Upload GLAForCausalLM
Browse files- config.json +6 -1
- generation_config.json +1 -1
- model.safetensors +1 -1
- tokenizer.json +1 -0
config.json
CHANGED
|
@@ -7,9 +7,11 @@
|
|
| 7 |
"bos_token_id": 1,
|
| 8 |
"clamp_min": null,
|
| 9 |
"conv_size": 4,
|
|
|
|
| 10 |
"eos_token_id": 2,
|
| 11 |
"expand_k": 0.5,
|
| 12 |
"expand_v": 1,
|
|
|
|
| 13 |
"fuse_cross_entropy": true,
|
| 14 |
"fuse_norm": true,
|
| 15 |
"hidden_act": "swish",
|
|
@@ -19,16 +21,19 @@
|
|
| 19 |
"intermediate_size": null,
|
| 20 |
"max_position_embeddings": 2048,
|
| 21 |
"model_type": "gla",
|
|
|
|
| 22 |
"num_heads": 4,
|
| 23 |
"num_hidden_layers": 24,
|
|
|
|
| 24 |
"rms_norm_eps": 1e-06,
|
| 25 |
"share_conv_kernel": true,
|
| 26 |
"tie_word_embeddings": false,
|
| 27 |
"torch_dtype": "bfloat16",
|
| 28 |
-
"transformers_version": "4.
|
| 29 |
"use_cache": true,
|
| 30 |
"use_gk": true,
|
| 31 |
"use_gv": false,
|
|
|
|
| 32 |
"use_short_conv": false,
|
| 33 |
"vocab_size": 32000
|
| 34 |
}
|
|
|
|
| 7 |
"bos_token_id": 1,
|
| 8 |
"clamp_min": null,
|
| 9 |
"conv_size": 4,
|
| 10 |
+
"elementwise_affine": true,
|
| 11 |
"eos_token_id": 2,
|
| 12 |
"expand_k": 0.5,
|
| 13 |
"expand_v": 1,
|
| 14 |
+
"feature_map": null,
|
| 15 |
"fuse_cross_entropy": true,
|
| 16 |
"fuse_norm": true,
|
| 17 |
"hidden_act": "swish",
|
|
|
|
| 21 |
"intermediate_size": null,
|
| 22 |
"max_position_embeddings": 2048,
|
| 23 |
"model_type": "gla",
|
| 24 |
+
"norm_eps": 1e-06,
|
| 25 |
"num_heads": 4,
|
| 26 |
"num_hidden_layers": 24,
|
| 27 |
+
"num_kv_heads": null,
|
| 28 |
"rms_norm_eps": 1e-06,
|
| 29 |
"share_conv_kernel": true,
|
| 30 |
"tie_word_embeddings": false,
|
| 31 |
"torch_dtype": "bfloat16",
|
| 32 |
+
"transformers_version": "4.40.2",
|
| 33 |
"use_cache": true,
|
| 34 |
"use_gk": true,
|
| 35 |
"use_gv": false,
|
| 36 |
+
"use_output_gate": true,
|
| 37 |
"use_short_conv": false,
|
| 38 |
"vocab_size": 32000
|
| 39 |
}
|
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": "4.40.2"
|
| 6 |
}
|
model.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 2731063560
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f086b8b8db79b9f466788f99f3e4d86951cc5eae8e37e4c7f04912ecb64d4eb2
|
| 3 |
size 2731063560
|
tokenizer.json
CHANGED
|
@@ -134,6 +134,7 @@
|
|
| 134 |
"end_of_word_suffix": null,
|
| 135 |
"fuse_unk": true,
|
| 136 |
"byte_fallback": true,
|
|
|
|
| 137 |
"vocab": {
|
| 138 |
"<unk>": 0,
|
| 139 |
"<s>": 1,
|
|
|
|
| 134 |
"end_of_word_suffix": null,
|
| 135 |
"fuse_unk": true,
|
| 136 |
"byte_fallback": true,
|
| 137 |
+
"ignore_merges": false,
|
| 138 |
"vocab": {
|
| 139 |
"<unk>": 0,
|
| 140 |
"<s>": 1,
|