Upload LlamaForCausalLM

README.md

@@ -0,0 +1,199 @@
+---
+library_name: transformers
+tags: []
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+This is the model card of a 🤗 transformers model that has been pushed on the Hub. This model card has been automatically generated.
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]

config.json

@@ -0,0 +1,50 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 256,
+    "hadamard_size": 512,
+    "modules_to_not_convert": [
+      "lm_head"
+    ],
+    "p": 2,
+    "quant_method": "higgs"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.0.dev0",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.47.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c88eebee708c75c91031e93a3fca4150f92a309c215d7b01aa5d62c695a562b
+size 4595760864

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e9a36ad418b0cd9b253f65771552d7dc05cf1abf1170b94de4b4d546aac255d
+size 1050673280

model.safetensors.index.json

@@ -0,0 +1,1194 @@
+{
+  "metadata": {
+    "total_size": 5646303104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.num_sms_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.tables": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.tables2": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors"
+  }
+}