初始化项目，由ModelHub XC社区提供模型
Model: tiiuae/falcon-mamba-7b-instruct Source: Original Platform
This commit is contained in:
ModelHub XC
38
.gitattributes
vendored
Normal file
38
.gitattributes
vendored
Normal file
@@ -0,0 +1,38 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.model filter=lfs diff=lfs merge=lfs -text
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00003.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
324
README.md
Normal file
324
README.md
Normal file
@@ -0,0 +1,324 @@
|
||||
---
|
||||
new_version: tiiuae/Falcon3-Mamba-7B-Instruct
|
||||
datasets:
|
||||
- tiiuae/falcon-refinedweb
|
||||
- HuggingFaceFW/fineweb-edu
|
||||
language:
|
||||
- en
|
||||
license: other
|
||||
license_name: falcon-mamba-7b-license
|
||||
license_link: https://falconllm.tii.ae/falcon-mamba-7b-terms-and-conditions.html
|
||||
base_model: tiiuae/falcon-mamba-7b
|
||||
pipeline_tag: text-generation
|
||||
inference: true
|
||||
---
|
||||
|
||||
<img src="https://huggingface.co/datasets/tiiuae/documentation-images/resolve/main/falcon_mamba/thumbnail.png" alt="drawing" width="800"/>
|
||||
|
||||
**Model card for FalconMamba Instruct model**
|
||||
|
||||
# Table of Contents
|
||||
|
||||
0. [TL;DR](#TL;DR)
|
||||
1. [Model Details](#model-details)
|
||||
2. [Usage](#usage)
|
||||
3. [Training Details](#training-details)
|
||||
4. [Evaluation](#evaluation)
|
||||
|
||||
|
||||
# TL;DR
|
||||
|
||||
# Model Details
|
||||
|
||||
## Model Description
|
||||
|
||||
- **Developed by:** [https://www.tii.ae](https://www.tii.ae)
|
||||
- **Model type:** Causal decoder-only
|
||||
- **Architecture:** Mamba
|
||||
- **Language(s) (NLP):** Mainly English
|
||||
- **License:** TII Falcon-Mamba License 2.0
|
||||
|
||||
<br>
|
||||
|
||||
Check out [the blogpost](https://huggingface.co/blog/falconmamba) for more details!
|
||||
|
||||
# Usage
|
||||
|
||||
Find below some example scripts on how to use the model in `transformers` (Make sure to have the latest transformers, or the one built from source):
|
||||
|
||||
## Using the Pytorch model
|
||||
|
||||
### Running the model on a CPU
|
||||
|
||||
<details>
|
||||
<summary> Click to expand </summary>
|
||||
|
||||
```python
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-mamba-7b-instruct")
|
||||
model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-mamba-7b-instruct")
|
||||
|
||||
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
|
||||
messages = [
|
||||
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
|
||||
]
|
||||
|
||||
input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
input_ids = tokenizer(input_text, return_tensors="pt").input_ids
|
||||
|
||||
outputs = model.generate(input_ids, max_new_tokens=30)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
### Running the model on a GPU
|
||||
|
||||
<details>
|
||||
<summary> Click to expand </summary>
|
||||
|
||||
```python
|
||||
# pip install accelerate
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-mamba-7b-instruct")
|
||||
model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-mamba-7b-instruct", device_map="auto")
|
||||
|
||||
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
|
||||
messages = [
|
||||
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
|
||||
]
|
||||
|
||||
input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
|
||||
|
||||
outputs = model.generate(input_ids, max_new_tokens=30)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
### Running the model on a GPU using `torch.compile`
|
||||
|
||||
<details>
|
||||
<summary> Click to expand </summary>
|
||||
|
||||
```python
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-mamba-7b-instruct")
|
||||
model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-mamba-7b-instruct", torch_dtype=torch.bfloat16).to(0)
|
||||
|
||||
model = torch.compile(model)
|
||||
|
||||
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
|
||||
messages = [
|
||||
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
|
||||
]
|
||||
input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
|
||||
|
||||
outputs = model.generate(input_ids, max_new_tokens=30)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
