Upload MambaForCausalLM
Browse files- config.json +29 -15
- generation_config.json +1 -0
- model.safetensors +2 -2
config.json
CHANGED
@@ -1,27 +1,41 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "/opt/dlami/nvme/checkpoints/distill/mistral_teacher_reverse_2e_5/checkpoint-950",
|
3 |
"architectures": [
|
4 |
-
"
|
5 |
],
|
6 |
-
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 1,
|
|
|
|
|
|
|
8 |
"eos_token_id": 2,
|
9 |
-
"
|
|
|
10 |
"hidden_act": "silu",
|
11 |
"hidden_size": 768,
|
12 |
-
"initializer_range": 0.
|
13 |
-
"intermediate_size":
|
14 |
-
"
|
15 |
-
"model_type": "
|
16 |
-
"
|
17 |
-
"num_hidden_layers":
|
18 |
-
"
|
19 |
-
"
|
20 |
-
"
|
21 |
-
"
|
22 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
23 |
"torch_dtype": "float32",
|
24 |
"transformers_version": "4.40.1",
|
|
|
25 |
"use_cache": false,
|
|
|
|
|
26 |
"vocab_size": 32000
|
27 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "/opt/dlami/nvme/checkpoints/distill/mamba-mistral_teacher_reverse_2e_5/checkpoint-950",
|
3 |
"architectures": [
|
4 |
+
"MambaForCausalLM"
|
5 |
],
|
|
|
6 |
"bos_token_id": 1,
|
7 |
+
"conv_kernel": 4,
|
8 |
+
"d_inner": 1536,
|
9 |
+
"d_model": 768,
|
10 |
"eos_token_id": 2,
|
11 |
+
"expand": 2,
|
12 |
+
"fused_add_norm": true,
|
13 |
"hidden_act": "silu",
|
14 |
"hidden_size": 768,
|
15 |
+
"initializer_range": 0.1,
|
16 |
+
"intermediate_size": 1536,
|
17 |
+
"layer_norm_epsilon": 1e-05,
|
18 |
+
"model_type": "mamba",
|
19 |
+
"n_layer": 24,
|
20 |
+
"num_hidden_layers": 24,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"pad_vocab_size_multiple": 8,
|
23 |
+
"rescale_prenorm_residual": false,
|
24 |
+
"residual_in_fp32": true,
|
25 |
+
"rms_norm": true,
|
26 |
+
"ssm_cfg": {},
|
27 |
+
"state_size": 16,
|
28 |
+
"time_step_floor": 0.0001,
|
29 |
+
"time_step_init_scheme": "random",
|
30 |
+
"time_step_max": 0.1,
|
31 |
+
"time_step_min": 0.001,
|
32 |
+
"time_step_rank": 48,
|
33 |
+
"time_step_scale": 1.0,
|
34 |
"torch_dtype": "float32",
|
35 |
"transformers_version": "4.40.1",
|
36 |
+
"use_bias": false,
|
37 |
"use_cache": false,
|
38 |
+
"use_conv_bias": true,
|
39 |
+
"use_mambapy": false,
|
40 |
"vocab_size": 32000
|
41 |
}
|
generation_config.json
CHANGED
@@ -2,5 +2,6 @@
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
|
|
5 |
"transformers_version": "4.40.1"
|
6 |
}
|
|
|
2 |
"_from_model_config": true,
|
3 |
"bos_token_id": 1,
|
4 |
"eos_token_id": 2,
|
5 |
+
"pad_token_id": 0,
|
6 |
"transformers_version": "4.40.1"
|
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 sha256:3496b2de3d4fe00f3e9489832b2519fb90a76d4a0f1eb205e5c9d10a809e6803
|
3 |
+
size 460411384
|