Upload GLAForCausalLM
Browse files- README.md +1 -1
- config.json +7 -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
@@ -3,13 +3,16 @@
|
|
3 |
"architectures": [
|
4 |
"GLAForCausalLM"
|
5 |
],
|
|
|
6 |
"attn_mode": "chunk",
|
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 +22,19 @@
|
|
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": true,
|
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 |
}
|
|
|
3 |
"architectures": [
|
4 |
"GLAForCausalLM"
|
5 |
],
|
6 |
+
"attn": null,
|
7 |
"attn_mode": "chunk",
|
8 |
"bos_token_id": 1,
|
9 |
"clamp_min": null,
|
10 |
"conv_size": 4,
|
11 |
+
"elementwise_affine": true,
|
12 |
"eos_token_id": 2,
|
13 |
"expand_k": 0.5,
|
14 |
"expand_v": 1,
|
15 |
+
"feature_map": null,
|
16 |
"fuse_cross_entropy": true,
|
17 |
"fuse_norm": true,
|
18 |
"hidden_act": "swish",
|
|
|
22 |
"intermediate_size": null,
|
23 |
"max_position_embeddings": 2048,
|
24 |
"model_type": "gla",
|
25 |
+
"norm_eps": 1e-06,
|
26 |
"num_heads": 4,
|
27 |
"num_hidden_layers": 24,
|
28 |
+
"num_kv_heads": null,
|
29 |
"rms_norm_eps": 1e-06,
|
30 |
"share_conv_kernel": true,
|
31 |
"tie_word_embeddings": true,
|
32 |
"torch_dtype": "bfloat16",
|
33 |
+
"transformers_version": "4.48.2",
|
34 |
"use_cache": true,
|
35 |
"use_gk": true,
|
36 |
"use_gv": false,
|
37 |
+
"use_output_gate": true,
|
38 |
"use_short_conv": false,
|
39 |
"vocab_size": 32000
|
40 |
}
|
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 sha256:07637f325a73991dcc31936e43ab9da2eb5c1a79135c477c3013bf3118a05a4a
|
3 |
+
size 683452592
|