|
||||
### Running the model on a GPU using different precisions
|
||||
|
||||
#### FP16
|
||||
|
||||
<details>
|
||||
<summary> Click to expand </summary>
|
||||
|
||||
```python
|
||||
# pip install accelerate
|
||||
import torch
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-mamba-7b-instruct")
|
||||
model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-mamba-7b-instruct", device_map="auto", torch_dtype=torch.float16)
|
||||
|
||||
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
|
||||
messages = [
|
||||
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
|
||||
]
|
||||
input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
|
||||
|
||||
outputs = model.generate(input_ids, max_new_tokens=30)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
#### 4-bit
|
||||
|
||||
<details>
|
||||
<summary> Click to expand </summary>
|
||||
|
||||
```python
|
||||
# pip install bitsandbytes accelerate
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig
|
||||
|
||||
tokenizer = AutoTokenizer.from_pretrained("tiiuae/falcon-mamba-7b-instruct")
|
||||
model = AutoModelForCausalLM.from_pretrained("tiiuae/falcon-mamba-7b-instruct", device_map="auto", quantization_config=BitsAndBytesConfig(load_in_4bit=True))
|
||||
|
||||
# We use the tokenizer's chat template to format each message - see https://huggingface.co/docs/transformers/main/en/chat_templating
|
||||
messages = [
|
||||
{"role": "user", "content": "How many helicopters can a human eat in one sitting?"},
|
||||
]
|
||||
input_text = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||||
input_ids = tokenizer(input_text, return_tensors="pt").input_ids.to("cuda")
|
||||
|
||||
outputs = model.generate(input_ids, max_new_tokens=30)
|
||||
print(tokenizer.decode(outputs[0]))
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
<br>
|
||||
|
||||
# Training Details
|
||||
|
||||
## Training Data
|
||||
|
||||
Falcon-Mamba has been trained with ~ 5,500 GT mainly coming from [Refined-Web](https://huggingface.co/datasets/tiiuae/falcon-refinedweb), a large volume web-only dataset filtered and deduplicated.
|
||||
Similar to the others [Falcon](https://huggingface.co/tiiuae/falcon-11B) suite models, Falcon-Mamba has been trained leveraging a multi-stage training strategy to increase the context-length from 2,048 to 8,192.
|
||||
Moreover, inspired by the concept of Curriculum Learning, we carefully selected data mixtures throughout the training stages, considering both data diversity and complexity.
|
||||
Note that at inference the context-length is not relevant as the Mamba architecture has no limit on long range dependency.
|
||||
At the last training stage, small portion of high-quality curated data was used to further enhance performance.
|
||||
|
||||
Overall, the data sources included RefinedWeb-English, high quality technical data, code data and math data extracted from public sources.
|
||||
In particular, we used samples coming from [Fineweb-edu](https://huggingface.co/datasets/HuggingFaceFW/fineweb-edu) during our last training stage.
|
||||
|
||||
The data was tokenized with the Falcon-[7B](https://huggingface.co/tiiuae/falcon-7B)/[11B](https://huggingface.co/tiiuae/falcon-11B) tokenizer.
|
||||
|
||||
After pre-training, the model has been further fine-tuned on instruction data.
|
||||
|
||||
## Training Procedure
|
||||
Falcon-Mamba-7B was trained on 256 H100 80GB GPUs for the majority of the training, using a 3D parallelism strategy (TP=1, PP=1, DP=256) combined with ZeRO.
|
||||
|
||||
### Training Hyperparameters
|
||||
|
||||
| **Hyperparameter** | **Value** | **Comment** |
|
||||
|--------------------|------------|-------------------------------------------|
|
||||
| Precision | `bfloat16` | |
|
||||
| Optimizer | AdamW | |
|
||||
| Max learning rate | 6.4e-4 | Following a WSD (warmup-stable-decay) learning rate schedule |
|
||||
| Weight decay | 1e-1 | |
|
||||
| Batch size | 2048 | |
|
||||
|
||||
|
||||
The model was trained AdamW optimizer, WSD (warmup-stable-decay) learning rate schedule, and a batch size rampup from \\(b_{\mathrm{min}}=128\\) to \\(b_{\mathrm{max}}=2048\\) during first 50 GT of training.
