初始化项目，由ModelHub XC社区提供模型

Model: AtlaAI/Selene-1-Mini-Llama-3.1-8B-GPTQ-W4A16
Source: Original Platform

.gitattributes

@@ -0,0 +1,38 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+model-00001-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00002.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,79 @@
+---
+base_model: AtlaAI/Selene-1-Mini-Llama-3.1-8B
+library_name: transformers
+language:
+- en
+- de
+- fr
+- it
+- pt
+- es
+pipeline_tag: text-generation
+tags:
+- llama
+- atla
+- evaluation
+- llm-as-a-judge
+- meta
+- conversational
+- lm-judge
+- llama-cpp
+- gptq
+license: llama3.1
+---
+
+
+<p align="center">
+  <picture>
+    <source 
+      srcset="https://atla-ai.notion.site/image/https%3A%2F%2Fprod-files-secure.s3.us-west-2.amazonaws.com%2Ff08e6e70-73af-4363-9621-90e906b92ebc%2F1bfb4316-1ce6-40a0-800c-253739cfcdeb%2Fatla_white3x.svg?table=block&id=17c309d1-7745-80f9-8f60-e755409acd8d&spaceId=f08e6e70-73af-4363-9621-90e906b92ebc&userId=&cache=v2"
+      media="(prefers-color-scheme: dark)"
+      width="200"
+    />
+    <source 
+      srcset="https://atla-ai.notion.site/image/attachment%3A230448e8-921f-45df-b2af-a3158b6c04cd%3Aatla_black2x.png?table=block&id=188309d1-7745-805c-87e4-c39ca54d598d&spaceId=f08e6e70-73af-4363-9621-90e906b92ebc&width=2000&userId=&cache=v2"
+      media="(prefers-color-scheme: light)"
+      width="200"
+    />
+    <img 
+      src="https://atla-ai.notion.site/image/attachment%3A230448e8-921f-45df-b2af-a3158b6c04cd%3Aatla_black2x.png?table=block&id=188309d1-7745-805c-87e4-c39ca54d598d&spaceId=f08e6e70-73af-4363-9621-90e906b92ebc&width=2000&userId=&cache=v2"
+      width="200"
+    />
+  </picture>
+</p>
+<p align="center">
+    🛝 <a href="https://hf.co/spaces/AtlaAI/selene">Playground</a> | 
+    📄 <a href="https://huggingface.co/spaces/AtlaAI/selene-1-mini-tech-report">Technical report</a> | 
+    💻 <a href="https://github.com/atla-ai/selene-mini">GitHub</a> | 
+    👀 <a href="https://www.atla-ai.com/" style="background-image: linear-gradient(to right, red, orange, yellow, green, blue, indigo, violet); -webkit-background-clip: text; color: transparent; animation: rainbow 5s ease infinite; text-decoration: underline; text-decoration-color: currentColor;">Atla agent evals</a>
+</p>
+
+<style>
+@keyframes rainbow {
+    0% { background-position: 0% 50%; }
+    50% { background-position: 100% 50%; }
+    100% { background-position: 0% 50%; }
+}
+</style>
+
+<style>
+@keyframes rainbow {
+    0% { background-position: 0% 50%; }
+    50% { background-position: 100% 50%; }
+    100% { background-position: 0% 50%; }
+}
+</style>
+
+# AtlaAI/Selene-1-Mini-Llama-3.1-8B-GPTQ-W4A16
+This model was quantised into a **4-bit** (W4A16) format using GPTQ from [`AtlaAI/Selene-1-Mini-Llama-3.1-8B`](https://huggingface.co/AtlaAI/Selene-1-Mini-Llama-3.1-8B).
+This was done using vLLM's llm-compressor library (https://docs.vllm.ai/en/latest/features/quantization/int4.html)
+
+Refer to the [original model card](https://huggingface.co/AtlaAI/Selene-1-Mini-Llama-3.1-8B) for more details on the model.
+
+This quantisation was calibrated using a sample of 512 datapoints from the data used to train Selene-1-Mini.
+As a result, our quantised models show minimal performance degradation, losing <0.5% overall across benchmarks!
+
+For reference, a GPTQ quantized 8-bit [Llama-3.1-8B](neuralmagic/Meta-Llama-3.1-8B-quantized.w8a8) shows ~1.5% degradation across benchmarks.
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/633c4fb100732349209f2aad/K-455q4bMkd11-0P4XSdc.png)
+

