Upload JambaForCausalLM

README.md

@@ -0,0 +1,201 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure 
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+
+

config.json

@@ -0,0 +1,42 @@
+{
+  "architectures": [
+    "JambaForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attn_layer_offset": 4,
+  "attn_layer_period": 8,
+  "bos_token_id": 1,
+  "calc_logits_for_entire_prompt": false,
+  "eos_token_id": 2,
+  "expert_layer_offset": 1,
+  "expert_layer_period": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_state": 16,
+  "mamba_dt_rank": 256,
+  "mamba_expand": 2,
+  "mamba_inner_layernorms": true,
+  "mamba_proj_bias": false,
+  "model_type": "jamba",
+  "n_ctx": 262144,
+  "num_attention_heads": 32,
+  "num_experts": 16,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.39.3",
+  "use_cache": true,
+  "use_mamba_kernels": false,
+  "vocab_size": 65536
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.39.3"
+}

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c1cb0813aa7b7947b100d5def870bc9007bed87e9b37609eb42e0577d9a2da68
+size 4969962312

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e42afe8aaf5e7b6730cad42dd25d8679ccab7175a0849be2c1fd6aae5be55a21
+size 4932504120

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc0ca09411409a8250c587b6b0c7eda884e8c19797970ca3a7e1406752d9b3a6
+size 4884009920

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5fed085a6c116563d2fe756da7f258bc1f35082ea43a0eb4cb971365571edcf9
+size 4884272128

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cbed5c551732bfa154eac609ad630729ba33bef55cf87e8ccd7680e5f39b9d7
+size 4932504128

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b02c596fcc7b1387d548cc7fc964c659cb4b13f62be3ad076ece8e1be8719c
+size 4817196624

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c52d109acab176ead45c946a80516ca90b90dc15b38d17c3a2c61e9ffc40e1
+size 4932504120

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1372be472ed40332bfa66a0149becdfd64b0a192cd36f1c90c2e9c7991e23d64
+size 4933258424

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd60b87524590c051a49cc6081f59ceb1b001110afac03ffff18747d75191771
+size 4835023592

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f87ae190ce25cbecfa77b33298cde814b2078bc5b925d4b43eb72306ffd5a96
+size 4932504128

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46703a22cc27bdcc08fbdbd4df84019d64927d16932ffb4f17b49a79706fc610
+size 4127246352