|
||||
In the stable phase we used maximal learning rate \\(\eta_{\mathrm{max}}=6.4 \times 10^{-4}\\), and decayed it to the minimal value \\(\eta_{\mathrm{min}}=\frac{\eta_{\mathrm{max}}}{256}\\) with exponential schedule over 500 GT.
|
||||
Also, we applied *BatchScaling* during the rampup — rescaling learning rate \\(\eta\\) so that the Adam noise temperature \\(T_{\mathrm{noise}}\equiv\frac{\eta}{\sqrt{b}}\\) is kept constant.
|
||||
|
||||
### Speeds, Sizes, Times
|
||||
|
||||
The model training took roughly two months.
|
||||
|
||||
<br>
|
||||
|
||||
# Evaluation
|
||||
|
||||
## Benchmarks
|
||||
|
||||
We evaluate our model on all benchmarks of the new leaderboard's version using the `lm-evaluation-harness` package, and then normalize the evaluation results with HuggingFace score normalization.
|
||||
|
||||
|
||||
| `model name` |`IFEval`| `BBH` |`MATH LvL5`| `GPQA`| `MUSR`|`MMLU-PRO`|`Average`|
|
||||
|:--------------------------|:------:|:-----:|:---------:|:-----:|:-----:|:--------:|:-------:|
|
||||
| ***Pure SSM models*** | | | | | | | |
|
||||
| `FalconMamba-7B` | 33.36 | 19.88 | 3.63 |8.05 |10.86 | 14.47 |**15.04**|
|
||||
| `TRI-ML/mamba-7b-rw`<sup>*</sup>| 22.46 | 6.71 | 0.45 | 1.12 | 5.51 | 1.69 | 6.25 |
|
||||
|***Hybrid SSM-attention models*** | | | | | | |
|
||||
|`recurrentgemma-9b` | 30.76 | 14.80 | 4.83 | 4.70 | 6.60 | 17.88 | 13.20 |
|
||||
| `Zyphra/Zamba-7B-v1`<sup>*</sup> | 24.06 | 21.12 | 3.32 | 3.03 | 7.74 | 16.02 | 12.55 |
|
||||
|***Transformer models*** | | | | | | | |
|
||||
| `Falcon2-11B` | 32.61 | 21.94 | 2.34 | 2.80 | 7.53 | 15.44 | 13.78 |
|
||||
| `Meta-Llama-3-8B` | 14.55 | 24.50 | 3.25 | 7.38 | 6.24 | 24.55 | 13.41 |
|
||||
| `Meta-Llama-3.1-8B` | 12.70 | 25.29 | 4.61 | 6.15 | 8.98 | 24.95 | 13.78 |
|
||||
| `Mistral-7B-v0.1` | 23.86 | 22.02 | 2.49 | 5.59 | 10.68 | 22.36 | 14.50 |
|
||||
| `Mistral-Nemo-Base-2407 (12B)` | 16.83 | 29.37 | 4.98 | 5.82 | 6.52 | 27.46 | 15.08 |
|
||||
| `gemma-7B` | 26.59 | 21.12 | 6.42 | 4.92 | 10.98 | 21.64 |**15.28**|
|
||||
|
||||
|
||||
Also, we evaluate our model on the benchmarks of the first leaderboard using `lighteval`.
