Upload GLAForCausalLM
Browse files- README.md +1 -1
- config.json +2 -1
- generation_config.json +1 -1
- model.safetensors +2 -2
README.md
CHANGED
|
@@ -8,4 +8,4 @@ license: mit
|
|
| 8 |
datasets:
|
| 9 |
- cerebras/SlimPajama-627B
|
| 10 |
library_name: fla
|
| 11 |
-
---
|
|
|
|
| 8 |
datasets:
|
| 9 |
- cerebras/SlimPajama-627B
|
| 10 |
library_name: fla
|
| 11 |
+
---
|
config.json
CHANGED
|
@@ -3,6 +3,7 @@
|
|
| 3 |
"architectures": [
|
| 4 |
"GLAForCausalLM"
|
| 5 |
],
|
|
|
|
| 6 |
"attn_mode": "chunk",
|
| 7 |
"bos_token_id": 1,
|
| 8 |
"clamp_min": null,
|
|
@@ -29,7 +30,7 @@
|
|
| 29 |
"share_conv_kernel": true,
|
| 30 |
"tie_word_embeddings": false,
|
| 31 |
"torch_dtype": "bfloat16",
|
| 32 |
-
"transformers_version": "4.
|
| 33 |
"use_cache": true,
|
| 34 |
"use_gk": true,
|
| 35 |
"use_gv": false,
|
|
|
|
| 3 |
"architectures": [
|
| 4 |
"GLAForCausalLM"
|
| 5 |
],
|
| 6 |
+
"attn": null,
|
| 7 |
"attn_mode": "chunk",
|
| 8 |
"bos_token_id": 1,
|
| 9 |
"clamp_min": null,
|
|
|
|
| 30 |
"share_conv_kernel": true,
|
| 31 |
"tie_word_embeddings": false,
|
| 32 |
"torch_dtype": "bfloat16",
|
| 33 |
+
"transformers_version": "4.48.2",
|
| 34 |
"use_cache": true,
|
| 35 |
"use_gk": true,
|
| 36 |
"use_gv": false,
|
generation_config.json
CHANGED
|
@@ -2,5 +2,5 @@
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
-
"transformers_version": "4.
|
| 6 |
}
|
|
|
|
| 2 |
"_from_model_config": true,
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.48.2"
|
| 6 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97c02567af31fc5ef98280a5d84e1c6b98842d8b92972940626bce8ebb3ed73d
|
| 3 |
+
size 2731066224
|