model.safetensors.index.json

@@ -0,0 +1,322 @@
+{
+  "metadata": {
+    "total_size": 53180948352
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00011-of-00011.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00011.safetensors",
+    "model.final_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mamba.A_log": "model-00001-of-00011.safetensors",
+    "model.layers.0.mamba.B_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mamba.C_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mamba.D": "model-00001-of-00011.safetensors",
+    "model.layers.0.mamba.conv1d.bias": "model-00001-of-00011.safetensors",
+    "model.layers.0.mamba.conv1d.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mamba.dt_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mamba.dt_proj.bias": "model-00001-of-00011.safetensors",
+    "model.layers.0.mamba.dt_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mamba.in_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mamba.out_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.mamba.x_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.moe.experts.0.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.moe.experts.0.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.moe.experts.0.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.0.pre_moe_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.mamba.A_log": "model-00001-of-00011.safetensors",
+    "model.layers.1.mamba.B_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mamba.C_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mamba.D": "model-00001-of-00011.safetensors",
+    "model.layers.1.mamba.conv1d.bias": "model-00001-of-00011.safetensors",
+    "model.layers.1.mamba.conv1d.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mamba.dt_layernorm.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mamba.dt_proj.bias": "model-00001-of-00011.safetensors",
+    "model.layers.1.mamba.dt_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mamba.in_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mamba.out_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.mamba.x_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.moe.experts.0.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.moe.experts.0.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.moe.experts.0.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.moe.experts.1.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.moe.experts.1.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.moe.experts.1.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.moe.experts.10.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.10.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.10.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.11.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.11.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.11.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.12.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.12.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.12.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.13.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.13.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.13.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.14.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.14.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.14.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.15.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.15.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.15.up_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.1.moe.experts.2.down_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.moe.experts.2.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.moe.experts.2.up_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.moe.experts.3.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.3.gate_proj.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.moe.experts.3.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.4.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.4.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.4.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.5.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.5.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.5.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.6.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.6.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.6.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.7.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.7.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.7.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.8.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.8.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.8.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.9.down_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.9.gate_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.experts.9.up_proj.weight": "model-00002-of-00011.safetensors",
+    "model.layers.1.moe.router.weight": "model-00001-of-00011.safetensors",
+    "model.layers.1.pre_moe_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.2.mamba.A_log": "model-00003-of-00011.safetensors",
+    "model.layers.2.mamba.B_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.2.mamba.C_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.2.mamba.D": "model-00003-of-00011.safetensors",
+    "model.layers.2.mamba.conv1d.bias": "model-00003-of-00011.safetensors",
+    "model.layers.2.mamba.conv1d.weight": "model-00003-of-00011.safetensors",
+    "model.layers.2.mamba.dt_layernorm.weight": "model-00003-of-00011.safetensors",
+    "model.layers.2.mamba.dt_proj.bias": "model-00003-of-00011.safetensors",
+    "model.layers.2.mamba.dt_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.2.mamba.in_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.2.mamba.out_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.2.mamba.x_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.2.moe.experts.0.down_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.2.moe.experts.0.gate_proj.weight": "model-00003-of-00011.safetensors",
+    "model.layers.2.moe.experts.0.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.2.pre_moe_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.3.mamba.A_log": "model-00004-of-00011.safetensors",
+    "model.layers.3.mamba.B_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.mamba.C_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.mamba.D": "model-00004-of-00011.safetensors",
+    "model.layers.3.mamba.conv1d.bias": "model-00004-of-00011.safetensors",
+    "model.layers.3.mamba.conv1d.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.mamba.dt_layernorm.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.mamba.dt_proj.bias": "model-00004-of-00011.safetensors",
+    "model.layers.3.mamba.dt_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.mamba.in_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.mamba.out_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.mamba.x_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.0.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.0.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.0.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.1.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.1.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.1.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.10.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.10.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.10.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.11.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.11.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.11.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.12.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.12.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.12.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.13.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.3.moe.experts.13.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.3.moe.experts.13.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.3.moe.experts.14.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.3.moe.experts.14.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.3.moe.experts.14.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.3.moe.experts.15.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.3.moe.experts.15.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.3.moe.experts.15.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.3.moe.experts.2.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.2.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.2.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.3.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.3.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.3.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.4.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.4.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.4.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.5.down_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.5.gate_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.5.up_proj.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.moe.experts.6.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.6.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.6.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.7.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.7.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.7.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.8.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.8.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.8.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.9.down_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.9.gate_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.experts.9.up_proj.weight": "model-00005-of-00011.safetensors",
+    "model.layers.3.moe.router.weight": "model-00004-of-00011.safetensors",
+    "model.layers.3.pre_moe_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.4.moe.experts.0.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.4.moe.experts.0.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.4.moe.experts.0.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.4.pre_moe_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.mamba.A_log": "model-00006-of-00011.safetensors",
+    "model.layers.5.mamba.B_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.mamba.C_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.mamba.D": "model-00006-of-00011.safetensors",
+    "model.layers.5.mamba.conv1d.bias": "model-00006-of-00011.safetensors",
+    "model.layers.5.mamba.conv1d.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.mamba.dt_layernorm.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.mamba.dt_proj.bias": "model-00006-of-00011.safetensors",
+    "model.layers.5.mamba.dt_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.mamba.in_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.mamba.out_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.mamba.x_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.moe.experts.0.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.moe.experts.0.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.moe.experts.0.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.moe.experts.1.down_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.moe.experts.1.gate_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.moe.experts.1.up_proj.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.moe.experts.10.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.10.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.10.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.11.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.11.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.11.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.12.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.12.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.12.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.13.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.13.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.13.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.14.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.14.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.14.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.15.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.15.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.15.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.2.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.2.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.2.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.3.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.3.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.3.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.4.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.4.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.4.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.5.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.5.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.5.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.6.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.6.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.6.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.7.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.7.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.7.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.8.down_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.8.gate_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.8.up_proj.weight": "model-00007-of-00011.safetensors",
+    "model.layers.5.moe.experts.9.down_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.9.gate_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.experts.9.up_proj.weight": "model-00008-of-00011.safetensors",
+    "model.layers.5.moe.router.weight": "model-00006-of-00011.safetensors",
+    "model.layers.5.pre_moe_layernorm.weight": "model-00008-of-00011.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.6.mamba.A_log": "model-00008-of-00011.safetensors",
+    "model.layers.6.mamba.B_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.6.mamba.C_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.6.mamba.D": "model-00008-of-00011.safetensors",
+    "model.layers.6.mamba.conv1d.bias": "model-00008-of-00011.safetensors",
+    "model.layers.6.mamba.conv1d.weight": "model-00008-of-00011.safetensors",
+    "model.layers.6.mamba.dt_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.6.mamba.dt_proj.bias": "model-00009-of-00011.safetensors",
+    "model.layers.6.mamba.dt_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.6.mamba.in_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.6.mamba.out_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.6.mamba.x_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.6.moe.experts.0.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.6.moe.experts.0.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.6.moe.experts.0.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.6.pre_moe_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.mamba.A_log": "model-00009-of-00011.safetensors",
+    "model.layers.7.mamba.B_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.mamba.C_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.mamba.D": "model-00009-of-00011.safetensors",
+    "model.layers.7.mamba.conv1d.bias": "model-00009-of-00011.safetensors",
+    "model.layers.7.mamba.conv1d.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.mamba.dt_layernorm.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.mamba.dt_proj.bias": "model-00009-of-00011.safetensors",
+    "model.layers.7.mamba.dt_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.mamba.in_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.mamba.out_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.mamba.x_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.0.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.0.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.0.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.1.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.1.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.1.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.10.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.10.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.10.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.11.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.11.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.11.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.moe.experts.12.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.moe.experts.12.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.moe.experts.12.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.moe.experts.13.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.moe.experts.13.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.moe.experts.13.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.moe.experts.14.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.moe.experts.14.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.moe.experts.14.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.moe.experts.15.down_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.moe.experts.15.gate_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.moe.experts.15.up_proj.weight": "model-00011-of-00011.safetensors",
+    "model.layers.7.moe.experts.2.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.2.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.2.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.3.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.3.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.3.up_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.4.down_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.4.gate_proj.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.moe.experts.4.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.5.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.5.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.5.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.6.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.6.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.6.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.7.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.7.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.7.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.8.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.8.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.8.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.9.down_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.9.gate_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.experts.9.up_proj.weight": "model-00010-of-00011.safetensors",
+    "model.layers.7.moe.router.weight": "model-00009-of-00011.safetensors",
+    "model.layers.7.pre_moe_layernorm.weight": "model-00011-of-00011.safetensors"
+  }
+}