Add files using upload-large-folder tool
Browse files- README.md +4 -6
- generation_config.json +12 -0
- model.safetensors +3 -0
- smash_config.json +2 -4
README.md
CHANGED
|
@@ -1,9 +1,9 @@
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
| 4 |
-
- pruna-ai
|
| 5 |
-
- pruna_pro-ai
|
| 6 |
- safetensors
|
|
|
|
|
|
|
| 7 |
---
|
| 8 |
|
| 9 |
# Model Card for loulou2/tiny_llama_hqq
|
|
@@ -59,11 +59,9 @@ The compression configuration of the model is stored in the `smash_config.json`
|
|
| 59 |
"batch_size": 1,
|
| 60 |
"device": "cuda",
|
| 61 |
"device_map": null,
|
| 62 |
-
"save_fns": [
|
| 63 |
-
"hqq"
|
| 64 |
-
],
|
| 65 |
"load_fns": [
|
| 66 |
-
"
|
| 67 |
],
|
| 68 |
"reapply_after_load": {
|
| 69 |
"factorizer": null,
|
|
|
|
| 1 |
---
|
| 2 |
library_name: transformers
|
| 3 |
tags:
|
|
|
|
|
|
|
| 4 |
- safetensors
|
| 5 |
+
- pruna_pro-ai
|
| 6 |
+
- pruna-ai
|
| 7 |
---
|
| 8 |
|
| 9 |
# Model Card for loulou2/tiny_llama_hqq
|
|
|
|
| 59 |
"batch_size": 1,
|
| 60 |
"device": "cuda",
|
| 61 |
"device_map": null,
|
| 62 |
+
"save_fns": [],
|
|
|
|
|
|
|
| 63 |
"load_fns": [
|
| 64 |
+
"transformers"
|
| 65 |
],
|
| 66 |
"reapply_after_load": {
|
| 67 |
"factorizer": null,
|
generation_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 128000,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
128001,
|
| 6 |
+
128008,
|
| 7 |
+
128009
|
| 8 |
+
],
|
| 9 |
+
"temperature": 0.6,
|
| 10 |
+
"top_p": 0.9,
|
| 11 |
+
"transformers_version": "4.52.4"
|
| 12 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:46d7b92493dca1f394dcc9318e4a9af32eafb5ff9b1b8056fcbe1a53a4c9c482
|
| 3 |
+
size 559573635
|
smash_config.json
CHANGED
|
@@ -19,11 +19,9 @@
|
|
| 19 |
"batch_size": 1,
|
| 20 |
"device": "cuda",
|
| 21 |
"device_map": null,
|
| 22 |
-
"save_fns": [
|
| 23 |
-
"hqq"
|
| 24 |
-
],
|
| 25 |
"load_fns": [
|
| 26 |
-
"
|
| 27 |
],
|
| 28 |
"reapply_after_load": {
|
| 29 |
"factorizer": null,
|
|
|
|
| 19 |
"batch_size": 1,
|
| 20 |
"device": "cuda",
|
| 21 |
"device_map": null,
|
| 22 |
+
"save_fns": [],
|
|
|
|
|
|
|
| 23 |
"load_fns": [
|
| 24 |
+
"transformers"
|
| 25 |
],
|
| 26 |
"reapply_after_load": {
|
| 27 |
"factorizer": null,
|