Update model with LoRA adapter

README.md

@@ -0,0 +1,202 @@
+---
+base_model: ''
+library_name: peft
+---
+
+# 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. -->
+
+
+
+- **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]
+### Framework versions
+
+- PEFT 0.14.0

model-00001-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cd3e07226abf36e5a4d59c1fad4f73cd64f1062c777bd87c248ca8b1b79c1f9
-size 4947827632
+oid sha256:8bf3e7b6b69bca98e2795ccfbd8fc06e0a5bd7e9ca453f08f14293e374a20046
+size 4976361384

model-00002-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03cf97b5896f8b8a1e90fca0023a029242fdb0f974248984d69522136818ba88
-size 4987779168
+oid sha256:76a68395368c49df4ccd5183ef3616b752428cc78adc8010a4404d8846f1b377
+size 4984907872

model-00003-of-00003.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d4ccef3310d54817c493930f48c67e48c14bcfe76bb58bf3eaa9ccdecba1f6f8
-size 1949903376
+oid sha256:da4ef7a5dacb58a0cc0cd35750e005eb8411d71a77a6a66b2274c576eae68d41
+size 732141104

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 11885195552
+    "total_size": 10693095712
   },
   "weight_map": {
     "audio_projector.0.bias": "model-00001-of-00003.safetensors",
@@ -1400,19 +1400,19 @@
     "language_model.model.base_model.model.layers.25.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.25.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.25.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.mlp.up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.mlp.up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.self_attn.k_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
@@ -1427,87 +1427,87 @@
     "language_model.model.base_model.model.layers.26.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.26.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.gate_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.gate_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.mlp.up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.k_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.k_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.o_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.o_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.q_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.q_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.v_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.27.self_attn.v_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.gate_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.gate_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.mlp.up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.k_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.k_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.o_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.o_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.q_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.q_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.v_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.28.self_attn.v_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.gate_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.gate_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.mlp.up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.k_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.k_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.o_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.o_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.q_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.q_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.v_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.29.self_attn.v_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.k_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.k_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.q_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.q_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.27.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.k_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.k_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.q_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.q_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.28.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.k_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.k_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.q_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.q_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.29.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.3.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.3.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
@@ -1539,29 +1539,29 @@
     "language_model.model.base_model.model.layers.30.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
     "language_model.model.base_model.model.layers.30.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
     "language_model.model.base_model.model.layers.30.mlp.down_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.mlp.gate_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.mlp.gate_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.mlp.gate_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.mlp.up_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.mlp.up_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.mlp.up_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.base_model.model.layers.30.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.base_model.model.layers.30.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.k_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.k_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.k_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.k_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.o_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.o_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.o_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.q_norm.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.q_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.q_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.q_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.v_proj.base_layer.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.v_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.30.self_attn.v_proj.lora_B.speech.weight": "model-00003-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.k_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.k_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.q_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.q_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.30.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
     "language_model.model.base_model.model.layers.31.mlp.down_proj.base_layer.weight": "model-00003-of-00003.safetensors",
     "language_model.model.base_model.model.layers.31.mlp.down_proj.lora_A.speech.weight": "model-00003-of-00003.safetensors",
@@ -1724,19 +1724,19 @@
     "language_model.model.base_model.model.layers.6.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.6.self_attn.v_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.6.self_attn.v_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.down_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.down_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.down_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.gate_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.gate_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.up_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.up_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.mlp.up_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.7.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.7.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.7.self_attn.k_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
@@ -1755,29 +1755,29 @@
     "language_model.model.base_model.model.layers.8.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.mlp.down_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.mlp.gate_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.mlp.gate_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.mlp.gate_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.mlp.gate_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.mlp.gate_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.mlp.gate_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.mlp.up_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.mlp.up_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.mlp.up_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.8.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.k_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.k_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.k_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.k_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.o_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.o_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.o_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.q_norm.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.q_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.q_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.q_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.v_proj.base_layer.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.v_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",
-    "language_model.model.base_model.model.layers.8.self_attn.v_proj.lora_B.speech.weight": "model-00002-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.k_norm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.k_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.k_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.k_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.o_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.o_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.o_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.q_norm.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.q_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.q_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.q_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.v_proj.base_layer.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.v_proj.lora_A.speech.weight": "model-00001-of-00003.safetensors",
+    "language_model.model.base_model.model.layers.8.self_attn.v_proj.lora_B.speech.weight": "model-00001-of-00003.safetensors",
     "language_model.model.base_model.model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.9.mlp.down_proj.base_layer.weight": "model-00002-of-00003.safetensors",
     "language_model.model.base_model.model.layers.9.mlp.down_proj.lora_A.speech.weight": "model-00002-of-00003.safetensors",

speech/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb71a3beb88481e89b90f3485f86bbc544c76975e3b0017d40e4c385a5634a76
-size 2384262280
+oid sha256:ffa174122957ca1ad890258291cc5a8ae0a8bbfd281dc330075412677c6432c7
+size 1192162472