commit 0c2340ff34e3e434e1753d7acd9885581f3e3ad7 Author: ModelHub XC Date: Fri Oct 23 16:08:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: fla-hub/mamba-2.7B-100B Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..92a497e --- /dev/null +++ b/.gitattributes @@ -0,0 +1,52 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 + +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text + +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +tokenizer.model filter=lfs diff=lfs merge=lfs -text +model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text +model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..49fb84d --- /dev/null +++ b/README.md @@ -0,0 +1,48 @@ +--- +license: Apache License 2.0 +tags: [] + +#model-type: +##如 gpt、phi、llama、chatglm、baichuan 等 +#- gpt + +#domain: +##如 nlp、cv、audio、multi-modal +#- nlp + +#language: +##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa +#- cn + +#metrics: +##如 CIDEr、Blue、ROUGE 等 +#- CIDEr + +#tags: +##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他 +#- pretrained + +#tools: +##如 vllm、fastchat、llamacpp、AdaSeq 等 +#- vllm +--- +### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。 +#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型 + +SDK下载 +```bash +#安装ModelScope +pip install modelscope +``` +```python +#SDK模型下载 +from modelscope import snapshot_download +model_dir = snapshot_download('fla-hub/mamba-2.7B-100B') +``` +Git下载 +``` +#Git模型下载 +git clone https://www.modelscope.cn/fla-hub/mamba-2.7B-100B.git +``` + +

如果您是本模型的贡献者，我们邀请您根据模型贡献文档，及时完善模型卡片内容。

\ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..29e62d1 --- /dev/null +++ b/config.json @@ -0,0 +1,36 @@ +{ + "_name_or_path": "fla-hub/mamba-2.7B-100B", + "architectures": [ + "MambaForCausalLM" + ], + "bos_token_id": 0, + "conv_kernel": 4, + "eos_token_id": 0, + "expand": 2, + "fuse_cross_entropy": true, + "fuse_norm": true, + "hidden_act": "silu", + "hidden_size": 2560, + "initializer_range": 0.1, + "intermediate_size": 5120, + "layer_norm_epsilon": 1e-05, + "model_type": "mamba", + "num_hidden_layers": 64, + "pad_token_id": null, + "rescale_prenorm_residual": false, + "residual_in_fp32": false, + "state_size": 16, + "tie_word_embeddings": true, + "time_step_floor": 0.0001, + "time_step_init_scheme": "random", + "time_step_max": 0.1, + "time_step_min": 0.001, + "time_step_rank": 160, + "time_step_scale": 1.0, + "torch_dtype": "bfloat16", + "transformers_version": "4.40.0", + "use_bias": false, + "use_cache": true, + "use_conv_bias": true, + "vocab_size": 32000 +} diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..6a8a63e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,7 @@ +{ + "_from_model_config": true, + "bos_token_id": 0, + "eos_token_id": 0, + "pad_token_id": 0, + "transformers_version": "4.40.0" +} diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors new file mode 100644 index 0000000..cfcd637 --- /dev/null +++ b/model-00001-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7efa97f7dec690a63ad27a2f10bb4dd86ff0cdc34e8a7b9a1ab4a8e6b9ea80a +size 4958124464 diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors new file mode 100644 index 0000000..33b3718 --- /dev/null +++ b/model-00002-of-00002.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2051baa14d032a9fb1233c640a023a0d3ecdf02e61f93085bd1b2164243b5a8 +size 495529984 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000..51aeebf --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,649 @@ +{ + "metadata": { + "total_size": 5453583360 + }, + "weight_map": { + "backbone.embeddings.weight": "model-00001-of-00002.safetensors", + "backbone.layers.0.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.0.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.0.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.0.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.0.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.0.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.0.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.0.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.0.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.0.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.1.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.1.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.1.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.1.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.1.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.1.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.1.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.1.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.1.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.1.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.10.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.10.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.10.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.10.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.10.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.10.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.10.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.10.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.10.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.10.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.11.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.11.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.11.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.11.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.11.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.11.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.11.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.11.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.11.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.11.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.12.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.12.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.12.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.12.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.12.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.12.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.12.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.12.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.12.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.12.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.13.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.13.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.13.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.13.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.13.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.13.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.13.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.13.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.13.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.13.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.14.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.14.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.14.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.14.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.14.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.14.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.14.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.14.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.14.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.14.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.15.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.15.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.15.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.15.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.15.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.15.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.15.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.15.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.15.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.15.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.16.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.16.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.16.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.16.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.16.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.16.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.16.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.16.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.16.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.16.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.17.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.17.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.17.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.17.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.17.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.17.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.17.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.17.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.17.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.17.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.18.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.18.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.18.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.18.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.18.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.18.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.18.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.18.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.18.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.18.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.19.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.19.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.19.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.19.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.19.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.19.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.19.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.19.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.19.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.19.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.2.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.2.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.2.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.2.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.2.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.2.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.2.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.2.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.2.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.2.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.20.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.20.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.20.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.20.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.20.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.20.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.20.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.20.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.20.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.20.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.21.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.21.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.21.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.21.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.21.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.21.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.21.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.21.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.21.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.21.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.22.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.22.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.22.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.22.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.22.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.22.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.22.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.22.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.22.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.22.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.23.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.23.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.23.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.23.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.23.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.23.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.23.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.23.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.23.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.23.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.24.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.24.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.24.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.24.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.24.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.24.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.24.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.24.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.24.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.24.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.25.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.25.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.25.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.25.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.25.