Upload folder using huggingface_hub
Browse files- README.md +130 -0
- config.json +43 -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
- requirements.txt +186 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +0 -0
README.md
ADDED
@@ -0,0 +1,130 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# **Scaling Reasoning without Attention**
|
2 |
+
|
3 |
+
|
4 |
+
[](http://arxiv.org/abs/2505.22425)
|
5 |
+
[](https://github.com/inclusionAI/PromptCoT)
|
6 |
+
|
7 |
+
---
|
8 |
+
|
9 |
+
## 🚀 Overview
|
10 |
+
|
11 |
+
**PromptCoT-Mamba** establishes the first **attention-free foundation model** capable of surpassing strong Transformer baselines across a broad suite of competition-level math and code reasoning tasks. Built on the **Mamba-2** architecture and trained through a structured, two-stage curriculum using the [**PromptCoT**](http://arxiv.org/abs/2503.02324) pipeline, it delivers **high accuracy with constant-memory inference**, eliminating the need for KV caching.
|
12 |
+
|
13 |
+
|
14 |
+
---
|
15 |
+
|
16 |
+
## 📈 Key Results
|
17 |
+
|
18 |
+
### 🔹 General Performance
|
19 |
+
|
20 |
+
| Model | MATH-500 | AIME 24 | AIME 25 | OlympiadBench | HumanEval | HumanEval+ | Livecodebench |
|
21 |
+
| ---------------------- | -------- | -------- | -------- | ------------- | --------- | ---------- | ------------- |
|
22 |
+
| **PromptCoT-Mamba-7B** | 84.6 | **35.2** | **24.6** | 50.7 | 81.7 | 75.0 | **29.9** |
|
23 |
+
| Gemma3-27B | **89.0** | 32.6 | 24.0 | **54.2** | **86.0** | **78.0** | 26.9 |
|
24 |
+
| Gemma3-12B | 83.8 | 22.9 | 19.2 | 49.9 | 81.1 | 73.2 | 22.2 |
|
25 |
+
| Sky-T1-7B | 85.0 | 19.2 | 19.2 | 49.2 | 41.5 | 37.2 | 18.3 |
|
26 |
+
| S1.1-7B | 82.0 | 19.2 | 17.5 | 43.1 | 64.0 | 56.7 | 13.3 |
|
27 |
+
| Bespoke-Stratos-7B | 81.2 | 18.3 | 16.3 | 45.0 | 73.2 | 68.3 | 8.6 |
|
28 |
+
| Nemotron-H-8B | 77.6 | -- | -- | -- | 79.3 | 74.4 | -- |
|
29 |
+
| M1-3B | 81.7 | 23.0 | 22.0 | 43.6 | -- | -- | -- |
|
30 |
+
|
31 |
+
> 🔍 **PromptCoT-Mamba-7B** consistently outperforms all 7B-scale Transformer and hybrid Mamba-Transformer baselines across all tasks.
|
32 |
+
|
33 |
+
---
|
34 |
+
|
35 |
+
### 🔹 Math Specialization vs. Generalist
|
36 |
+
|
37 |
+
| Model | MATH-500 | AIME 24 | AIME 25 | OlympiadBench | HumanEval | HumanEval+ | Livecodebench |
|
38 |
+
| --------------------------- | -------- | -------- | -------- | ------------- | --------- | ---------- | ------------- |
|
39 |
+
| **PromptCoT-Mamba-Math-7B** | **88.0** | **42.9** | **30.8** | **52.1** | 71.3 | 66.5 | 20.3 |
|
40 |
+
| PromptCoT-Mamba-7B | 84.6 | 35.2 | 24.6 | 50.7 | **81.7** | **75.0** | **29.9** |
|
41 |
+
|
42 |
+
> 🎯 The math-specialized variant improves AIME 24 by **+7.7%** and AIME 25 by **+6.2%**, with a slight trade-off in code-related performance.
