Upload HF format weights for Mamba2ForCausalLM (#9)
Browse files- Upload Mamba2ForCausalLM (ab5ea2a2342c616ca1e29b325df2cf51cd286211)
- Upload tokenizer (a92680008f39180a70b2c22145963a93caa84ccc)
Co-authored-by: Pablo Montalvo <Molbap@users.noreply.huggingface.co>
- README.md +2 -2
- config.json +44 -0
- generation_config.json +7 -0
- model-00001-of-00003.safetensors +3 -0
- model-00002-of-00003.safetensors +3 -0
- model-00003-of-00003.safetensors +3 -0
- model.safetensors.index.json +586 -0
- special_tokens_map.json +23 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
-
|
| 4 |
-
|
| 5 |
---
|
| 6 |
|
| 7 |
# Model Card for Mamba-Codestral-7B-v0.1
|
|
|
|
| 1 |
---
|
| 2 |
license: apache-2.0
|
| 3 |
+
extra_gated_description: If you want to learn more about how we process your personal
|
| 4 |
+
data, please read our <a href="https://mistral.ai/terms/">Privacy Policy</a>.
|
| 5 |
---
|
| 6 |
|
| 7 |
# Model Card for Mamba-Codestral-7B-v0.1
|
config.json
ADDED
|
@@ -0,0 +1,44 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/raid/pablo/codestral-hf-good/",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Mamba2ForCausalLM"
|
| 5 |
+
],
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"chunk_size": 256,
|
| 8 |
+
"conv_kernel": 4,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"expand": 2,
|
| 11 |
+
"head_dim": 64,
|
| 12 |
+
"hidden_act": "silu",
|
| 13 |
+
"hidden_size": 4096,
|
| 14 |
+
"initializer_range": 0.1,
|
| 15 |
+
"intermediate_size": 8192,
|
| 16 |
+
"layer_norm_epsilon": 1e-05,
|
| 17 |
+
"model_type": "mamba2",
|
| 18 |
+
"n_groups": 8,
|
| 19 |
+
"norm_before_gate": true,
|
| 20 |
+
"num_heads": 128,
|
| 21 |
+
"num_hidden_layers": 64,
|
| 22 |
+
"pad_token_id": 0,
|
| 23 |
+
"rescale_prenorm_residual": false,
|
| 24 |
+
"residual_in_fp32": true,
|
| 25 |
+
"rms_norm": true,
|
| 26 |
+
"state_size": 128,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"time_step_floor": 0.0001,
|
| 29 |
+
"time_step_init_scheme": "random",
|
| 30 |
+
"time_step_limit": [
|
| 31 |
+
0.0,
|
| 32 |
+
Infinity
|
| 33 |
+
],
|
| 34 |
+
"time_step_max": 0.1,
|
| 35 |
+
"time_step_min": 0.001,
|
| 36 |
+
"time_step_rank": 256,
|
| 37 |
+
"time_step_scale": 1.0,
|
| 38 |
+
"torch_dtype": "bfloat16",
|
| 39 |
+
"transformers_version": "4.44.0.dev0",
|
| 40 |
+
"use_bias": false,
|
| 41 |
+
"use_cache": true,
|
| 42 |
+
"use_conv_bias": true,
|
| 43 |
+
"vocab_size": 32768
|
| 44 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"bos_token_id": 0,
|
| 4 |
+
"eos_token_id": 2,
|
| 5 |
+
"pad_token_id": 1,
|
| 6 |
+
"transformers_version": "4.44.0.dev0"
|
| 7 |
+
}
|
model-00001-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fceef8df9e1e182bda9a0c71f46473ddc3914cedda85e07d324aeb2121de5e80
|
| 3 |
+
size 4873450856
|
model-00002-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42232512449b2a496f447e2c1b7a491f725bbf3f3761b5e889955dfcd933a569
|
| 3 |
+
size 4976244624
|
model-00003-of-00003.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5d655663c24ecd409cfe96275e557457be38fa5ad82afbdf70b99230f3368c2
|
| 3 |
+
size 4721175056
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,586 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 14570807296
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"backbone.embeddings.weight": "model-00001-of-00003.safetensors",
|
| 7 |
+
"backbone.layers.0.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 8 |
+
"backbone.layers.0.mixer.D": "model-00001-of-00003.safetensors",
|
| 9 |
+
"backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 10 |
+
"backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 11 |
+
"backbone.layers.0.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 12 |
+
"backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 13 |
+
"backbone.layers.0.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 14 |
+
"backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 15 |
+
"backbone.layers.0.norm.weight": "model-00001-of-00003.safetensors",
|
| 16 |
+
"backbone.layers.1.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 17 |
+
"backbone.layers.1.mixer.D": "model-00001-of-00003.safetensors",
|
| 18 |
+
"backbone.layers.1.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 19 |
+
"backbone.layers.1.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 20 |
+
"backbone.layers.1.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 21 |
+
"backbone.layers.1.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 22 |
+
"backbone.layers.1.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 23 |
+
"backbone.layers.1.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 24 |
+
"backbone.layers.1.norm.weight": "model-00001-of-00003.safetensors",
|
| 25 |
+
"backbone.layers.10.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 26 |
+
"backbone.layers.10.mixer.D": "model-00001-of-00003.safetensors",
|
| 27 |
+
"backbone.layers.10.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 28 |
+
"backbone.layers.10.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 29 |
+
"backbone.layers.10.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 30 |
+
"backbone.layers.10.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 31 |
+
"backbone.layers.10.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 32 |
+
"backbone.layers.10.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 33 |
+
"backbone.layers.10.norm.weight": "model-00001-of-00003.safetensors",
|
| 34 |
+
"backbone.layers.11.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 35 |
+
"backbone.layers.11.mixer.D": "model-00001-of-00003.safetensors",
|
| 36 |
+
"backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 37 |
+
"backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 38 |
+
"backbone.layers.11.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 39 |
+
"backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 40 |
+
"backbone.layers.11.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 41 |
+
"backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 42 |
+
"backbone.layers.11.norm.weight": "model-00001-of-00003.safetensors",
|
| 43 |
+
"backbone.layers.12.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 44 |
+
"backbone.layers.12.mixer.D": "model-00001-of-00003.safetensors",
|
