Upload MambaForCausalLM
Browse files- README.md +3 -3
- config.json +2 -1
- generation_config.json +1 -1
README.md
CHANGED
|
@@ -1,10 +1,10 @@
|
|
| 1 |
---
|
| 2 |
-
|
|
|
|
| 3 |
license: mit
|
|
|
|
| 4 |
datasets:
|
| 5 |
- mlsquare/CLIENT_samantar_mixed_train_val
|
| 6 |
-
language:
|
| 7 |
-
- en
|
| 8 |
pipeline_tag: text-generation
|
| 9 |
---
|
| 10 |
|
|
|
|
| 1 |
---
|
| 2 |
+
language:
|
| 3 |
+
- en
|
| 4 |
license: mit
|
| 5 |
+
library_name: transformers
|
| 6 |
datasets:
|
| 7 |
- mlsquare/CLIENT_samantar_mixed_train_val
|
|
|
|
|
|
|
| 8 |
pipeline_tag: text-generation
|
| 9 |
---
|
| 10 |
|
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"MambaForCausalLM"
|
| 4 |
],
|
|
@@ -15,6 +16,6 @@
|
|
| 15 |
"n_layer": 5,
|
| 16 |
"pad_vocab_size_multiple": 8,
|
| 17 |
"torch_dtype": "float32",
|
| 18 |
-
"transformers_version": "4.38.
|
| 19 |
"vocab_size": 7000
|
| 20 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "mlsquare/pico_seshu_test",
|
| 3 |
"architectures": [
|
| 4 |
"MambaForCausalLM"
|
| 5 |
],
|
|
|
|
| 16 |
"n_layer": 5,
|
| 17 |
"pad_vocab_size_multiple": 8,
|
| 18 |
"torch_dtype": "float32",
|
| 19 |
+
"transformers_version": "4.38.2",
|
| 20 |
"vocab_size": 7000
|
| 21 |
}
|
generation_config.json
CHANGED
|
@@ -1,4 +1,4 @@
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
-
"transformers_version": "4.38.
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"_from_model_config": true,
|
| 3 |
+
"transformers_version": "4.38.2"
|
| 4 |
}
|