Upload MambaForCausalLM
Browse files- config.json +32 -0
- generation_config.json +6 -0
- model.safetensors +3 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "state-spaces/mamba-790m",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"MambaForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 1,
|
| 7 |
+
"conv_kernel": 4,
|
| 8 |
+
"d_model": 1536,
|
| 9 |
+
"eos_token_id": 2,
|
| 10 |
+
"expand": 2,
|
| 11 |
+
"fused_add_norm": true,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 1536,
|
| 14 |
+
"initializer_range": 0.1,
|
| 15 |
+
"intermediate_size": 3072,
|
| 16 |
+
"layer_norm_epsilon": 1e-05,
|
| 17 |
+
"model_type": "mamba",
|
| 18 |
+
"n_layer": 48,
|
| 19 |
+
"num_hidden_layers": 32,
|
| 20 |
+
"pad_vocab_size_multiple": 8,
|
| 21 |
+
"residual_in_fp32": true,
|
| 22 |
+
"rms_norm": true,
|
| 23 |
+
"ssm_cfg": {},
|
| 24 |
+
"state_size": 16,
|
| 25 |
+
"time_step_rank": 96,
|
| 26 |
+
"torch_dtype": "float16",
|
| 27 |
+
"transformers_version": "4.39.0.dev0",
|
| 28 |
+
"use_bias": false,
|
| 29 |
+
"use_cache": true,
|
| 30 |
+
"use_conv_bias": true,
|
| 31 |
+
"vocab_size": 50280
|
| 32 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,6 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 1,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"transformers_version": "4.39.0.dev0"
|
| 6 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6ed41bdb3582ac8312606e0413024d0265769003f9519505f4373e50a01d553a
|
| 3 |
+
size 1112273944
|