| 45 |
+
"backbone.layers.12.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 46 |
+
"backbone.layers.12.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 47 |
+
"backbone.layers.12.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 48 |
+
"backbone.layers.12.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 49 |
+
"backbone.layers.12.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 50 |
+
"backbone.layers.12.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 51 |
+
"backbone.layers.12.norm.weight": "model-00001-of-00003.safetensors",
|
| 52 |
+
"backbone.layers.13.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 53 |
+
"backbone.layers.13.mixer.D": "model-00001-of-00003.safetensors",
|
| 54 |
+
"backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 55 |
+
"backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 56 |
+
"backbone.layers.13.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 57 |
+
"backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 58 |
+
"backbone.layers.13.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 59 |
+
"backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 60 |
+
"backbone.layers.13.norm.weight": "model-00001-of-00003.safetensors",
|
| 61 |
+
"backbone.layers.14.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 62 |
+
"backbone.layers.14.mixer.D": "model-00001-of-00003.safetensors",
|
| 63 |
+
"backbone.layers.14.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 64 |
+
"backbone.layers.14.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 65 |
+
"backbone.layers.14.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 66 |
+
"backbone.layers.14.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 67 |
+
"backbone.layers.14.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 68 |
+
"backbone.layers.14.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 69 |
+
"backbone.layers.14.norm.weight": "model-00001-of-00003.safetensors",
|
| 70 |
+
"backbone.layers.15.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 71 |
+
"backbone.layers.15.mixer.D": "model-00001-of-00003.safetensors",
|
| 72 |
+
"backbone.layers.15.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 73 |
+
"backbone.layers.15.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 74 |
+
"backbone.layers.15.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 75 |
+
"backbone.layers.15.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 76 |
+
"backbone.layers.15.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 77 |
+
"backbone.layers.15.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 78 |
+
"backbone.layers.15.norm.weight": "model-00001-of-00003.safetensors",
|
| 79 |
+
"backbone.layers.16.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 80 |
+
"backbone.layers.16.mixer.D": "model-00001-of-00003.safetensors",
|
| 81 |
+
"backbone.layers.16.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 82 |
+
"backbone.layers.16.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 83 |
+
"backbone.layers.16.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 84 |
+
"backbone.layers.16.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 85 |
+
"backbone.layers.16.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 86 |
+
"backbone.layers.16.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 87 |
+
"backbone.layers.16.norm.weight": "model-00001-of-00003.safetensors",
|
| 88 |
+
"backbone.layers.17.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 89 |
+
"backbone.layers.17.mixer.D": "model-00001-of-00003.safetensors",
|
| 90 |
+
"backbone.layers.17.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 91 |
+
"backbone.layers.17.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 92 |
+
"backbone.layers.17.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 93 |
+
"backbone.layers.17.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 94 |
+
"backbone.layers.17.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 95 |
+
"backbone.layers.17.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 96 |
+
"backbone.layers.17.norm.weight": "model-00001-of-00003.safetensors",
|
| 97 |
+
"backbone.layers.18.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 98 |
+
"backbone.layers.18.mixer.D": "model-00001-of-00003.safetensors",
|
| 99 |
+
"backbone.layers.18.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 100 |
+
"backbone.layers.18.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 101 |
+
"backbone.layers.18.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 102 |
+
"backbone.layers.18.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 103 |
+
"backbone.layers.18.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 104 |
+
"backbone.layers.18.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 105 |
+
"backbone.layers.18.norm.weight": "model-00001-of-00003.safetensors",
|
| 106 |
+
"backbone.layers.19.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 107 |
+
"backbone.layers.19.mixer.D": "model-00001-of-00003.safetensors",
|
| 108 |
+
"backbone.layers.19.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 109 |
+
"backbone.layers.19.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 110 |
+
"backbone.layers.19.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 111 |
+
"backbone.layers.19.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 112 |
+
"backbone.layers.19.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 113 |
+
"backbone.layers.19.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 114 |
+
"backbone.layers.19.norm.weight": "model-00001-of-00003.safetensors",
|
| 115 |
+
"backbone.layers.2.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 116 |
+
"backbone.layers.2.mixer.D": "model-00001-of-00003.safetensors",
|
| 117 |
+
"backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 118 |
+
"backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 119 |
+
"backbone.layers.2.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 120 |
+
"backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 121 |
+
"backbone.layers.2.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 122 |
+
"backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 123 |
+
"backbone.layers.2.norm.weight": "model-00001-of-00003.safetensors",
|
| 124 |
+