|
43 |
+
|
44 |
+
---
|
45 |
+
|
46 |
+
### ⚡ Inference Efficiency
|
47 |
+
|
48 |
+
Using `vLLM` under constrained memory, PromptCoT-Mamba-7B demonstrates substantial speedups over the S1.1-7B Transformer baseline:
|
49 |
+
|
50 |
+
* 💡 **3.66× faster** at long-sequence generation on **24GB GPU**
|
51 |
+
* 💡 **1.69× faster** under **72GB memory**
|
52 |
+
|
53 |
+
> ⚙️ Practical for cost-sensitive or long-context inference workloads at scale.
|
54 |
+
|
55 |
+
---
|
56 |
+
|
57 |
+
## 🧪 Quick Start
|
58 |
+
|
59 |
+
### 🔧 Install Requirements
|
60 |
+
|
61 |
+
```bash
|
62 |
+
pip install transformers vllm torch accelerate
|
63 |
+
```
|
64 |
+
|
65 |
+
### 🧠 Load and Run the Model
|
66 |
+
|
67 |
+
```python
|
68 |
+
from transformers import AutoModelForCausalLM, AutoTokenizer
|
69 |
+
|
70 |
+
model_name = "xl-zhao/PromptCoT-Mamba-7B"
|
71 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
72 |
+
model = AutoModelForCausalLM.from_pretrained(model_name).to("cuda")
|
73 |
+
|
74 |
+
problem_statement = (
|
75 |
+
"A robe takes 2 bolts of blue fiber and half that much white fiber. How many bolts in total does it take?"
|
76 |
+
)
|
77 |
+
|
78 |
+
prompt = (
|
79 |
+
f"<|im_start|>user\n{problem_statement}\nPlease reason step by step, and put your final answer within \\boxed{{}}.<|im_end|>\n"
|
80 |
+
"<|im_start|>assistant\n"
|
81 |
+
)
|
82 |
+
|
83 |
+
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
|
84 |
+
|
85 |
+
with torch.no_grad():
|
86 |
+
output = model.generate(**inputs, max_length=65536, temperature=0.8)
|
87 |
+
|
88 |
+
generated_solution = tokenizer.decode(output[0], skip_special_tokens=True)
|
89 |
+
print(generated_solution)
|
90 |
+
```
|
91 |
+
|
92 |
+
---
|
93 |
+
|
94 |
+
## ⚡ Fast Inference with vLLM
|
95 |
+
|
96 |
+
```python
|
97 |
+
from vllm import LLM, SamplingParams
|
98 |
+
|
99 |
+
model_name = "xl-zhao/PromptCoT-Mamba-7B"
|
100 |
+
llm = LLM(model=model_name, tensor_parallel_size=1)
|
101 |
+
|
102 |
+
problem_statement = (
|
103 |
+
"A robe takes 2 bolts of blue fiber and half that much white fiber. How many bolts in total does it take?"
|
104 |
+
)
|
105 |
+
|
106 |
+
prompt = (
|
107 |
+
f"<|im_start|>user\n{problem_statement}\nPlease reason step by step, and put your final answer within \\boxed{{}}.<|im_end|>\n"
|
108 |
+
"<|im_start|>assistant\n"
|
109 |
+
)
|
110 |
+
|
111 |
+
sampling_params = SamplingParams(temperature=0.8, max_tokens=65536)
|
112 |
+
outputs = llm.generate([prompt], sampling_params)
|
113 |
+
|
114 |
+
print(outputs[0].outputs[0].text)
|
115 |
+
```
|
116 |
+
|
117 |
+
---