|
||||
|
||||
|
||||
| `model name` |`ARC`|`HellaSwag` |`MMLU` |`Winogrande`|`TruthfulQA`|`GSM8K`|`Average` |
|
||||
|:-----------------------------|:------:|:---------:|:-----:|:----------:|:----------:|:-----:|:----------------:|
|
||||
| ***Pure SSM models*** | | | | | | | |
|
||||
| `FalconMamba-7B`<sup>*</sup> | 62.03 | 80.82 | 62.11 | 73.64 | 53.42 | 52.54 | **64.09** |
|
||||
| `TRI-ML/mamba-7b-rw`<sup>*</sup> | 51.25 | 80.85 | 33.41 | 71.11 | 32.08 | 4.70 | 45.52 |
|
||||
|***Hybrid SSM-attention models***| | | | | | | |
|
||||
| `recurrentgemma-9b`<sup>**</sup> |52.00 | 80.40 | 60.50 | 73.60 | 38.60 | 42.60 | 57.95 |
|
||||
| `Zyphra/Zamba-7B-v1`<sup>*</sup> | 56.14 | 82.23 | 58.11 | 79.87 | 52.88 | 30.78 | 60.00 |
|
||||
|***Transformer models*** | | | | | | | |
|
||||
| `Falcon2-11B` | 59.73 | 82.91 | 58.37 | 78.30 | 52.56 | 53.83 | **64.28** |
|
||||
| `Meta-Llama-3-8B` | 60.24 | 82.23 | 66.70 | 78.45 | 42.93 | 45.19 | 62.62 |
|
||||
| `Meta-Llama-3.1-8B` | 58.53 | 82.13 | 66.43 | 74.35 | 44.29 | 47.92 | 62.28 |
|
||||
| `Mistral-7B-v0.1` | 59.98 | 83.31 | 64.16 | 78.37 | 42.15 | 37.83 | 60.97 |
|
||||
| `gemma-7B` | 61.09 | 82.20 | 64.56 | 79.01 | 44.79 | 50.87 | 63.75 |
|
||||
|
||||
Mostly, we took evaluation results from both leaderboards. For the models marked by *star* we evaluated the tasks internally, while for the models marked by two *stars* the results were taken from paper or model card.
|
||||
|
||||
## Throughput
|
||||
|
||||
This model can achieve comparable throughput and performance compared to other transformer based models that use optimized kernels such as Flash Attention 2. Make sure to install the optimized Mamba kernels with the following commands:
|
||||
|
||||
```bash
|
||||
pip install "causal-conv1d>=1.4.0" mamba-ssm
|
||||
```
|
||||
|
||||
Refer to our [FalconMamba blogpost](https://huggingface.co/blog/falconmamba) for more details about performance evaluation.
|
||||
|
||||
|
||||
<br>
|
||||
|
||||
# Technical Specifications
|
||||
|
||||
## Model Architecture and Objective
|
||||
|
||||
Falcon-Mamba-7B is a causal decoder-only model trained on a causal language modeling task (i.e., predict the next token).
|
||||
|
||||
The model is based on the Mamba architecture ([Gu et al., 2023](https://arxiv.org/abs/2312.00752)).
|
||||
|
||||
| **Hyperparameter** | **Value** | **Comment** |
|
||||
|--------------------|-----------|----------------------------------------|
|
||||
| Layers | 64 | Number of layers |
|
||||
| `d_model` | 4096 | Hidden dimension |
|
||||
| `d_state` | 16 | The SSM state dimension |
|
||||
| Vocabulary | 65024 | Vocabulary Size |
|
||||
| Sequence length | 8192 | During the last training stages |
|
||||
|
||||
## Compute Infrastructure
|
||||
|
||||
### Hardware
|
||||
|
||||
Falcon-Mamba-7B was trained on AWS SageMaker, using on average 256 H100 80GB GPUs in 32 p5 instances.
|
||||
|
||||
### Software
|
||||
|
||||
Falcon-Mamba-7B was trained on an internal distributed training codebase, Gigatron. It uses a 3D parallelism approach combined with ZeRO, high-performance Triton kernels.