"backbone.layers.20.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 125 |
+
"backbone.layers.20.mixer.D": "model-00001-of-00003.safetensors",
|
| 126 |
+
"backbone.layers.20.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 127 |
+
"backbone.layers.20.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 128 |
+
"backbone.layers.20.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 129 |
+
"backbone.layers.20.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 130 |
+
"backbone.layers.20.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 131 |
+
"backbone.layers.20.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 132 |
+
"backbone.layers.20.norm.weight": "model-00001-of-00003.safetensors",
|
| 133 |
+
"backbone.layers.21.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 134 |
+
"backbone.layers.21.mixer.D": "model-00001-of-00003.safetensors",
|
| 135 |
+
"backbone.layers.21.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 136 |
+
"backbone.layers.21.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 137 |
+
"backbone.layers.21.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 138 |
+
"backbone.layers.21.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 139 |
+
"backbone.layers.21.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 140 |
+
"backbone.layers.21.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 141 |
+
"backbone.layers.21.norm.weight": "model-00001-of-00003.safetensors",
|
| 142 |
+
"backbone.layers.22.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 143 |
+
"backbone.layers.22.mixer.D": "model-00002-of-00003.safetensors",
|
| 144 |
+
"backbone.layers.22.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 145 |
+
"backbone.layers.22.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 146 |
+
"backbone.layers.22.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 147 |
+
"backbone.layers.22.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 148 |
+
"backbone.layers.22.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 149 |
+
"backbone.layers.22.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 150 |
+
"backbone.layers.22.norm.weight": "model-00002-of-00003.safetensors",
|
| 151 |
+
"backbone.layers.23.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 152 |
+
"backbone.layers.23.mixer.D": "model-00002-of-00003.safetensors",
|
| 153 |
+
"backbone.layers.23.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 154 |
+
"backbone.layers.23.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 155 |
+
"backbone.layers.23.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 156 |
+
"backbone.layers.23.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 157 |
+
"backbone.layers.23.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 158 |
+
"backbone.layers.23.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 159 |
+
"backbone.layers.23.norm.weight": "model-00002-of-00003.safetensors",
|
| 160 |
+
"backbone.layers.24.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 161 |
+
"backbone.layers.24.mixer.D": "model-00002-of-00003.safetensors",
|
| 162 |
+
"backbone.layers.24.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 163 |
+
"backbone.layers.24.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 164 |
+
"backbone.layers.24.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 165 |
+
"backbone.layers.24.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 166 |
+
"backbone.layers.24.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 167 |
+
"backbone.layers.24.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 168 |
+
"backbone.layers.24.norm.weight": "model-00002-of-00003.safetensors",
|
| 169 |
+
"backbone.layers.25.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 170 |
+
"backbone.layers.25.mixer.D": "model-00002-of-00003.safetensors",
|
| 171 |
+
"backbone.layers.25.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 172 |
+
"backbone.layers.25.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 173 |
+
"backbone.layers.25.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 174 |
+
"backbone.layers.25.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 175 |
+
"backbone.layers.25.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 176 |
+
"backbone.layers.25.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 177 |
+
"backbone.layers.25.norm.weight": "model-00002-of-00003.safetensors",
|
| 178 |
+
"backbone.layers.26.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 179 |
+
"backbone.layers.26.mixer.D": "model-00002-of-00003.safetensors",
|
| 180 |
+
"backbone.layers.26.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 181 |
+
"backbone.layers.26.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 182 |
+
"backbone.layers.26.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 183 |
+
"backbone.layers.26.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 184 |
+
"backbone.layers.26.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 185 |
+
"backbone.layers.26.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 186 |
+
"backbone.layers.26.norm.weight": "model-00002-of-00003.safetensors",
|
| 187 |
+
"backbone.layers.27.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 188 |
+
"backbone.layers.27.mixer.D": "model-00002-of-00003.safetensors",
|
| 189 |
+
"backbone.layers.27.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 190 |
+
"backbone.layers.27.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 191 |
+
"backbone.layers.27.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 192 |
+
"backbone.layers.27.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 193 |
+
"backbone.layers.27.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 194 |
+
"backbone.layers.27.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 195 |
+
"backbone.layers.27.norm.weight": "model-00002-of-00003.safetensors",
|
| 196 |
+
"backbone.layers.28.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 197 |
+
"backbone.layers.28.mixer.D": "model-00002-of-00003.safetensors",
|
| 198 |
+
"backbone.layers.28.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 199 |
+
"backbone.layers.28.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 200 |
+
"backbone.layers.28.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 201 |
+
