Upload folder using huggingface_hub (#1)

- 52acb41ad8056689fce94a4ceaee2160a4d14eb2d7e6c4d440b30d7dd60876ca (19c28fb994a5b7fe83689d01f02cd5e999aceb7d)
- fb05d9283b502c442e354afda851eaf248941a819c9f3bb38d7d4be09eedc2fd (8886e728e25eb130845ba56868b59265e42114f9)
- 54e0292f72195c697b45e017936310a38c4ec52f5731b6238309b69908ad964b (1915a7d862b5bf55776c584e9fceedc4a637fe80)

README.md

@@ -0,0 +1,85 @@
+---
+thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg"
+base_model: zelk12/MT4-Gen4-GMUBI-gemma-2-9B
+metrics:
+- memory_disk
+- memory_inference
+- inference_latency
+- inference_throughput
+- inference_CO2_emissions
+- inference_energy_consumption
+tags:
+- pruna-ai
+---
+<!-- header start -->
+<!-- 200823 -->
+<div style="width: auto; margin-left: auto; margin-right: auto">
+    <a href="https://docs.pruna.ai/en/latest/setup/pip.html" target="_blank" rel="noopener noreferrer">
+        <img src="https://imgur.com/rVAgqMY.png" alt="PrunaAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
+    </a>
+</div>
+<!-- header end -->
+
+[![Twitter](https://img.shields.io/twitter/follow/PrunaAI?style=social)](https://twitter.com/PrunaAI)
+[![GitHub](https://img.shields.io/github/followers/PrunaAI?label=Follow%20%40PrunaAI&style=social)](https://github.com/PrunaAI)
+[![LinkedIn](https://img.shields.io/badge/LinkedIn-Connect-blue)](https://www.linkedin.com/company/93832878/admin/feed/posts/?feedType=following)
+[![Discord](https://img.shields.io/badge/Discord-Join%20Us-blue?style=social&logo=discord)](https://discord.gg/rskEr4BZJx)
+
+# Simply make AI models cheaper, smaller, faster, and greener!
+
+- Give a thumbs up if you like this model!
+- Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
+- Request access to easily compress your *own* AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
+- Read the documentations to know more [here](https://pruna-ai-pruna.readthedocs-hosted.com/en/latest/)
+- Join Pruna AI community on Discord [here](https://discord.gg/CP4VSgck) to share feedback/suggestions or get help.
+
+## Results
+
+![image info](./plots.png)
+
+**Frequently Asked Questions**
+- ***How does the compression work?*** The model is compressed with llm-int8.
+- ***How does the model quality change?*** The quality of the model output might vary compared to the base model.
+- ***How is the model efficiency evaluated?*** These results were obtained with configuration described in `model/smash_config.json` and are obtained after a hardware warmup. The smashed model is directly compared to the original base model. Efficiency results may vary in other settings (e.g. other hardware, image size, batch size, ...). We recommend to directly run them in the use-case conditions to know if the smashed model can benefit you.
+- ***What is the model format?*** We use safetensors.
+- ***What calibration data has been used?*** If needed by the compression method, we used WikiText as the calibration data.
+- ***What is the naming convention for Pruna Huggingface models?*** We take the original model name and append "turbo", "tiny", or "green" if the smashed model has a measured inference speed, inference memory, or inference energy consumption which is less than 90% of the original base model.
+- ***How to compress my own models?*** You can request premium access to more compression methods and tech support for your specific use-cases [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
+- ***What are "first" metrics?*** Results mentioning "first" are obtained after the first run of the model. The first run might take more memory or be slower than the subsequent runs due cuda overheads.
+- ***What are "Sync" and "Async" metrics?*** "Sync" metrics are obtained by syncing all GPU processes and stop measurement when all of them are executed. "Async" metrics are obtained without syncing all GPU processes and stop when the model output can be used by the CPU. We provide both metrics since both could be relevant depending on the use-case. We recommend to test the efficiency gains directly in your use-cases.
+
+## Setup
+
+You can run the smashed model with these steps:
+
+0. Check requirements from the original repo zelk12/MT4-Gen4-GMUBI-gemma-2-9B installed. In particular, check python, cuda, and transformers versions.
+1. Make sure that you have installed quantization related packages.
+    ```bash
+    pip install transformers accelerate bitsandbytes>0.37.0
+    ```
+2. Load & run the model.
+    ```python 
+   from transformers import AutoModelForCausalLM, AutoTokenizer
+   
+
+   model = AutoModelForCausalLM.from_pretrained("PrunaAI/zelk12-MT4-Gen4-GMUBI-gemma-2-9B-bnb-8bit-smashed", trust_remote_code=True, device_map='auto')
+   tokenizer = AutoTokenizer.from_pretrained("zelk12/MT4-Gen4-GMUBI-gemma-2-9B")
+    
+   input_ids = tokenizer("What is the color of prunes?,", return_tensors='pt').to(model.device)["input_ids"]
+    
+   outputs = model.generate(input_ids, max_new_tokens=216)
+   tokenizer.decode(outputs[0])
+    ```
+
+## Configurations
+
+The configuration info are in `smash_config.json`.
+
+## Credits & License
+
+The license of the smashed model follows the license of the original model. Please check the license of the original model zelk12/MT4-Gen4-GMUBI-gemma-2-9B before using this model which provided the base model. The license  of the `pruna-engine` is [here](https://pypi.org/project/pruna-engine/) on Pypi.
+
+## Want to compress other models?
+
+- Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
+- Do it by yourself [here](https://docs.pruna.ai/en/latest/setup/pip.html).