|
||||
|
||||
<br>
|
||||
|
||||
# Citation
|
||||
|
||||
You can use the following bibtex citation:
|
||||
```
|
||||
@misc{zuo2024falconmambacompetitiveattentionfree,
|
||||
title={Falcon Mamba: The First Competitive Attention-free 7B Language Model},
|
||||
author={Jingwei Zuo and Maksim Velikanov and Dhia Eddine Rhaiem and Ilyas Chahed and Younes Belkada and Guillaume Kunsch and Hakim Hacid},
|
||||
year={2024},
|
||||
eprint={2410.05355},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL},
|
||||
url={https://arxiv.org/abs/2410.05355},
|
||||
}
|
||||
```
|
||||
35
config.json
Normal file
35
config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"_name_or_path": "tiiuae/falcon-mamba-7b-chat",
|
||||
"architectures": [
|
||||
"FalconMambaForCausalLM"
|
||||
],
|
||||
"bos_token_id": 8,
|
||||
"conv_kernel": 4,
|
||||
"eos_token_id": 11,
|
||||
"expand": 16,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.1,
|
||||
"intermediate_size": 8192,
|
||||
"layer_norm_epsilon": 1e-05,
|
||||
"model_type": "falcon_mamba",
|
||||
"num_hidden_layers": 64,
|
||||
"pad_token_id": 0,
|
||||
"rescale_prenorm_residual": false,
|
||||
"residual_in_fp32": true,
|
||||
"state_size": 16,
|
||||
"tie_word_embeddings": false,
|
||||
"time_step_floor": 0.0001,
|
||||
"time_step_init_scheme": "random",
|
||||
"time_step_max": 0.1,
|
||||
"time_step_min": 0.001,
|
||||
"time_step_rank": 256,
|
||||
"time_step_scale": 1.0,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.44.0.dev0",
|
||||
"use_bias": false,
|
||||
"use_cache": true,
|
||||
"use_conv_bias": true,
|
||||
"use_mambapy": false,
|
||||
"vocab_size": 65024
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
10
generation_config.json
Normal file
10
generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 8,
|
||||
"eos_token_id": [
|
||||
11,
|
||||
10
|
||||
],
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.44.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00003.safetensors
Normal file
3
model-00001-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f44b8d6bf70728703ee89acfdc4ba5c0b86dbcf59d00ae07692dc943a682caf0
|
||||
size 4956184024
|
||||
3
model-00002-of-00003.safetensors
Normal file
3
model-00002-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fc5fe83e4f7eee28ed1717aaae90cf67931c4551a927b48026742782064a86da
|
||||
size 4987536920
|
||||
3
model-00003-of-00003.safetensors
Normal file
3
model-00003-of-00003.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8044847d7225503eaa76ca48df04685c56c8aff0a4350761f309708477434efd
|
||||
size 4601680888
|
||||
650
model.safetensors.index.json
Normal file
650
model.safetensors.index.json
Normal file
@@ -0,0 +1,650 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 14545330176
|
||||
},
|
||||
"weight_map": {
|
||||
"backbone.embeddings.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.0.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.0.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.0.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.0.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.0.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.0.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.1.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.1.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.1.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.1.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.1.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.1.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.1.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.1.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.1.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.1.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.10.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.10.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.10.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.10.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.10.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.10.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.10.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.10.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.10.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.10.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.11.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.11.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.11.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.11.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.11.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.11.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.12.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.12.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.12.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.12.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.12.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.12.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.12.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.12.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.12.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.12.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.13.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.13.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.13.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.13.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.13.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.13.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.14.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.14.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.14.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.14.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.14.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.14.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.14.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.14.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.14.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.14.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.15.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.15.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.15.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.15.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.15.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.15.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.15.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.15.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.15.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.15.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.16.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.16.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.16.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.16.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.16.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.16.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.16.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.16.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.16.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.16.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.17.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.17.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.17.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.17.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.17.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.17.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.17.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.17.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.17.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.17.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.18.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.18.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.18.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.18.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.18.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.18.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.18.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.18.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.18.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.18.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.19.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.19.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.19.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.19.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.19.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.19.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.19.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.19.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.19.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.19.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.2.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.2.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.2.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.2.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.2.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.2.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.20.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.20.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.20.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.20.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.20.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.20.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.20.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.20.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.20.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.20.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.21.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.21.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.21.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.21.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.21.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.21.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.21.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.21.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.21.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.21.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.22.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.22.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.22.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.22.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.22.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.22.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.22.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.22.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.22.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.22.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.23.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.23.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.23.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.23.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.23.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.23.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.23.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.23.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.23.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.23.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.24.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.24.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.24.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.24.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.24.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.24.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.24.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.24.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.24.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.24.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.25.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.25.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.25.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.25.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.25.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.25.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.25.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.25.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.25.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.25.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.26.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.26.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.26.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.26.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.26.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.26.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.26.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.26.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.26.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.26.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.27.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.27.