"backbone.layers.28.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 202 |
+
"backbone.layers.28.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 203 |
+
"backbone.layers.28.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 204 |
+
"backbone.layers.28.norm.weight": "model-00002-of-00003.safetensors",
|
| 205 |
+
"backbone.layers.29.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 206 |
+
"backbone.layers.29.mixer.D": "model-00002-of-00003.safetensors",
|
| 207 |
+
"backbone.layers.29.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 208 |
+
"backbone.layers.29.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 209 |
+
"backbone.layers.29.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 210 |
+
"backbone.layers.29.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 211 |
+
"backbone.layers.29.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 212 |
+
"backbone.layers.29.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 213 |
+
"backbone.layers.29.norm.weight": "model-00002-of-00003.safetensors",
|
| 214 |
+
"backbone.layers.3.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 215 |
+
"backbone.layers.3.mixer.D": "model-00001-of-00003.safetensors",
|
| 216 |
+
"backbone.layers.3.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 217 |
+
"backbone.layers.3.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 218 |
+
"backbone.layers.3.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 219 |
+
"backbone.layers.3.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 220 |
+
"backbone.layers.3.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 221 |
+
"backbone.layers.3.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 222 |
+
"backbone.layers.3.norm.weight": "model-00001-of-00003.safetensors",
|
| 223 |
+
"backbone.layers.30.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 224 |
+
"backbone.layers.30.mixer.D": "model-00002-of-00003.safetensors",
|
| 225 |
+
"backbone.layers.30.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 226 |
+
"backbone.layers.30.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 227 |
+
"backbone.layers.30.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 228 |
+
"backbone.layers.30.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 229 |
+
"backbone.layers.30.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 230 |
+
"backbone.layers.30.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 231 |
+
"backbone.layers.30.norm.weight": "model-00002-of-00003.safetensors",
|
| 232 |
+
"backbone.layers.31.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 233 |
+
"backbone.layers.31.mixer.D": "model-00002-of-00003.safetensors",
|
| 234 |
+
"backbone.layers.31.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 235 |
+
"backbone.layers.31.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 236 |
+
"backbone.layers.31.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 237 |
+
"backbone.layers.31.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 238 |
+
"backbone.layers.31.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 239 |
+
"backbone.layers.31.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 240 |
+
"backbone.layers.31.norm.weight": "model-00002-of-00003.safetensors",
|
| 241 |
+
"backbone.layers.32.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 242 |
+
"backbone.layers.32.mixer.D": "model-00002-of-00003.safetensors",
|
| 243 |
+
"backbone.layers.32.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 244 |
+
"backbone.layers.32.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 245 |
+
"backbone.layers.32.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 246 |
+
"backbone.layers.32.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 247 |
+
"backbone.layers.32.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 248 |
+
"backbone.layers.32.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 249 |
+
"backbone.layers.32.norm.weight": "model-00002-of-00003.safetensors",
|
| 250 |
+
"backbone.layers.33.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 251 |
+
"backbone.layers.33.mixer.D": "model-00002-of-00003.safetensors",
|
| 252 |
+
"backbone.layers.33.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 253 |
+
"backbone.layers.33.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 254 |
+
"backbone.layers.33.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 255 |
+
"backbone.layers.33.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 256 |
+
"backbone.layers.33.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 257 |
+
"backbone.layers.33.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 258 |
+
"backbone.layers.33.norm.weight": "model-00002-of-00003.safetensors",
|
| 259 |
+
"backbone.layers.34.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 260 |
+
"backbone.layers.34.mixer.D": "model-00002-of-00003.safetensors",
|
| 261 |
+
"backbone.layers.34.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 262 |
+
"backbone.layers.34.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 263 |
+
"backbone.layers.34.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 264 |
+
"backbone.layers.34.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 265 |
+
"backbone.layers.34.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 266 |
+
"backbone.layers.34.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 267 |
+
"backbone.layers.34.norm.weight": "model-00002-of-00003.safetensors",
|
| 268 |
+
"backbone.layers.35.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 269 |
+
"backbone.layers.35.mixer.D": "model-00002-of-00003.safetensors",
|
| 270 |
+
"backbone.layers.35.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 271 |
+
"backbone.layers.35.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 272 |
+
"backbone.layers.35.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 273 |
+
"backbone.layers.35.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 274 |
+
"backbone.layers.35.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 275 |
+
"backbone.layers.35.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 276 |
+
"backbone.layers.35.norm.weight": "model-00002-of-00003.safetensors",
|
| 277 |
+
"backbone.layers.36.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 278 |
+