config.json

@@ -0,0 +1,306 @@
+{
+  "_name_or_path": "AtlaAI/Selene-1-Mini-Llama-3.1-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "quantization_config": {
+    "config_groups": {
+      "group_0": {
+        "input_activations": null,
+        "output_activations": null,
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "actorder": null,
+          "block_structure": null,
+          "dynamic": false,
+          "group_size": 128,
+          "num_bits": 4,
+          "observer": "minmax",
+          "observer_kwargs": {},
+          "strategy": "group",
+          "symmetric": true,
+          "type": "int"
+        }
+      }
+    },
+    "format": "pack-quantized",
+    "global_compression_ratio": 1.8917232374233346,
+    "ignore": [
+      "lm_head"
+    ],
+    "kv_cache_scheme": null,
+    "quant_method": "compressed-tensors",
+    "quantization_status": "compressed",
+    "sparsity_config": {
+      "format": "dense",
+      "global_sparsity": 0.1408116157465175,
+      "ignore": [
+        "model.layers.0.self_attn.v_proj",
+        "model.layers.0.self_attn.o_proj",
+        "model.layers.0.mlp.gate_proj",
+        "model.layers.0.mlp.up_proj",
+        "model.layers.0.mlp.down_proj",
+        "model.layers.1.self_attn.q_proj",
+        "model.layers.1.self_attn.k_proj",
+        "model.layers.1.self_attn.v_proj",
+        "model.layers.1.self_attn.o_proj",
+        "model.layers.1.mlp.gate_proj",
+        "model.layers.1.mlp.up_proj",
+        "model.layers.1.mlp.down_proj",
+        "model.layers.2.self_attn.q_proj",
+        "model.layers.2.self_attn.k_proj",
+        "model.layers.2.self_attn.v_proj",
+        "model.layers.2.self_attn.o_proj",
+        "model.layers.2.mlp.gate_proj",
+        "model.layers.2.mlp.up_proj",
+        "model.layers.2.mlp.down_proj",
+        "model.layers.3.self_attn.q_proj",
+        "model.layers.3.self_attn.k_proj",
+        "model.layers.3.self_attn.v_proj",
+        "model.layers.3.self_attn.o_proj",
+        "model.layers.3.mlp.gate_proj",
+        "model.layers.3.mlp.up_proj",
+        "model.layers.3.mlp.down_proj",
+        "model.layers.4.self_attn.q_proj",
+        "model.layers.4.self_attn.k_proj",
+        "model.layers.4.self_attn.v_proj",
+        "model.layers.4.self_attn.o_proj",
+        "model.layers.4.mlp.gate_proj",
+        "model.layers.4.mlp.up_proj",
+        "model.layers.4.mlp.down_proj",
+        "model.layers.5.self_attn.q_proj",
+        "model.layers.5.self_attn.k_proj",
+        "model.layers.5.self_attn.v_proj",
+        "model.layers.5.self_attn.o_proj",
+        "model.layers.5.mlp.gate_proj",
+        "model.layers.5.mlp.up_proj",
+        "model.layers.5.mlp.down_proj",
+        "model.layers.6.self_attn.q_proj",
+        "model.layers.6.self_attn.k_proj",
+        "model.layers.6.self_attn.v_proj",
+        "model.layers.6.self_attn.o_proj",
+        "model.layers.6.mlp.gate_proj",
+        "model.layers.6.mlp.up_proj",
+        "model.layers.6.mlp.down_proj",
+        "model.layers.7.self_attn.q_proj",
+        "model.layers.7.self_attn.k_proj",
+        "model.layers.7.self_attn.v_proj",
+        "model.layers.7.self_attn.o_proj",
+        "model.layers.7.mlp.gate_proj",
+        "model.layers.7.mlp.up_proj",
+        "model.layers.7.mlp.down_proj",
+        "model.layers.8.self_attn.q_proj",
+        "model.layers.8.self_attn.k_proj",
+        "model.layers.8.self_attn.v_proj",
+        "model.layers.8.self_attn.o_proj",
+        "model.layers.8.mlp.gate_proj",
+        "model.layers.8.mlp.up_proj",
+        "model.layers.8.mlp.down_proj",
+        "model.layers.9.self_attn.q_proj",
+        "model.layers.9.self_attn.k_proj",
+        "model.layers.9.self_attn.v_proj",
+        "model.layers.9.self_attn.o_proj",
+        "model.layers.9.mlp.gate_proj",
+        "model.layers.9.mlp.up_proj",
+        "model.layers.9.mlp.down_proj",
+        "model.layers.10.self_attn.q_proj",