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.27.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.27.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.27.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.27.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.27.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.27.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.27.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.27.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.28.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.28.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.28.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.28.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.28.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.28.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.28.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.28.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.28.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.28.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.29.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.29.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.29.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.29.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.29.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.29.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.29.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.29.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.29.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.29.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.3.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.3.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.3.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.3.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.3.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.3.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.3.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.3.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.3.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.3.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.30.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.30.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.30.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.30.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.30.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.30.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.30.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.30.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.30.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.30.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.31.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.31.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.31.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.31.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.31.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.31.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.31.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.31.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.31.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.31.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.32.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.32.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.32.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.32.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.32.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.32.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.32.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.32.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.32.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.32.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.33.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.33.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.33.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.33.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.33.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.33.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.33.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.33.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.33.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.33.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.34.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.34.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.34.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.34.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.34.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.34.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.34.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.34.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.34.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.34.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.35.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.35.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.35.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.35.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.35.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.35.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.35.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.35.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.35.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.35.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.36.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.36.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.36.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.36.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.36.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.36.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.36.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.36.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.36.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.36.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.37.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.37.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.37.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.37.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.37.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.37.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.37.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.37.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.37.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.37.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.38.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.38.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.38.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.38.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.38.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.38.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.38.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.38.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.38.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.38.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.39.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.39.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.39.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.39.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.39.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.39.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.39.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.39.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.39.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.39.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.4.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.4.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.4.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.4.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.4.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.4.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.40.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.40.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.40.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.40.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.40.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.40.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.40.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.40.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.40.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.40.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.41.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.41.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.41.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.41.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.41.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.41.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.41.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.41.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.41.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.41.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.42.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.42.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.42.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.42.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.42.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.42.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.42.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.42.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.42.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.42.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.43.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.43.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.43.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.43.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.43.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.43.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.43.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.43.mixer.out_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.43.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.43.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.44.mixer.A_log": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.44.mixer.D": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.44.mixer.conv1d.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.44.mixer.conv1d.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.44.mixer.dt_proj.bias": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.44.mixer.dt_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.44.mixer.in_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.44.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.44.mixer.x_proj.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.44.norm.weight": "model-00002-of-00003.safetensors",
|
||||
"backbone.layers.45.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.45.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.45.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.45.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.45.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.45.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.45.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.45.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.45.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.45.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.46.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.46.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.46.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.46.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.46.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.46.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.46.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.46.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.46.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.46.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.47.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.47.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.47.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.47.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.47.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.47.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.47.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.47.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.47.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.47.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.48.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.48.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.48.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.48.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.48.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.48.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.48.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.48.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.48.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.48.