"backbone.layers.36.mixer.D": "model-00002-of-00003.safetensors",
|
| 279 |
+
"backbone.layers.36.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 280 |
+
"backbone.layers.36.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 281 |
+
"backbone.layers.36.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 282 |
+
"backbone.layers.36.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 283 |
+
"backbone.layers.36.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 284 |
+
"backbone.layers.36.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 285 |
+
"backbone.layers.36.norm.weight": "model-00002-of-00003.safetensors",
|
| 286 |
+
"backbone.layers.37.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 287 |
+
"backbone.layers.37.mixer.D": "model-00002-of-00003.safetensors",
|
| 288 |
+
"backbone.layers.37.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 289 |
+
"backbone.layers.37.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 290 |
+
"backbone.layers.37.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 291 |
+
"backbone.layers.37.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 292 |
+
"backbone.layers.37.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 293 |
+
"backbone.layers.37.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 294 |
+
"backbone.layers.37.norm.weight": "model-00002-of-00003.safetensors",
|
| 295 |
+
"backbone.layers.38.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 296 |
+
"backbone.layers.38.mixer.D": "model-00002-of-00003.safetensors",
|
| 297 |
+
"backbone.layers.38.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 298 |
+
"backbone.layers.38.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 299 |
+
"backbone.layers.38.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 300 |
+
"backbone.layers.38.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 301 |
+
"backbone.layers.38.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 302 |
+
"backbone.layers.38.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 303 |
+
"backbone.layers.38.norm.weight": "model-00002-of-00003.safetensors",
|
| 304 |
+
"backbone.layers.39.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 305 |
+
"backbone.layers.39.mixer.D": "model-00002-of-00003.safetensors",
|
| 306 |
+
"backbone.layers.39.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 307 |
+
"backbone.layers.39.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 308 |
+
"backbone.layers.39.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 309 |
+
"backbone.layers.39.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 310 |
+
"backbone.layers.39.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 311 |
+
"backbone.layers.39.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 312 |
+
"backbone.layers.39.norm.weight": "model-00002-of-00003.safetensors",
|
| 313 |
+
"backbone.layers.4.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 314 |
+
"backbone.layers.4.mixer.D": "model-00001-of-00003.safetensors",
|
| 315 |
+
"backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 316 |
+
"backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 317 |
+
"backbone.layers.4.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 318 |
+
"backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 319 |
+
"backbone.layers.4.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 320 |
+
"backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 321 |
+
"backbone.layers.4.norm.weight": "model-00001-of-00003.safetensors",
|
| 322 |
+
"backbone.layers.40.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 323 |
+
"backbone.layers.40.mixer.D": "model-00002-of-00003.safetensors",
|
| 324 |
+
"backbone.layers.40.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 325 |
+
"backbone.layers.40.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 326 |
+
"backbone.layers.40.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 327 |
+
"backbone.layers.40.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 328 |
+
"backbone.layers.40.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 329 |
+
"backbone.layers.40.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 330 |
+
"backbone.layers.40.norm.weight": "model-00002-of-00003.safetensors",
|
| 331 |
+
"backbone.layers.41.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 332 |
+
"backbone.layers.41.mixer.D": "model-00002-of-00003.safetensors",
|
| 333 |
+
"backbone.layers.41.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 334 |
+
"backbone.layers.41.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 335 |
+
"backbone.layers.41.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 336 |
+
"backbone.layers.41.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 337 |
+
"backbone.layers.41.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 338 |
+
"backbone.layers.41.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 339 |
+
"backbone.layers.41.norm.weight": "model-00002-of-00003.safetensors",
|
| 340 |
+
"backbone.layers.42.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 341 |
+
"backbone.layers.42.mixer.D": "model-00002-of-00003.safetensors",
|
| 342 |
+
"backbone.layers.42.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 343 |
+
"backbone.layers.42.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 344 |
+
"backbone.layers.42.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 345 |
+
"backbone.layers.42.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 346 |
+
"backbone.layers.42.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 347 |
+
"backbone.layers.42.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
| 348 |
+
"backbone.layers.42.norm.weight": "model-00002-of-00003.safetensors",
|
| 349 |
+
"backbone.layers.43.mixer.A_log": "model-00002-of-00003.safetensors",
|
| 350 |
+
"backbone.layers.43.mixer.D": "model-00002-of-00003.safetensors",
|
| 351 |
+
"backbone.layers.43.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
| 352 |
+
"backbone.layers.43.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
| 353 |
+
"backbone.layers.43.mixer.dt_bias": "model-00002-of-00003.safetensors",
|
| 354 |
+
"backbone.layers.43.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
| 355 |
+
"backbone.layers.43.mixer.norm.weight": "model-00002-of-00003.safetensors",