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.25.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.25.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.25.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.25.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.25.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.26.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.26.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.26.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.26.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.26.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.26.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.26.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.26.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.26.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.26.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.27.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.27.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.27.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.27.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.27.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.27.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.27.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.27.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.27.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.27.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.28.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.28.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.28.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.28.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.28.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.28.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.28.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.28.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.28.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.28.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.29.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.29.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.29.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.29.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.29.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.29.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.29.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.29.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.29.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.29.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.3.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.3.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.3.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.3.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.3.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.3.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.3.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.3.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.3.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.3.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.30.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.30.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.30.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.30.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.30.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.30.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.30.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.30.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.30.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.30.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.31.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.31.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.31.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.31.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.31.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.31.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.31.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.31.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.31.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.31.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.32.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.32.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.32.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.32.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.32.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.32.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.32.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.32.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.32.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.32.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.33.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.33.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.33.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.33.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.33.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.33.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.33.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.33.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.33.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.33.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.34.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.34.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.34.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.34.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.34.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.34.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.34.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.34.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.34.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.34.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.35.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.35.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.35.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.35.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.35.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.35.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.35.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.35.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.35.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.35.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.36.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.36.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.36.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.36.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.36.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.36.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.36.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.36.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.36.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.36.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.37.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.37.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.37.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.37.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.37.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.37.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.37.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.37.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.37.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.37.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.38.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.38.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.38.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.38.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.38.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.38.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.38.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.38.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.38.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.38.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.39.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.39.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.39.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.39.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.39.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.39.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.39.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.39.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.39.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.39.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.4.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.4.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.4.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.4.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.4.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.4.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.4.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.4.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.4.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.4.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.40.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.40.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.40.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.40.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.40.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.40.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.40.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.40.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.40.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.40.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.41.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.41.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.41.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.41.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.41.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.41.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.41.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.41.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.41.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.41.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.42.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.42.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.42.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.42.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.42.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.42.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.42.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.42.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.42.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.42.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.43.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.43.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.43.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.43.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.43.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.43.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.43.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.43.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.43.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.43.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.44.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.44.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.44.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.44.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.44.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.44.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.44.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.44.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.44.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.44.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.45.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.45.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.45.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.45.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.45.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.45.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.45.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.45.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.45.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.45.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.46.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.46.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.46.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.46.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.46.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.46.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.46.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.46.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.46.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.46.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.47.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.47.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.47.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.47.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.47.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.47.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.47.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.47.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.47.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.47.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.48.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.48.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.48.