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.49.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.49.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.49.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.49.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.49.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.49.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.49.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.49.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.49.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.49.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.5.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.5.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.5.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.5.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.5.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.5.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.5.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.5.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.5.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.5.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.50.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.50.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.50.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.50.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.50.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.50.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.50.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.50.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.50.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.50.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.51.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.51.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.51.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.51.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.51.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.51.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.51.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.51.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.51.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.51.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.52.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.52.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.52.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.52.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.52.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.52.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.52.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.52.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.52.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.52.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.53.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.53.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.53.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.53.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.53.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.53.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.53.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.53.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.53.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.53.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.54.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.54.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.54.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.54.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.54.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.54.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.54.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.54.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.54.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.54.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.55.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.55.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.55.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.55.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.55.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.55.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.55.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.55.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.55.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.55.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.56.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.56.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.56.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.56.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.56.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.56.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.56.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.56.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.56.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.56.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.57.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.57.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.57.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.57.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.57.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.57.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.57.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.57.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.57.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.57.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.58.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.58.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.58.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.58.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.58.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.58.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.58.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.58.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.58.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.58.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.59.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.59.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.59.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.59.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.59.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.59.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.59.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.59.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.59.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.59.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.6.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.6.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.6.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.6.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.6.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.6.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.60.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.60.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.60.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.60.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.60.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.60.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.60.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.60.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.60.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.60.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.61.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.61.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.61.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.61.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.61.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.61.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.61.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.61.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.61.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.61.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.62.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.62.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.62.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.62.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.62.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.62.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.62.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.62.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.62.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.62.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.63.mixer.A_log": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.63.mixer.D": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.63.mixer.conv1d.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.63.mixer.conv1d.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.63.mixer.dt_proj.bias": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.63.mixer.dt_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.63.mixer.in_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.63.mixer.out_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.63.mixer.x_proj.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.63.norm.weight": "model-00003-of-00003.safetensors",
|
||||
"backbone.layers.7.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.7.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.7.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.7.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.7.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.7.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.8.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.8.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.8.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.8.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.8.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.8.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.8.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.8.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.8.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.8.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.9.mixer.A_log": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.9.mixer.D": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.9.mixer.dt_proj.bias": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.9.mixer.dt_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.9.mixer.x_proj.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.layers.9.norm.weight": "model-00001-of-00003.safetensors",
|
||||
"backbone.norm_f.weight": "model-00003-of-00003.safetensors",
|
||||
"lm_head.weight": "model-00003-of-00003.safetensors"
|
||||
}
|
||||
}
|
||||
36
special_tokens_map.json
Normal file
36
special_tokens_map.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
">>TITLE<<",
|
||||
">>ABSTRACT<<",
|
||||
">>INTRODUCTION<<",
|
||||
">>SUMMARY<<",
|
||||
">>COMMENT<<",
|
||||
">>ANSWER<<",
|
||||
">>QUESTION<<",
|
||||
"assistant",
|
||||
"<|begin_of_text|>",
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
129979
tokenizer.json
Normal file
129979
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
129
tokenizer_config.json
Normal file
129
tokenizer_config.json
Normal file
@@ -0,0 +1,129 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": ">>TITLE<<",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": ">>ABSTRACT<<",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": ">>INTRODUCTION<<",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"3": {
|
||||
"content": ">>SUMMARY<<",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"4": {
|
||||
"content": ">>COMMENT<<",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"5": {
|
||||
"content": ">>ANSWER<<",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"6": {
|
||||
"content": ">>QUESTION<<",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"7": {
|
||||
"content": "assistant",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"8": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"9": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"10": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"11": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
">>TITLE<<",
|
||||
">>ABSTRACT<<",
|
||||
">>INTRODUCTION<<",
|
||||
">>SUMMARY<<",
|
||||
">>COMMENT<<",
|
||||
">>ANSWER<<",
|
||||
">>QUESTION<<",
|
||||
"assistant",
|
||||
"<|begin_of_text|>",
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"bos_token": "<|begin_of_text|>",
|
||||
"chat_template": "{{bos_token}}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": true,
|
||||
"eos_token": "<|end_of_text|>",
|
||||
"max_length": null,
|
||||
"model_input_names": [
|
||||
"input_ids",
|
||||
"attention_mask"
|
||||
],
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_to_multiple_of": null,
|
||||
"pad_token": ">>TITLE<<",
|
||||
"pad_token_type_id": 0,
|
||||
"padding_side": "left",
|
||||
"tokenizer_class": "PreTrainedTokenizerFast"
|
||||
}
|
||||
Reference in New Issue
Block a user