|
118 |
+
|
119 |
+
## 📜 Citation
|
120 |
+
|
121 |
+
```bibtex
|
122 |
+
@article{zhao2025scaling,
|
123 |
+
author = {Xueliang Zhao and Wei Wu and Lingpeng Kong},
|
124 |
+
title = {Scaling Reasoning without Attention},
|
125 |
+
journal = {arXiv preprint arXiv:2505.22425},
|
126 |
+
year = {2025},
|
127 |
+
url = {https://arxiv.org/abs/2505.22425}
|
128 |
+
}
|
129 |
+
```
|
130 |
+
|
config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architectures": [
|
3 |
+
"Mamba2ForCausalLM"
|
4 |
+
],
|
5 |
+
"bos_token_id": 0,
|
6 |
+
"chunk_size": 256,
|
7 |
+
"conv_kernel": 4,
|
8 |
+
"eos_token_id": 0,
|
9 |
+
"expand": 2,
|
10 |
+
"head_dim": 64,
|
11 |
+
"hidden_act": "silu",
|
12 |
+
"hidden_size": 4096,
|
13 |
+
"initializer_range": 0.1,
|
14 |
+
"intermediate_size": 8192,
|
15 |
+
"layer_norm_epsilon": 1e-05,
|
16 |
+
"model_type": "mamba2",
|
17 |
+
"n_groups": 8,
|
18 |
+
"norm_before_gate": true,
|
19 |
+
"num_heads": 128,
|
20 |
+
"num_hidden_layers": 64,
|
21 |
+
"pad_token_id": 0,
|
22 |
+
"rescale_prenorm_residual": false,
|
23 |
+
"residual_in_fp32": true,
|
24 |
+
"rms_norm": true,
|
25 |
+
"state_size": 128,
|
26 |
+
"tie_word_embeddings": false,
|
27 |
+
"time_step_floor": 0.0001,
|
28 |
+
"time_step_init_scheme": "random",
|
29 |
+
"time_step_limit": [
|
30 |
+
0.0,
|
31 |
+
Infinity
|
32 |
+
],
|
33 |
+
"time_step_max": 0.1,
|
34 |
+
"time_step_min": 0.001,
|
35 |
+
"time_step_rank": 256,
|
36 |
+
"time_step_scale": 1.0,
|
37 |
+
"torch_dtype": "bfloat16",
|
38 |
+
"transformers_version": "4.49.0",
|
39 |
+
"use_bias": false,
|
40 |
+
"use_cache": false,
|
41 |
+
"use_conv_bias": true,
|
42 |
+
"vocab_size": 32768
|
43 |
+
}
|
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": "4.49.0"
|
7 |
+
}
|
model-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:114bed2638f47387c22f9f74eebed655c969e260282512829c4b0ecf15ccbd8d
|
3 |
+
size 4873450856
|
model-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e6f13bbdd9691e0a78bcf9d02fd42b9506b077db0c80e63822d3f8b3a32d0c8
|
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:edb717707a82f8e42e96aeab68e9cd095e1f34688c85187526cf9049278fada8
|
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 |
+
}
|
requirements.txt
ADDED
@@ -0,0 +1,186 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
accelerate==1.6.0
|
2 |
+
addict==2.4.0
|
3 |
+
aiohappyeyeballs==2.6.1
|
4 |
+
aiohttp==3.11.14
|
5 |
+
aiohttp-cors==0.8.0
|
6 |
+
aiosignal==1.3.2
|
7 |
+
airportsdata==20250224
|
8 |
+
annotated-types==0.7.0
|
9 |
+
anyio==4.9.0
|
10 |
+
astor==0.8.1
|
11 |
+
attrs==25.3.0
|
12 |