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.48.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.48.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.48.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.48.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.48.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.48.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.48.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.49.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.49.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.49.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.49.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.49.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.49.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.49.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.49.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.49.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.49.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.5.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.5.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.5.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.5.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.5.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.5.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.5.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.5.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.5.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.5.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.50.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.50.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.50.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.50.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.50.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.50.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.50.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.50.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.50.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.50.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.51.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.51.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.51.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.51.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.51.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.51.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.51.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.51.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.51.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.51.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.52.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.52.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.52.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.52.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.52.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.52.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.52.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.52.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.52.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.52.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.53.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.53.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.53.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.53.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.53.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.53.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.53.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.53.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.53.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.53.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.54.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.54.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.54.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.54.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.54.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.54.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.54.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.54.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.54.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.54.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.55.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.55.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.55.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.55.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.55.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.55.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.55.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.55.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.55.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.55.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.56.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.56.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.56.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.56.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.56.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.56.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.56.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.56.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.56.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.56.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.57.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.57.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.57.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.57.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.57.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.57.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.57.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.57.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.57.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.57.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.58.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.58.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.58.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.58.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.58.mixer.dt_proj.bias": "model-00002-of-00002.safetensors", + "backbone.layers.58.mixer.dt_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.58.mixer.in_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.58.mixer.out_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.58.mixer.x_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.58.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.59.mixer.A_log": "model-00002-of-00002.safetensors", + "backbone.layers.59.mixer.D": "model-00002-of-00002.safetensors", + "backbone.layers.59.mixer.conv1d.bias": "model-00002-of-00002.safetensors", + "backbone.layers.59.mixer.conv1d.weight": "model-00002-of-00002.safetensors", + "backbone.layers.59.mixer.dt_proj.bias": "model-00002-of-00002.safetensors", + "backbone.layers.59.mixer.dt_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.59.mixer.in_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.59.mixer.out_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.59.mixer.x_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.59.norm.weight": "model-00002-of-00002.safetensors", + "backbone.layers.6.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.6.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.6.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.6.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.6.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.6.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.6.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.6.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.6.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.6.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.60.mixer.A_log": "model-00002-of-00002.safetensors", + "backbone.layers.60.mixer.D": "model-00002-of-00002.safetensors", + "backbone.layers.60.mixer.conv1d.bias": "model-00002-of-00002.safetensors", + "backbone.layers.60.mixer.conv1d.weight": "model-00002-of-00002.safetensors", + "backbone.layers.60.mixer.dt_proj.bias": "model-00002-of-00002.safetensors", + "backbone.layers.60.mixer.dt_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.60.mixer.in_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.60.mixer.out_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.60.mixer.x_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.60.norm.weight": "model-00002-of-00002.safetensors", + "backbone.layers.61.mixer.A_log": "model-00002-of-00002.safetensors", + "backbone.layers.61.mixer.D": "model-00002-of-00002.safetensors", + "backbone.layers.61.mixer.conv1d.bias": "model-00002-of-00002.safetensors", + "backbone.layers.61.mixer.conv1d.weight": "model-00002-of-00002.safetensors", + "backbone.layers.61.mixer.dt_proj.bias": "model-00002-of-00002.safetensors", + "backbone.layers.61.mixer.dt_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.61.mixer.in_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.61.mixer.out_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.61.mixer.x_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.61.norm.weight": "model-00002-of-00002.safetensors", + "backbone.layers.62.mixer.A_log": "model-00002-of-00002.safetensors", + "backbone.layers.62.mixer.D": "model-00002-of-00002.safetensors", + "backbone.layers.62.mixer.conv1d.bias": "model-00002-of-00002.safetensors", + "backbone.layers.62.mixer.conv1d.weight": "model-00002-of-00002.safetensors", + "backbone.layers.62.mixer.dt_proj.bias": "model-00002-of-00002.safetensors", + "backbone.layers.62.mixer.dt_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.62.mixer.in_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.62.mixer.out_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.62.mixer.x_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.62.norm.weight": "model-00002-of-00002.safetensors", + "backbone.layers.63.mixer.A_log": "model-00002-of-00002.safetensors", + "backbone.layers.63.mixer.D": "model-00002-of-00002.safetensors", + "backbone.layers.63.mixer.conv1d.bias": "model-00002-of-00002.safetensors", + "backbone.layers.63.mixer.conv1d.weight": "model-00002-of-00002.safetensors", + "backbone.layers.63.mixer.dt_proj.bias": "model-00002-of-00002.safetensors", + "backbone.layers.63.mixer.dt_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.63.mixer.in_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.63.mixer.out_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.63.mixer.x_proj.weight": "model-00002-of-00002.safetensors", + "backbone.layers.63.norm.weight": "model-00002-of-00002.safetensors", + "backbone.layers.7.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.7.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.7.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.7.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.7.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.7.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.7.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.7.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.7.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.7.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.8.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.8.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.8.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.8.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.8.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.8.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.8.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.8.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.8.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.8.norm.weight": "model-00001-of-00002.safetensors", + "backbone.layers.9.mixer.A_log": "model-00001-of-00002.safetensors", + "backbone.layers.9.mixer.D": "model-00001-of-00002.safetensors", + "backbone.layers.9.mixer.conv1d.bias": "model-00001-of-00002.safetensors", + "backbone.layers.9.mixer.conv1d.weight": "model-00001-of-00002.safetensors", + "backbone.layers.9.mixer.dt_proj.bias": "model-00001-of-00002.safetensors", + "backbone.layers.9.mixer.dt_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.9.mixer.in_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.9.mixer.out_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.9.mixer.x_proj.weight": "model-00001-of-00002.safetensors", + "backbone.layers.9.norm.weight": "model-00001-of-00002.safetensors", + "backbone.norm_f.weight": "model-00002-of-00002.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000..451134b --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,23 @@ +{ + "bos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "eos_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "unk_token": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..e3f4214 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdc45dc7f18a5c55e0dcb36f4f187a7c429d6aaa1693a17d20422b85081642d9 +size 1795331 diff --git a/tokenizer.model b/tokenizer.model new file mode 100644 index 0000000..8b443ef --- /dev/null +++ b/tokenizer.model @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055 +size 493443 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..81730cd --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,42 @@ +{ + "add_bos_token": true, + "add_eos_token": false, + "added_tokens_decoder": { + "0": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "1": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "2": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + } + }, + "additional_special_tokens": [], + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "legacy": true, + "model_max_length": 1000000000000000019884624838656, + "pad_token": null, + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "LlamaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}