Upload DeltaNetForCausalLM

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

@@ -11,6 +11,7 @@
   "expand_k": 1,
   "expand_v": 1,
   "fuse_cross_entropy": true,
+  "fuse_norm": true,
   "hidden_act": "swish",
   "hidden_ratio": 4,
   "hidden_size": 2560,
@@ -33,4 +34,4 @@
   "use_output_norm": true,
   "use_short_conv": true,
   "vocab_size": 32000
-}
+}

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c079868b8f9c695c5dd2f4837ac4b0d2cdf67cf50540cdbcd926d8c2a3ae2e63
-size 4979631520
+oid sha256:3cfc0c88ff8fcc5ec6300876b6a037fd7188f5c7db929dd57abdd0ee18764607
+size 4979634856

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:390c1da40aecbe6fa6829a7c51612f103d27ed1b840aba612f7c54e0dd038ba3
-size 428786768
+oid sha256:fd584ce6fc67096444f7a8978bf919085cd6983b3dce3fea166542562c527e38
+size 428786984

model.safetensors.index.json

@@ -17,6 +17,7 @@
     "model.layers.0.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -30,6 +31,7 @@
     "model.layers.1.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -43,6 +45,7 @@
     "model.layers.10.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -56,6 +59,7 @@
     "model.layers.11.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -69,6 +73,7 @@
     "model.layers.12.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -82,6 +87,7 @@
     "model.layers.13.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -95,6 +101,7 @@
     "model.layers.14.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -108,6 +115,7 @@
     "model.layers.15.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -121,6 +129,7 @@
     "model.layers.16.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -134,6 +143,7 @@
     "model.layers.17.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -147,6 +157,7 @@
     "model.layers.18.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -160,6 +171,7 @@
     "model.layers.19.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -173,6 +185,7 @@
     "model.layers.2.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -186,6 +199,7 @@
     "model.layers.20.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -199,6 +213,7 @@
     "model.layers.21.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -212,6 +227,7 @@
     "model.layers.22.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -225,6 +241,7 @@
     "model.layers.23.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -238,6 +255,7 @@
     "model.layers.24.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -251,6 +269,7 @@
     "model.layers.25.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -264,6 +283,7 @@
     "model.layers.26.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -277,6 +297,7 @@
     "model.layers.27.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -290,6 +311,7 @@
     "model.layers.28.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -303,6 +325,7 @@
     "model.layers.29.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -316,6 +339,7 @@
     "model.layers.3.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -329,6 +353,7 @@
     "model.layers.30.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.31.attn.b_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.attn.k_conv1d.weight": "model-00002-of-00002.safetensors",
@@ -342,6 +367,7 @@
     "model.layers.31.attn_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp_norm.weight": "model-00002-of-00002.safetensors",
     "model.layers.4.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -355,6 +381,7 @@
     "model.layers.4.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -368,6 +395,7 @@
     "model.layers.5.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -381,6 +409,7 @@
     "model.layers.6.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -394,6 +423,7 @@
     "model.layers.7.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -407,6 +437,7 @@
     "model.layers.8.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.attn.b_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.attn.k_conv1d.weight": "model-00001-of-00002.safetensors",
@@ -420,6 +451,7 @@
     "model.layers.9.attn_norm.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp_norm.weight": "model-00001-of-00002.safetensors",
     "model.norm.weight": "model-00002-of-00002.safetensors"
   }