config.json

@@ -0,0 +1,52 @@
+{
+    "_name_or_path": "/covalent/.cache/models/tmp63r76xg6zltketw4",
+    "architectures": [
+        "Gemma2ForCausalLM"
+    ],
+    "attention_bias": false,
+    "attention_dropout": 0.0,
+    "attn_logit_softcapping": 50.0,
+    "bos_token_id": 2,
+    "cache_implementation": "hybrid",
+    "eos_token_id": 1,
+    "final_logit_softcapping": 30.0,
+    "head_dim": 256,
+    "hidden_act": "gelu_pytorch_tanh",
+    "hidden_activation": "gelu_pytorch_tanh",
+    "hidden_size": 3584,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 8192,
+    "model_type": "gemma2",
+    "num_attention_heads": 16,
+    "num_hidden_layers": 42,
+    "num_key_value_heads": 8,
+    "pad_token_id": 0,
+    "quantization_config": {
+        "_load_in_4bit": false,
+        "_load_in_8bit": true,
+        "bnb_4bit_compute_dtype": "bfloat16",
+        "bnb_4bit_quant_storage": "uint8",
+        "bnb_4bit_quant_type": "fp4",
+        "bnb_4bit_use_double_quant": false,
+        "llm_int8_enable_fp32_cpu_offload": false,
+        "llm_int8_has_fp16_weight": false,
+        "llm_int8_skip_modules": [
+            "lm_head"
+        ],
+        "llm_int8_threshold": 6.0,
+        "load_in_4bit": false,
+        "load_in_8bit": true,
+        "quant_method": "bitsandbytes"
+    },
+    "query_pre_attn_scalar": 224,
+    "rms_norm_eps": 1e-06,
+    "rope_theta": 10000.0,
+    "sliding_window": 4096,
+    "sliding_window_size": 4096,
+    "torch_dtype": "float16",
+    "transformers_version": "4.46.2",
+    "use_cache": true,
+    "vocab_size": 256000,
+    "api_key": null
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "pad_token_id": 0,
+  "transformers_version": "4.46.2"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c094e3d28f64aabe1f406780fdbde63baecdec566517425cde4198bf395fd9c5
+size 4957798951

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8d95d59a2d6546b63855f5ef3d93cdffaf439879015de15032edb9ab04daed7
+size 4959710487

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99c86bdefa6c71ef7ef224a44cc84a81f6a9d85180cb72c1dec33b0f8ae39d9b
+size 249819648

model.safetensors.index.json

@@ -0,0 +1,1059 @@
+{
+  "metadata": {
+    "total_size": 10167213350
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.36.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.37.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.38.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.down_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.post_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.pre_feedforward_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.39.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.SCB": "model-00003-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.mlp.down_proj.weight_format": "model-00003-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.gate_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.mlp.up_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.k_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.o_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.q_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.SCB": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.40.self_attn.v_proj.weight_format": "model-00002-of-00003.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.SCB": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.down_proj.weight_format": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.SCB": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.gate_proj.weight_format": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.SCB": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.mlp.up_proj.weight_format": "model-00003-of-00003.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.post_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.pre_feedforward_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.SCB": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.k_proj.weight_format": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.SCB": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.o_proj.weight_format": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.SCB": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.q_proj.weight_format": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.SCB": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.41.self_attn.v_proj.weight_format": "model-00003-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.pre_feedforward_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.SCB": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight_format": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

smash_config.json

@@ -0,0 +1,35 @@
+{
+    "comp_cgenerate_active": false,
+    "comp_ctranslate_active": false,
+    "comp_cwhisper_active": false,
+    "comp_diffusers2_active": false,
+    "comp_ifw_active": false,
+    "comp_onediff_active": false,
+    "comp_step_caching_active": false,
+    "comp_torch_compile_active": false,
+    "comp_ws2t_active": false,
+    "comp_x-fast_active": false,
+    "prune_torch-structured_active": false,
+    "quant_aqlm_active": false,
+    "quant_awq_active": false,
+    "quant_gptq_active": false,
+    "quant_half_active": false,
+    "quant_hqq_active": false,
+    "quant_llm-int8_active": true,
+    "quant_quanto_active": false,
+    "quant_torch_dynamic_active": false,
+    "quant_torch_static_active": false,
+    "quant_llm-int8_compute_dtype": "bfloat16",
+    "quant_llm-int8_double_quant": false,
+    "quant_llm-int8_enable_fp32_cpu_offload": false,
+    "quant_llm-int8_has_fp16_weight": false,
+    "quant_llm-int8_quant_type": "fp4",
+    "quant_llm-int8_threshold": 6.0,
+    "quant_llm-int8_weight_bits": 8,
+    "max_batch_size": 1,
+    "device": "cuda",
+    "cache_dir": "/covalent/.cache/models/tmp63r76xg6",
+    "task": "",
+    "save_load_fn": "bitsandbytes",
+    "save_load_fn_args": {}
+}