Upload JambaForCausalLM

README.md

@@ -0,0 +1,199 @@
+---
+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,
+  "d_model": 768,
+  "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_proj_bias": false,
+  "max_position_embeddings": 2048,
+  "model_type": "jamba",
+  "num_attention_heads": 32,
+  "num_experts": 16,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 8,
+  "num_key_value_heads": 8,
+  "num_logits_to_keep": 1,
+  "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": "4.46.2",
+  "use_cache": true,
+  "use_mamba_kernels": true,
+  "vocab_size": 128000
+}

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": "4.46.2"
+}

model-00001-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f9cf1c3c96216bd581c7578254bcaa04314a3210ec68d0dad35559ecb65699a
+size 4818966800

model-00002-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea523619b039d1d0281aff50c71ff838140edc638bb35644e8f2426092d5a398
+size 4932504312

model-00003-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db15f292786403482bc67341f66a8a44dc787ff9bfbaa84adc90da5cc63bf107
+size 4932504328

model-00004-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:09f2d9dc9ff9ffd992889a009105b4e5b9b5b25788a7a46e06f962b29f0c93b0
+size 4835778056

model-00005-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0288d5135ba72ee1807d9ba4e6dede2888ee5fda5331f48ddc174509cf7f6c4e
+size 4932504312

model-00006-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59ae5db4f240755472cd591de19366b931947806a4bd6294485ec9ed5a2fc110
+size 4817196784

model-00007-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4eea42c85183494efd653304458087b6cda1aa6cc059cddf4094f4b0ffd7371f
+size 4932504312

model-00008-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5459728d7d741b514dbcbe8a7c0b091d7dcdf25c4bafa9c00aa5009f983d0620
+size 4932504320

model-00009-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cce39f30980753d7449f64d3ffb06f7d197309e8375f324d5057fe46f25ad9b9
+size 4835778088

model-00010-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:980d357fccfb9ce7a6d9623079a5c256a7f4632a795d5208304fc45ee1b4ab03
+size 4932504312

model-00011-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8750be03851eac7fcb1bfee24d1e2ebcfed4c1aefca72606478cb7b7c3dd6dd3
+size 4227910320

model-00012-of-00012.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c701fc6a4e7f89ee41ad2c93d5fc9c1b75232ca5123e6d652dde4d92f0548af8
+size 2097152128