+        "model.layers.10.self_attn.k_proj",
+        "model.layers.10.self_attn.v_proj",
+        "model.layers.10.self_attn.o_proj",
+        "model.layers.10.mlp.gate_proj",
+        "model.layers.10.mlp.up_proj",
+        "model.layers.10.mlp.down_proj",
+        "model.layers.11.self_attn.q_proj",
+        "model.layers.11.self_attn.k_proj",
+        "model.layers.11.self_attn.v_proj",
+        "model.layers.11.self_attn.o_proj",
+        "model.layers.11.mlp.gate_proj",
+        "model.layers.11.mlp.up_proj",
+        "model.layers.11.mlp.down_proj",
+        "model.layers.12.self_attn.q_proj",
+        "model.layers.12.self_attn.k_proj",
+        "model.layers.12.self_attn.v_proj",
+        "model.layers.12.self_attn.o_proj",
+        "model.layers.12.mlp.gate_proj",
+        "model.layers.12.mlp.up_proj",
+        "model.layers.12.mlp.down_proj",
+        "model.layers.13.self_attn.q_proj",
+        "model.layers.13.self_attn.k_proj",
+        "model.layers.13.self_attn.v_proj",
+        "model.layers.13.self_attn.o_proj",
+        "model.layers.13.mlp.gate_proj",
+        "model.layers.13.mlp.up_proj",
+        "model.layers.13.mlp.down_proj",
+        "model.layers.14.self_attn.q_proj",
+        "model.layers.14.self_attn.k_proj",
+        "model.layers.14.self_attn.v_proj",
+        "model.layers.14.self_attn.o_proj",
+        "model.layers.14.mlp.gate_proj",
+        "model.layers.14.mlp.up_proj",
+        "model.layers.14.mlp.down_proj",
+        "model.layers.15.self_attn.q_proj",
+        "model.layers.15.self_attn.k_proj",
+        "model.layers.15.self_attn.v_proj",
+        "model.layers.15.self_attn.o_proj",
+        "model.layers.15.mlp.gate_proj",
+        "model.layers.15.mlp.up_proj",
+        "model.layers.15.mlp.down_proj",
+        "model.layers.16.self_attn.q_proj",
+        "model.layers.16.self_attn.k_proj",
+        "model.layers.16.self_attn.v_proj",
+        "model.layers.16.self_attn.o_proj",
+        "model.layers.16.mlp.gate_proj",
+        "model.layers.16.mlp.up_proj",
+        "model.layers.16.mlp.down_proj",
+        "model.layers.17.self_attn.q_proj",
+        "model.layers.17.self_attn.k_proj",
+        "model.layers.17.self_attn.v_proj",
+        "model.layers.17.self_attn.o_proj",
+        "model.layers.17.mlp.gate_proj",
+        "model.layers.17.mlp.up_proj",
+        "model.layers.17.mlp.down_proj",
+        "model.layers.18.self_attn.q_proj",
+        "model.layers.18.self_attn.k_proj",
+        "model.layers.18.self_attn.v_proj",
+        "model.layers.18.self_attn.o_proj",
+        "model.layers.18.mlp.gate_proj",
+        "model.layers.18.mlp.up_proj",
+        "model.layers.18.mlp.down_proj",
+        "model.layers.19.self_attn.q_proj",
+        "model.layers.19.self_attn.k_proj",
+        "model.layers.19.self_attn.v_proj",
+        "model.layers.19.self_attn.o_proj",
+        "model.layers.19.mlp.gate_proj",
+        "model.layers.19.mlp.up_proj",
+        "model.layers.19.mlp.down_proj",
+        "model.layers.20.self_attn.q_proj",
+        "model.layers.20.self_attn.k_proj",
+        "model.layers.20.self_attn.v_proj",
+        "model.layers.20.self_attn.o_proj",
+        "model.layers.20.mlp.gate_proj",
+        "model.layers.20.mlp.up_proj",
+        "model.layers.20.mlp.down_proj",
+        "model.layers.21.self_attn.q_proj",
+        "model.layers.21.self_attn.k_proj",
+        "model.layers.21.self_attn.v_proj",
+        "model.layers.21.self_attn.o_proj",
+        "model.layers.21.mlp.gate_proj",
+        "model.layers.21.mlp.up_proj",
+        "model.layers.21.mlp.down_proj",
+        "model.layers.22.self_attn.q_proj",
+        "model.layers.22.self_attn.k_proj",
+        "model.layers.22.self_attn.v_proj",
+        "model.layers.22.self_attn.o_proj",
+        "model.layers.22.mlp.gate_proj",
+        "model.layers.22.mlp.up_proj",
+        "model.layers.22.mlp.down_proj",