|
| 356 |
+
"backbone.layers.43.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 357 |
+
"backbone.layers.43.norm.weight": "model-00002-of-00003.safetensors",
|
| 358 |
+
"backbone.layers.44.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 359 |
+
"backbone.layers.44.mixer.D": "model-00003-of-00003.safetensors",
|
| 360 |
+
"backbone.layers.44.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 361 |
+
"backbone.layers.44.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 362 |
+
"backbone.layers.44.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 363 |
+
"backbone.layers.44.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 364 |
+
"backbone.layers.44.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 365 |
+
"backbone.layers.44.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 366 |
+
"backbone.layers.44.norm.weight": "model-00003-of-00003.safetensors",
|
| 367 |
+
"backbone.layers.45.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 368 |
+
"backbone.layers.45.mixer.D": "model-00003-of-00003.safetensors",
|
| 369 |
+
"backbone.layers.45.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 370 |
+
"backbone.layers.45.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 371 |
+
"backbone.layers.45.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 372 |
+
"backbone.layers.45.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 373 |
+
"backbone.layers.45.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 374 |
+
"backbone.layers.45.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 375 |
+
"backbone.layers.45.norm.weight": "model-00003-of-00003.safetensors",
|
| 376 |
+
"backbone.layers.46.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 377 |
+
"backbone.layers.46.mixer.D": "model-00003-of-00003.safetensors",
|
| 378 |
+
"backbone.layers.46.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 379 |
+
"backbone.layers.46.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 380 |
+
"backbone.layers.46.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 381 |
+
"backbone.layers.46.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 382 |
+
"backbone.layers.46.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 383 |
+
"backbone.layers.46.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 384 |
+
"backbone.layers.46.norm.weight": "model-00003-of-00003.safetensors",
|
| 385 |
+
"backbone.layers.47.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 386 |
+
"backbone.layers.47.mixer.D": "model-00003-of-00003.safetensors",
|
| 387 |
+
"backbone.layers.47.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 388 |
+
"backbone.layers.47.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 389 |
+
"backbone.layers.47.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 390 |
+
"backbone.layers.47.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 391 |
+
"backbone.layers.47.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 392 |
+
"backbone.layers.47.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 393 |
+
"backbone.layers.47.norm.weight": "model-00003-of-00003.safetensors",
|
| 394 |
+
"backbone.layers.48.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 395 |
+
"backbone.layers.48.mixer.D": "model-00003-of-00003.safetensors",
|
| 396 |
+
"backbone.layers.48.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 397 |
+
"backbone.layers.48.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 398 |
+
"backbone.layers.48.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 399 |
+
"backbone.layers.48.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 400 |
+
"backbone.layers.48.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 401 |
+
"backbone.layers.48.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 402 |
+
"backbone.layers.48.norm.weight": "model-00003-of-00003.safetensors",
|
| 403 |
+
"backbone.layers.49.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 404 |
+
"backbone.layers.49.mixer.D": "model-00003-of-00003.safetensors",
|
| 405 |
+
"backbone.layers.49.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 406 |
+
"backbone.layers.49.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 407 |
+
"backbone.layers.49.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 408 |
+
"backbone.layers.49.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 409 |
+
"backbone.layers.49.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 410 |
+
"backbone.layers.49.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 411 |
+
"backbone.layers.49.norm.weight": "model-00003-of-00003.safetensors",
|
| 412 |
+
"backbone.layers.5.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 413 |
+
"backbone.layers.5.mixer.D": "model-00001-of-00003.safetensors",
|
| 414 |
+
"backbone.layers.5.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 415 |
+
"backbone.layers.5.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 416 |
+
"backbone.layers.5.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 417 |
+
"backbone.layers.5.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 418 |
+
"backbone.layers.5.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 419 |
+
"backbone.layers.5.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 420 |
+
"backbone.layers.5.norm.weight": "model-00001-of-00003.safetensors",
|
| 421 |
+
"backbone.layers.50.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 422 |
+
"backbone.layers.50.mixer.D": "model-00003-of-00003.safetensors",
|
| 423 |
+
"backbone.layers.50.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 424 |
+
"backbone.layers.50.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 425 |
+
"backbone.layers.50.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 426 |
+
"backbone.layers.50.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 427 |
+
"backbone.layers.50.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 428 |
+
"backbone.layers.50.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 429 |
+
"backbone.layers.50.norm.weight": "model-00003-of-00003.safetensors",
|
| 430 |
+
"backbone.layers.51.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 431 |
+
"backbone.layers.51.mixer.D": "model-00003-of-00003.safetensors",
|
| 432 |
+
"backbone.layers.51.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 433 |
