Upload FalconMambaForCausalLM
Browse files- config.json +3 -3
- generation_config.json +1 -1
- model.safetensors +2 -2
config.json
CHANGED
@@ -9,7 +9,7 @@
|
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 8,
|
11 |
"initializer_range": 0.1,
|
12 |
-
"intermediate_size":
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"mixer_rms_eps": 1e-06,
|
15 |
"model_type": "falcon_mamba",
|
@@ -27,10 +27,10 @@
|
|
27 |
"time_step_rank": 1,
|
28 |
"time_step_scale": 1.0,
|
29 |
"torch_dtype": "float32",
|
30 |
-
"transformers_version": "4.
|
31 |
"use_bias": false,
|
32 |
"use_cache": true,
|
33 |
"use_conv_bias": true,
|
34 |
-
"
|
35 |
"vocab_size": 65036
|
36 |
}
|
|
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 8,
|
11 |
"initializer_range": 0.1,
|
12 |
+
"intermediate_size": 16,
|
13 |
"layer_norm_epsilon": 1e-05,
|
14 |
"mixer_rms_eps": 1e-06,
|
15 |
"model_type": "falcon_mamba",
|
|
|
27 |
"time_step_rank": 1,
|
28 |
"time_step_scale": 1.0,
|
29 |
"torch_dtype": "float32",
|
30 |
+
"transformers_version": "4.55.0.dev0",
|
31 |
"use_bias": false,
|
32 |
"use_cache": true,
|
33 |
"use_conv_bias": true,
|
34 |
+
"use_falcon_mambapy": false,
|
35 |
"vocab_size": 65036
|
36 |
}
|
generation_config.json
CHANGED
@@ -3,5 +3,5 @@
|
|
3 |
"bos_token_id": 0,
|
4 |
"eos_token_id": 0,
|
5 |
"pad_token_id": 0,
|
6 |
-
"transformers_version": "4.
|
7 |
}
|
|
|
3 |
"bos_token_id": 0,
|
4 |
"eos_token_id": 0,
|
5 |
"pad_token_id": 0,
|
6 |
+
"transformers_version": "4.55.0.dev0"
|
7 |
}
|
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 sha256:8815c8a41013afd78473fa748fd03a91bad7206057bb412300ec7782563317fa
|
3 |
+
size 2093848
|