+        "model.layers.23.self_attn.q_proj",
+        "model.layers.23.self_attn.k_proj",
+        "model.layers.23.self_attn.v_proj",
+        "model.layers.23.self_attn.o_proj",
+        "model.layers.23.mlp.gate_proj",
+        "model.layers.23.mlp.up_proj",
+        "model.layers.23.mlp.down_proj",
+        "model.layers.24.self_attn.q_proj",
+        "model.layers.24.self_attn.k_proj",
+        "model.layers.24.self_attn.v_proj",
+        "model.layers.24.self_attn.o_proj",
+        "model.layers.24.mlp.gate_proj",
+        "model.layers.24.mlp.up_proj",
+        "model.layers.24.mlp.down_proj",
+        "model.layers.25.self_attn.q_proj",
+        "model.layers.25.self_attn.k_proj",
+        "model.layers.25.self_attn.v_proj",
+        "model.layers.25.self_attn.o_proj",
+        "model.layers.25.mlp.gate_proj",
+        "model.layers.25.mlp.up_proj",
+        "model.layers.25.mlp.down_proj",
+        "model.layers.26.self_attn.q_proj",
+        "model.layers.26.self_attn.k_proj",
+        "model.layers.26.self_attn.v_proj",
+        "model.layers.26.self_attn.o_proj",
+        "model.layers.26.mlp.gate_proj",
+        "model.layers.26.mlp.up_proj",
+        "model.layers.26.mlp.down_proj",
+        "model.layers.27.self_attn.q_proj",
+        "model.layers.27.self_attn.k_proj",
+        "model.layers.27.self_attn.v_proj",
+        "model.layers.27.self_attn.o_proj",
+        "model.layers.27.mlp.gate_proj",
+        "model.layers.27.mlp.up_proj",
+        "model.layers.27.mlp.down_proj",
+        "model.layers.28.self_attn.q_proj",
+        "model.layers.28.self_attn.k_proj",
+        "model.layers.28.self_attn.v_proj",
+        "model.layers.28.self_attn.o_proj",
+        "model.layers.28.mlp.gate_proj",
+        "model.layers.28.mlp.up_proj",
+        "model.layers.28.mlp.down_proj",
+        "model.layers.29.self_attn.q_proj",
+        "model.layers.29.self_attn.k_proj",
+        "model.layers.29.self_attn.v_proj",
+        "model.layers.29.self_attn.o_proj",
+        "model.layers.29.mlp.gate_proj",
+        "model.layers.29.mlp.up_proj",
+        "model.layers.29.mlp.down_proj",
+        "model.layers.30.self_attn.q_proj",
+        "model.layers.30.self_attn.k_proj",
+        "model.layers.30.self_attn.v_proj",
+        "model.layers.30.self_attn.o_proj",
+        "model.layers.30.mlp.gate_proj",
+        "model.layers.30.mlp.up_proj",
+        "model.layers.30.mlp.down_proj",
+        "model.layers.31.self_attn.q_proj",
+        "model.layers.31.self_attn.k_proj",
+        "model.layers.31.self_attn.v_proj",
+        "model.layers.31.self_attn.o_proj",
+        "model.layers.31.mlp.gate_proj",
+        "model.layers.31.mlp.up_proj",
+        "model.layers.31.mlp.down_proj",
+        "lm_head"
+      ],
+      "registry_requires_subclass": false,
+      "sparsity_structure": "unstructured",
+      "targets": [
+        "model.layers.0.self_attn.q_proj",
+        "model.layers.0.self_attn.k_proj"
+      ]
+    }
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.46.2"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6f41a1443dab1fe71a134884140c10a8852bde1e2de0ab938db227c1775b689a
+size 4650006320

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d81984a8b7897b09dcd0111cdb2024d5a69e0d7482c4051c264c01d00b543a4b
+size 1050673280

model.safetensors.index.json

@@ -0,0 +1,746 @@
+{
+  "metadata": {
+    "total_size": 5700595200
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight_packed": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight_scale": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight_shape": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00001-of-00002.safetensors"
+  }
+}

recipe.yaml

@@ -0,0 +1,7 @@
+DEFAULT_stage:
+  DEFAULT_modifiers:
+    GPTQModifier:
+      sequential_update: true
+      scheme: W4A16
+      targets: Linear
+      ignore: [lm_head]

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}