model.safetensors.index.json

@@ -0,0 +1,322 @@
+{
+  "metadata": {
+    "total_size": 55227768704
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00012-of-00012.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00012.safetensors",
+    "model.final_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.0.feed_forward.down_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.feed_forward.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.feed_forward.up_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mamba.A_log": "model-00001-of-00012.safetensors",
+    "model.layers.0.mamba.D": "model-00001-of-00012.safetensors",
+    "model.layers.0.mamba.b_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mamba.c_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mamba.conv1d.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.mamba.conv1d.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mamba.dt_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mamba.dt_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.0.mamba.dt_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mamba.in_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mamba.out_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.mamba.x_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.0.pre_ff_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.0.down_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.0.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.0.up_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.1.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.1.gate_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.1.up_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.10.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.10.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.10.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.11.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.11.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.11.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.12.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.12.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.12.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.13.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.13.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.13.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.14.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.14.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.14.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.15.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.15.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.15.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.2.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.2.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.2.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.3.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.3.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.3.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.4.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.4.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.4.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.5.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.5.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.5.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.6.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.6.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.6.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.7.down_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.7.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.7.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.8.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.8.gate_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.8.up_proj.weight": "model-00002-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.9.down_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.9.gate_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.experts.9.up_proj.weight": "model-00003-of-00012.safetensors",
+    "model.layers.1.feed_forward.router.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.1.mamba.A_log": "model-00001-of-00012.safetensors",
+    "model.layers.1.mamba.D": "model-00001-of-00012.safetensors",
+    "model.layers.1.mamba.b_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mamba.c_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mamba.conv1d.bias": "model-00001-of-00012.safetensors",
+    "model.layers.1.mamba.conv1d.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mamba.dt_layernorm.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mamba.dt_proj.bias": "model-00001-of-00012.safetensors",
+    "model.layers.1.mamba.dt_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mamba.in_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mamba.out_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.mamba.x_proj.weight": "model-00001-of-00012.safetensors",
+    "model.layers.1.pre_ff_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.2.feed_forward.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.2.feed_forward.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.2.feed_forward.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.2.mamba.A_log": "model-00004-of-00012.safetensors",
+    "model.layers.2.mamba.D": "model-00004-of-00012.safetensors",
+    "model.layers.2.mamba.b_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.2.mamba.c_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.2.mamba.conv1d.bias": "model-00004-of-00012.safetensors",
+    "model.layers.2.mamba.conv1d.weight": "model-00004-of-00012.safetensors",
+    "model.layers.2.mamba.dt_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.2.mamba.dt_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.2.mamba.dt_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.2.mamba.in_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.2.mamba.out_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.2.mamba.x_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.2.pre_ff_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.0.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.0.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.0.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.1.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.1.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.1.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.10.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.10.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.10.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.11.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.11.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.11.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.12.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.12.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.12.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.13.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.13.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.13.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.14.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.14.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.14.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.15.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.15.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.15.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.2.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.2.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.2.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.3.down_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.3.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.3.up_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.4.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.4.gate_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.4.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.5.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.5.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.5.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.6.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.6.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.6.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.7.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.7.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.7.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.8.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.8.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.8.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.9.down_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.9.gate_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.experts.9.up_proj.weight": "model-00005-of-00012.safetensors",
+    "model.layers.3.feed_forward.router.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.3.mamba.A_log": "model-00004-of-00012.safetensors",
+    "model.layers.3.mamba.D": "model-00004-of-00012.safetensors",
+    "model.layers.3.mamba.b_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.mamba.c_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.mamba.conv1d.bias": "model-00004-of-00012.safetensors",
+    "model.layers.3.mamba.conv1d.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.mamba.dt_layernorm.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.mamba.dt_proj.bias": "model-00004-of-00012.safetensors",
+    "model.layers.3.mamba.dt_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.mamba.in_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.mamba.out_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.mamba.x_proj.weight": "model-00004-of-00012.safetensors",
+    "model.layers.3.pre_ff_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.4.feed_forward.down_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.4.feed_forward.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.4.feed_forward.up_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.4.pre_ff_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.0.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.0.gate_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.0.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.1.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.1.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.1.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.10.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.10.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.10.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.11.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.11.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.11.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.12.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.12.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.12.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.13.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.13.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.13.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.14.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.14.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.14.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.15.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.15.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.15.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.2.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.2.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.2.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.3.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.3.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.3.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.4.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.4.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.4.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.5.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.5.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.5.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.6.down_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.6.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.6.up_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.7.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.7.gate_proj.weight": "model-00007-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.7.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.8.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.8.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.8.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.9.down_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.9.gate_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.experts.9.up_proj.weight": "model-00008-of-00012.safetensors",
+    "model.layers.5.feed_forward.router.weight": "model-00006-of-00012.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.5.mamba.A_log": "model-00006-of-00012.safetensors",
+    "model.layers.5.mamba.D": "model-00006-of-00012.safetensors",
+    "model.layers.5.mamba.b_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.5.mamba.c_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.5.mamba.conv1d.bias": "model-00006-of-00012.safetensors",
+    "model.layers.5.mamba.conv1d.weight": "model-00006-of-00012.safetensors",
+    "model.layers.5.mamba.dt_layernorm.weight": "model-00006-of-00012.safetensors",
+    "model.layers.5.mamba.dt_proj.bias": "model-00006-of-00012.safetensors",
+    "model.layers.5.mamba.dt_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.5.mamba.in_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.5.mamba.out_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.5.mamba.x_proj.weight": "model-00006-of-00012.safetensors",
+    "model.layers.5.pre_ff_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.6.feed_forward.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.6.feed_forward.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.6.feed_forward.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.6.mamba.A_log": "model-00009-of-00012.safetensors",
+    "model.layers.6.mamba.D": "model-00009-of-00012.safetensors",
+    "model.layers.6.mamba.b_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.6.mamba.c_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.6.mamba.conv1d.bias": "model-00009-of-00012.safetensors",
+    "model.layers.6.mamba.conv1d.weight": "model-00009-of-00012.safetensors",
+    "model.layers.6.mamba.dt_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.6.mamba.dt_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.6.mamba.dt_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.6.mamba.in_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.6.mamba.out_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.6.mamba.x_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.6.pre_ff_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.0.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.0.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.0.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.1.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.1.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.1.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.10.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.10.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.10.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.11.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.11.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.11.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.12.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.12.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.12.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.13.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.13.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.13.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.14.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.14.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.14.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.15.down_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.15.gate_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.15.up_proj.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.2.down_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.2.gate_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.2.up_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.3.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.3.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.3.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.4.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.4.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.4.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.5.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.5.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.5.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.6.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.6.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.6.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.7.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.7.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.7.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.8.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.8.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.8.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.9.down_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.9.gate_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.experts.9.up_proj.weight": "model-00010-of-00012.safetensors",
+    "model.layers.7.feed_forward.router.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00011-of-00012.safetensors",
+    "model.layers.7.mamba.A_log": "model-00009-of-00012.safetensors",
+    "model.layers.7.mamba.D": "model-00009-of-00012.safetensors",
+    "model.layers.7.mamba.b_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.mamba.c_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.mamba.conv1d.bias": "model-00009-of-00012.safetensors",
+    "model.layers.7.mamba.conv1d.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.mamba.dt_layernorm.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.mamba.dt_proj.bias": "model-00009-of-00012.safetensors",
+    "model.layers.7.mamba.dt_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.mamba.in_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.mamba.out_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.mamba.x_proj.weight": "model-00009-of-00012.safetensors",
+    "model.layers.7.pre_ff_layernorm.weight": "model-00011-of-00012.safetensors"
+  }
+}