+
blake3==1.0.4
|
13 |
+
cachetools==5.5.2
|
14 |
+
causal-conv1d==1.5.0
|
15 |
+
certifi==2025.1.31
|
16 |
+
charset-normalizer==3.4.1
|
17 |
+
click==8.1.8
|
18 |
+
cloudpickle==3.1.1
|
19 |
+
cmake==3.31.6
|
20 |
+
colorful==0.5.6
|
21 |
+
compressed-tensors==0.9.1
|
22 |
+
cupy-cuda12x==13.4.1
|
23 |
+
datasets==3.2.0
|
24 |
+
deepspeed==0.16.7
|
25 |
+
depyf==0.18.0
|
26 |
+
dill==0.3.8
|
27 |
+
diskcache==5.6.3
|
28 |
+
distlib==0.3.9
|
29 |
+
distro==1.9.0
|
30 |
+
dnspython==2.7.0
|
31 |
+
einops==0.8.1
|
32 |
+
email_validator==2.2.0
|
33 |
+
fastapi==0.115.11
|
34 |
+
fastapi-cli==0.0.7
|
35 |
+
fastrlock==0.8.3
|
36 |
+
filelock==3.18.0
|
37 |
+
fire==0.7.0
|
38 |
+
flash_attn==2.7.4.post1
|
39 |
+
frozenlist==1.5.0
|
40 |
+
fsspec==2024.9.0
|
41 |
+
gguf==0.10.0
|
42 |
+
google-api-core==2.24.2
|
43 |
+
google-auth==2.38.0
|
44 |
+
googleapis-common-protos==1.69.2
|
45 |
+
grpcio==1.71.0
|
46 |
+
h11==0.14.0
|
47 |
+
hjson==3.1.0
|
48 |
+
httpcore==1.0.7
|
49 |
+
httptools==0.6.4
|
50 |
+
httpx==0.28.1
|
51 |
+
huggingface-hub==0.29.3
|
52 |
+
idna==3.10
|
53 |
+
immutables==0.20
|
54 |
+
importlib_metadata==8.6.1
|
55 |
+
iniconfig==2.1.0
|
56 |
+
intel-cmplr-lib-ur==2025.0.5
|
57 |
+
intel-openmp==2025.0.5
|
58 |
+
interegular==0.3.3
|
59 |
+
Jinja2==3.1.6
|
60 |
+
jiter==0.9.0
|
61 |
+
joblib==1.4.2
|
62 |
+
jsonschema==4.23.0
|
63 |
+
jsonschema-specifications==2024.10.1
|
64 |
+
lark==1.2.2
|
65 |
+
llvmlite==0.43.0
|
66 |
+
lm-format-enforcer==0.10.11
|
67 |
+
mamba-ssm==2.2.3
|
68 |
+
mambapy==1.2.0
|
69 |
+
markdown-it-py==3.0.0
|
70 |
+
MarkupSafe==3.0.2
|
71 |
+
mdurl==0.1.2
|
72 |
+
mistral_common==1.5.4
|
73 |
+
mkl==2025.0.1
|
74 |
+
mkl-include==2025.0.1
|
75 |
+
modelscope==1.24.0
|
76 |
+
mpmath==1.3.0
|
77 |
+
msgpack==1.1.0
|
78 |
+
msgspec==0.19.0
|
79 |
+
multidict==6.2.0
|
80 |
+
multiprocess==0.70.16
|
81 |
+
nest-asyncio==1.6.0
|
82 |
+
networkx==3.4.2
|
83 |
+
ninja==1.11.1.3
|
84 |
+
numba==0.60.0
|
85 |
+
numpy==1.26.4
|
86 |
+
nvidia-cublas-cu12==12.1.3.1
|
87 |
+
nvidia-cuda-cupti-cu12==12.1.105
|
88 |
+
nvidia-cuda-nvrtc-cu12==12.1.105
|
89 |
+
nvidia-cuda-runtime-cu12==12.1.105
|
90 |
+
nvidia-cudnn-cu12==9.1.0.70
|
91 |
+
nvidia-cufft-cu12==11.0.2.54
|
92 |
+
nvidia-curand-cu12==10.3.2.106
|
93 |
+
nvidia-cusolver-cu12==11.4.5.107
|
94 |
+
nvidia-cusparse-cu12==12.1.0.106
|
95 |
+
nvidia-ml-py==12.570.86
|
96 |
+
nvidia-nccl-cu12==2.21.5
|
97 |
+
nvidia-nvjitlink-cu12==12.8.93
|
98 |
+
nvidia-nvtx-cu12==12.1.105
|
99 |
+
openai==1.66.3
|
100 |
+
opencensus==0.11.4
|
101 |
+
opencensus-context==0.1.3
