 |
+
"88": "SUCCESS",
|
249 |
"89": "NON_PARTICIPATING",
|
250 |
"9": "NON_PARTICIPATING",
|
251 |
"90": "NON_PARTICIPATING",
|
252 |
"91": "NON_PARTICIPATING",
|
253 |
"92": "NON_PARTICIPATING",
|
254 |
"93": "NON_PARTICIPATING",
|
255 |
+
"94": "NON_PARTICIPATING",
|
256 |
"95": "SUCCESS",
|
257 |
"96": "NON_PARTICIPATING",
|
258 |
"97": "NON_PARTICIPATING",
|
259 |
+
"98": "NON_PARTICIPATING",
|
260 |
"99": "NON_PARTICIPATING"
|
261 |
},
|
262 |
"architectures": [
|
model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 1207575528
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:129bac3621dfd112f94500629cc35d3df6c1e4c645ac42707f058a2e8d7f789d
|
3 |
size 1207575528
|
smash_config.json
CHANGED
@@ -28,7 +28,7 @@
|
|
28 |
"quant_llm-int8_weight_bits": 8,
|
29 |
"max_batch_size": 1,
|
30 |
"device": "cuda",
|
31 |
-
"cache_dir": "/covalent/.cache/models/
|
32 |
"task": "",
|
33 |
"save_load_fn": "bitsandbytes",
|
34 |
"save_load_fn_args": {}
|
|
|
28 |
"quant_llm-int8_weight_bits": 8,
|
29 |
"max_batch_size": 1,
|
30 |
"device": "cuda",
|
31 |
+
"cache_dir": "/covalent/.cache/models/tmpg_8jo7a3",
|
32 |
"task": "",
|
33 |
"save_load_fn": "bitsandbytes",
|
34 |
"save_load_fn_args": {}
|