+
"backbone.layers.51.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 434 |
+
"backbone.layers.51.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 435 |
+
"backbone.layers.51.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 436 |
+
"backbone.layers.51.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 437 |
+
"backbone.layers.51.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 438 |
+
"backbone.layers.51.norm.weight": "model-00003-of-00003.safetensors",
|
| 439 |
+
"backbone.layers.52.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 440 |
+
"backbone.layers.52.mixer.D": "model-00003-of-00003.safetensors",
|
| 441 |
+
"backbone.layers.52.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 442 |
+
"backbone.layers.52.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 443 |
+
"backbone.layers.52.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 444 |
+
"backbone.layers.52.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 445 |
+
"backbone.layers.52.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 446 |
+
"backbone.layers.52.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 447 |
+
"backbone.layers.52.norm.weight": "model-00003-of-00003.safetensors",
|
| 448 |
+
"backbone.layers.53.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 449 |
+
"backbone.layers.53.mixer.D": "model-00003-of-00003.safetensors",
|
| 450 |
+
"backbone.layers.53.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 451 |
+
"backbone.layers.53.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 452 |
+
"backbone.layers.53.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 453 |
+
"backbone.layers.53.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 454 |
+
"backbone.layers.53.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 455 |
+
"backbone.layers.53.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 456 |
+
"backbone.layers.53.norm.weight": "model-00003-of-00003.safetensors",
|
| 457 |
+
"backbone.layers.54.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 458 |
+
"backbone.layers.54.mixer.D": "model-00003-of-00003.safetensors",
|
| 459 |
+
"backbone.layers.54.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 460 |
+
"backbone.layers.54.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 461 |
+
"backbone.layers.54.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 462 |
+
"backbone.layers.54.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 463 |
+
"backbone.layers.54.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 464 |
+
"backbone.layers.54.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 465 |
+
"backbone.layers.54.norm.weight": "model-00003-of-00003.safetensors",
|
| 466 |
+
"backbone.layers.55.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 467 |
+
"backbone.layers.55.mixer.D": "model-00003-of-00003.safetensors",
|
| 468 |
+
"backbone.layers.55.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 469 |
+
"backbone.layers.55.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 470 |
+
"backbone.layers.55.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 471 |
+
"backbone.layers.55.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 472 |
+
"backbone.layers.55.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 473 |
+
"backbone.layers.55.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 474 |
+
"backbone.layers.55.norm.weight": "model-00003-of-00003.safetensors",
|
| 475 |
+
"backbone.layers.56.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 476 |
+
"backbone.layers.56.mixer.D": "model-00003-of-00003.safetensors",
|
| 477 |
+
"backbone.layers.56.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 478 |
+
"backbone.layers.56.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 479 |
+
"backbone.layers.56.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 480 |
+
"backbone.layers.56.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 481 |
+
"backbone.layers.56.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 482 |
+
"backbone.layers.56.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 483 |
+
"backbone.layers.56.norm.weight": "model-00003-of-00003.safetensors",
|
| 484 |
+
"backbone.layers.57.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 485 |
+
"backbone.layers.57.mixer.D": "model-00003-of-00003.safetensors",
|
| 486 |
+
"backbone.layers.57.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 487 |
+
"backbone.layers.57.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 488 |
+
"backbone.layers.57.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 489 |
+
"backbone.layers.57.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 490 |
+
"backbone.layers.57.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 491 |
+
"backbone.layers.57.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 492 |
+
"backbone.layers.57.norm.weight": "model-00003-of-00003.safetensors",
|
| 493 |
+
"backbone.layers.58.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 494 |
+
"backbone.layers.58.mixer.D": "model-00003-of-00003.safetensors",
|
| 495 |
+
"backbone.layers.58.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 496 |
+
"backbone.layers.58.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 497 |
+
"backbone.layers.58.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 498 |
+
"backbone.layers.58.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 499 |
+
"backbone.layers.58.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 500 |
+
"backbone.layers.58.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 501 |
+
"backbone.layers.58.norm.weight": "model-00003-of-00003.safetensors",
|
| 502 |
+
"backbone.layers.59.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 503 |
+
"backbone.layers.59.mixer.D": "model-00003-of-00003.safetensors",
|
| 504 |
+
"backbone.layers.59.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 505 |
+
"backbone.layers.59.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 506 |
+
"backbone.layers.59.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 507 |
+
"backbone.layers.59.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 508 |
+
"backbone.layers.59.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 509 |
+
"backbone.layers.59.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 510 |
