Upload GLAForCausalLM

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

@@ -3,6 +3,7 @@
   "architectures": [
     "GLAForCausalLM"
   ],
+  "attn": null,
   "attn_mode": "chunk",
   "bos_token_id": 1,
   "clamp_min": null,
@@ -28,7 +29,7 @@
   "share_conv_kernel": true,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
-  "transformers_version": "4.42.3",
+  "transformers_version": "4.48.2",
   "use_cache": true,
   "use_gk": true,
   "use_gv": false,

generation_config.json

@@ -2,5 +2,5 @@
   "_from_model_config": true,
   "bos_token_id": 1,
   "eos_token_id": 2,
-  "transformers_version": "4.42.3"
+  "transformers_version": "4.48.2"
 }

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0381fcd860459b2fd37dc1dd23a365b31098b6e2d926b06197a8ad1b9ddc9e9d
-size 4945009656
+oid sha256:c761d1c8dde9cb4351d1e70f3ff013e03fab8087978db10bc0a3cb30ad25a3a1
+size 4945010896

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d2842706e64b0a3e95e66fc688008c2c827eccb1c04ef1f52e9888976026d5fc
-size 4968253424
+oid sha256:81e05a1a4d19c4aa6c64ec28d1847981b65ac2997e87028b4556599dc73030f4
+size 4968254672

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:133cdd5750d21f56735e438b74f1e335e01e63772bb64f95a670e4fa2540a6d2
-size 4575560696
+oid sha256:e7ba758aafea9bd2983e8695bb47cc13377c2489dfeed6e0b346e41f72ea0fed
+size 4575561832