|
102 |
+
opencv-python-headless==4.11.0.86
|
103 |
+
outlines==0.1.11
|
104 |
+
outlines_core==0.1.26
|
105 |
+
packaging==24.2
|
106 |
+
pandas==2.2.3
|
107 |
+
partial-json-parser==0.2.1.1.post5
|
108 |
+
peft==0.15.2
|
109 |
+
pillow==11.1.0
|
110 |
+
platformdirs==4.3.6
|
111 |
+
pluggy==1.5.0
|
112 |
+
prometheus-fastapi-instrumentator==7.0.2
|
113 |
+
prometheus_client==0.21.1
|
114 |
+
propcache==0.3.0
|
115 |
+
proto-plus==1.26.1
|
116 |
+
protobuf==6.30.1
|
117 |
+
psutil==7.0.0
|
118 |
+
py-cpuinfo==9.0.0
|
119 |
+
py-spy==0.4.0
|
120 |
+
pyarrow==19.0.1
|
121 |
+
pyasn1==0.6.1
|
122 |
+
pyasn1_modules==0.4.1
|
123 |
+
pybind11==2.13.6
|
124 |
+
pycountry==24.6.1
|
125 |
+
pydantic==2.10.6
|
126 |
+
pydantic_core==2.27.2
|
127 |
+
Pygments==2.19.1
|
128 |
+
pytest==8.3.5
|
129 |
+
python-dateutil==2.9.0.post0
|
130 |
+
python-dotenv==1.0.1
|
131 |
+
python-multipart==0.0.20
|
132 |
+
pytz==2025.1
|
133 |
+
PyYAML==6.0.2
|
134 |
+
pyzmq==26.3.0
|
135 |
+
ray==2.40.0
|
136 |
+
referencing==0.36.2
|
137 |
+
regex==2024.11.6
|
138 |
+
requests==2.32.3
|
139 |
+
rich==14.0.0
|
140 |
+
rich-toolkit==0.14.1
|
141 |
+
rpds-py==0.23.1
|
142 |
+
rsa==4.9
|
143 |
+
safetensors==0.5.3
|
144 |
+
scikit-learn==1.6.1
|
145 |
+
scipy==1.15.2
|
146 |
+
sentencepiece==0.2.0
|
147 |
+
shellingham==1.5.4
|
148 |
+
simplejson==3.20.1
|
149 |
+
six==1.17.0
|
150 |
+
smart-open==7.1.0
|
151 |
+
sniffio==1.3.1
|
152 |
+
sortedcontainers==2.4.0
|
153 |
+
starlette==0.46.1
|
154 |
+
str2bool==1.1
|
155 |
+
sympy==1.13.1
|
156 |
+
tbb==2022.0.0
|
157 |
+
tcmlib==1.2.0
|
158 |
+
termcolor==2.5.0
|
159 |
+
threadpoolctl==3.6.0
|
160 |
+
tiktoken==0.9.0
|
161 |
+
timm==1.0.15
|
162 |
+
tokenizers==0.21.1
|
163 |
+
torch==2.5.1
|
164 |
+
torchaudio==2.5.1
|
165 |
+
torchvision==0.20.1
|
166 |
+
tqdm==4.66.5
|
167 |
+
transformers==4.49.0
|
168 |
+
triton==3.1.0
|
169 |
+
trl==0.16.1
|
170 |
+
typer==0.15.2
|
171 |
+
typing_extensions==4.12.2
|
172 |
+
tzdata==2025.1
|
173 |
+
umf==0.9.1
|
174 |
+
urllib3==2.3.0
|
175 |
+
uvicorn==0.34.0
|
176 |
+
uvloop==0.21.0
|
177 |
+
virtualenv==20.29.3
|
178 |
+
vllm==0.7.3
|
179 |
+
watchfiles==1.0.4
|
180 |
+
websockets==15.0.1
|
181 |
+
wrapt==1.17.2
|
182 |
+
xformers==0.0.28.post3
|
183 |
+
xgrammar==0.1.11
|
184 |
+
xxhash==3.5.0
|
185 |
+
yarl==1.18.3
|
186 |
+
zipp==3.21.0
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"pad_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
27 |
+
"rstrip": false,
|
28 |
+
"single_word": false
|
29 |
+
}
|
30 |
+
}
|
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
|
|