+
"backbone.layers.59.norm.weight": "model-00003-of-00003.safetensors",
|
| 511 |
+
"backbone.layers.6.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 512 |
+
"backbone.layers.6.mixer.D": "model-00001-of-00003.safetensors",
|
| 513 |
+
"backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 514 |
+
"backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 515 |
+
"backbone.layers.6.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 516 |
+
"backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 517 |
+
"backbone.layers.6.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 518 |
+
"backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 519 |
+
"backbone.layers.6.norm.weight": "model-00001-of-00003.safetensors",
|
| 520 |
+
"backbone.layers.60.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 521 |
+
"backbone.layers.60.mixer.D": "model-00003-of-00003.safetensors",
|
| 522 |
+
"backbone.layers.60.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 523 |
+
"backbone.layers.60.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 524 |
+
"backbone.layers.60.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 525 |
+
"backbone.layers.60.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 526 |
+
"backbone.layers.60.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 527 |
+
"backbone.layers.60.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 528 |
+
"backbone.layers.60.norm.weight": "model-00003-of-00003.safetensors",
|
| 529 |
+
"backbone.layers.61.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 530 |
+
"backbone.layers.61.mixer.D": "model-00003-of-00003.safetensors",
|
| 531 |
+
"backbone.layers.61.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 532 |
+
"backbone.layers.61.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 533 |
+
"backbone.layers.61.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 534 |
+
"backbone.layers.61.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 535 |
+
"backbone.layers.61.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 536 |
+
"backbone.layers.61.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 537 |
+
"backbone.layers.61.norm.weight": "model-00003-of-00003.safetensors",
|
| 538 |
+
"backbone.layers.62.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 539 |
+
"backbone.layers.62.mixer.D": "model-00003-of-00003.safetensors",
|
| 540 |
+
"backbone.layers.62.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 541 |
+
"backbone.layers.62.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 542 |
+
"backbone.layers.62.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 543 |
+
"backbone.layers.62.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 544 |
+
"backbone.layers.62.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 545 |
+
"backbone.layers.62.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 546 |
+
"backbone.layers.62.norm.weight": "model-00003-of-00003.safetensors",
|
| 547 |
+
"backbone.layers.63.mixer.A_log": "model-00003-of-00003.safetensors",
|
| 548 |
+
"backbone.layers.63.mixer.D": "model-00003-of-00003.safetensors",
|
| 549 |
+
"backbone.layers.63.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
| 550 |
+
"backbone.layers.63.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
| 551 |
+
"backbone.layers.63.mixer.dt_bias": "model-00003-of-00003.safetensors",
|
| 552 |
+
"backbone.layers.63.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
| 553 |
+
"backbone.layers.63.mixer.norm.weight": "model-00003-of-00003.safetensors",
|
| 554 |
+
"backbone.layers.63.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
| 555 |
+
"backbone.layers.63.norm.weight": "model-00003-of-00003.safetensors",
|
| 556 |
+
"backbone.layers.7.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 557 |
+
"backbone.layers.7.mixer.D": "model-00001-of-00003.safetensors",
|
| 558 |
+
"backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 559 |
+
"backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 560 |
+
"backbone.layers.7.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 561 |
+
"backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 562 |
+
"backbone.layers.7.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 563 |
+
"backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 564 |
+
"backbone.layers.7.norm.weight": "model-00001-of-00003.safetensors",
|
| 565 |
+
"backbone.layers.8.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 566 |
+
"backbone.layers.8.mixer.D": "model-00001-of-00003.safetensors",
|
| 567 |
+
"backbone.layers.8.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 568 |
+
"backbone.layers.8.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 569 |
+
"backbone.layers.8.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 570 |
+
"backbone.layers.8.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 571 |
+
"backbone.layers.8.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 572 |
+
"backbone.layers.8.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 573 |
+
"backbone.layers.8.norm.weight": "model-00001-of-00003.safetensors",
|
| 574 |
+
"backbone.layers.9.mixer.A_log": "model-00001-of-00003.safetensors",
|
| 575 |
+
"backbone.layers.9.mixer.D": "model-00001-of-00003.safetensors",
|
| 576 |
+
"backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
| 577 |
+
"backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
| 578 |
+
"backbone.layers.9.mixer.dt_bias": "model-00001-of-00003.safetensors",
|
| 579 |
+
"backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
| 580 |
+
"backbone.layers.9.mixer.norm.weight": "model-00001-of-00003.safetensors",
|
| 581 |
+
"backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
| 582 |
+
"backbone.layers.9.norm.weight": "model-00001-of-00003.safetensors",
|
| 583 |
+
"backbone.norm_f.weight": "model-00003-of-00003.safetensors",
|
| 584 |
+
"lm_head.weight": "model-00003-of-00003.safetensors"
|
| 585 |
+
}
|
| 586 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "</s>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<unk>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer.model
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
|
| 3 |
+
size 587583
|
tokenizer_config.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|