model.safetensors.index.json

@@ -16,6 +16,7 @@
     "model.layers.0.attn_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.0.mlp_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.attn.g_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.attn.gk_proj.0.weight": "model-00001-of-00003.safetensors",
@@ -28,6 +29,7 @@
     "model.layers.1.attn_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.1.mlp_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.attn.g_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.attn.gk_proj.0.weight": "model-00001-of-00003.safetensors",
@@ -40,6 +42,7 @@
     "model.layers.10.attn_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.10.mlp_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.11.attn.g_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.11.attn.gk_proj.0.weight": "model-00002-of-00003.safetensors",
@@ -52,6 +55,7 @@
     "model.layers.11.attn_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.11.mlp_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.12.attn.g_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.12.attn.gk_proj.0.weight": "model-00002-of-00003.safetensors",
@@ -64,6 +68,7 @@
     "model.layers.12.attn_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.12.mlp_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.attn.g_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.attn.gk_proj.0.weight": "model-00002-of-00003.safetensors",
@@ -76,6 +81,7 @@
     "model.layers.13.attn_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.13.mlp_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.attn.g_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.attn.gk_proj.0.weight": "model-00002-of-00003.safetensors",
@@ -88,6 +94,7 @@
     "model.layers.14.attn_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.14.mlp_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.attn.g_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.attn.gk_proj.0.weight": "model-00002-of-00003.safetensors",
@@ -100,6 +107,7 @@
     "model.layers.15.attn_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.15.mlp_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.attn.g_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.attn.gk_proj.0.weight": "model-00002-of-00003.safetensors",
@@ -112,6 +120,7 @@
     "model.layers.16.attn_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.16.mlp_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.attn.g_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.attn.gk_proj.0.weight": "model-00002-of-00003.safetensors",
@@ -124,6 +133,7 @@
     "model.layers.17.attn_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.17.mlp_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.attn.g_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.attn.gk_proj.0.weight": "model-00002-of-00003.safetensors",
@@ -136,6 +146,7 @@
     "model.layers.18.attn_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.18.mlp_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.attn.g_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.attn.gk_proj.0.weight": "model-00002-of-00003.safetensors",
@@ -148,6 +159,7 @@
     "model.layers.19.attn_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.19.mlp_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.2.attn.g_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.attn.gk_proj.0.weight": "model-00001-of-00003.safetensors",
@@ -160,6 +172,7 @@
     "model.layers.2.attn_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.2.mlp_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.20.attn.g_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.attn.gk_proj.0.weight": "model-00002-of-00003.safetensors",
@@ -172,6 +185,7 @@
     "model.layers.20.attn_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.20.mlp_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.attn.g_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.attn.gk_proj.0.weight": "model-00002-of-00003.safetensors",
@@ -184,6 +198,7 @@
     "model.layers.21.attn_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
     "model.layers.21.mlp_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.attn.g_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.22.attn.gk_proj.0.weight": "model-00002-of-00003.safetensors",
@@ -196,6 +211,7 @@
     "model.layers.22.attn_norm.weight": "model-00002-of-00003.safetensors",
     "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.22.mlp_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.23.attn.g_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.23.attn.gk_proj.0.weight": "model-00003-of-00003.safetensors",
@@ -208,6 +224,7 @@
     "model.layers.23.attn_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.23.mlp_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.attn.g_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.attn.gk_proj.0.weight": "model-00003-of-00003.safetensors",
@@ -220,6 +237,7 @@
     "model.layers.24.attn_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.24.mlp_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.attn.g_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.attn.gk_proj.0.weight": "model-00003-of-00003.safetensors",
@@ -232,6 +250,7 @@
     "model.layers.25.attn_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.25.mlp_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.attn.g_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.attn.gk_proj.0.weight": "model-00003-of-00003.safetensors",
@@ -244,6 +263,7 @@
     "model.layers.26.attn_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.26.mlp_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.attn.g_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.attn.gk_proj.0.weight": "model-00003-of-00003.safetensors",
@@ -256,6 +276,7 @@
     "model.layers.27.attn_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.27.mlp_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.attn.g_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.attn.gk_proj.0.weight": "model-00003-of-00003.safetensors",
@@ -268,6 +289,7 @@
     "model.layers.28.attn_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.28.mlp_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.attn.g_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.attn.gk_proj.0.weight": "model-00003-of-00003.safetensors",
@@ -280,6 +302,7 @@
     "model.layers.29.attn_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.29.mlp_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.3.attn.g_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.attn.gk_proj.0.weight": "model-00001-of-00003.safetensors",
@@ -292,6 +315,7 @@
     "model.layers.3.attn_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.3.mlp_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.30.attn.g_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.attn.gk_proj.0.weight": "model-00003-of-00003.safetensors",
@@ -304,6 +328,7 @@
     "model.layers.30.attn_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.30.mlp_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.attn.g_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.attn.gk_proj.0.weight": "model-00003-of-00003.safetensors",
@@ -316,6 +341,7 @@
     "model.layers.31.attn_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
     "model.layers.31.mlp_norm.weight": "model-00003-of-00003.safetensors",
     "model.layers.4.attn.g_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.attn.gk_proj.0.weight": "model-00001-of-00003.safetensors",
@@ -328,6 +354,7 @@
     "model.layers.4.attn_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.4.mlp_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.attn.g_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.attn.gk_proj.0.weight": "model-00001-of-00003.safetensors",
@@ -340,6 +367,7 @@
     "model.layers.5.attn_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.5.mlp_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.attn.g_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.attn.gk_proj.0.weight": "model-00001-of-00003.safetensors",
@@ -352,6 +380,7 @@
     "model.layers.6.attn_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.6.mlp_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.attn.g_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.attn.gk_proj.0.weight": "model-00001-of-00003.safetensors",
@@ -364,6 +393,7 @@
     "model.layers.7.attn_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.7.mlp_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.attn.g_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.attn.gk_proj.0.weight": "model-00001-of-00003.safetensors",
@@ -376,6 +406,7 @@
     "model.layers.8.attn_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.8.mlp_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.attn.g_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.attn.gk_proj.0.weight": "model-00001-of-00003.safetensors",
@@ -388,6 +419,7 @@
     "model.layers.9.attn_norm.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
     "model.layers.9.mlp_norm.weight": "model-00001-of-00003.safetensors",
     "model.norm.weight": "model-00003-of-00003.safetensors"
   }