commit ed77c994c4ee5f4d1a5155e6ee8e5b9ae3625976
Author: ModelHub XC <noreply@modelhub.org.cn>
Date:   Mon Jul 6 08:32:17 2026 +0800

    初始化项目，由ModelHub XC社区提供模型
    
    Model: kevinbazira/aya-expanse-8b-awq-4bit
    Source: Original Platform

diff --git a/.gitattributes b/.gitattributes
new file mode 100644
index 0000000..52373fe
--- /dev/null
+++ b/.gitattributes
@@ -0,0 +1,36 @@
+*.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
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..9126e28
--- /dev/null
+++ b/README.md
@@ -0,0 +1,117 @@
+---
+language:
+  - en
+  - fr
+  - de
+  - es
+  - it
+  - pt
+  - ja
+  - ko
+  - zh
+  - ar
+  - el
+  - fa
+  - pl
+  - id
+  - cs
+  - he
+  - hi
+  - nl
+  - ro
+  - ru
+  - tr
+  - uk
+  - vi
+license: cc-by-nc-4.0
+library_name: transformers
+tags:
+- cohere
+- pytorch
+- awq
+model_name: aya-expanse-8b-awq-4bit
+base_model: CohereForAI/aya-expanse-8b
+inference: false
+model_creator: Cohere For AI
+pipeline_tag: text-generation
+quantized_by: kevinbazira
+---
+
+# aya-expanse-8b-awq-4bit
+
+This repository contains a quantized version of the `CohereForAI/aya-expanse-8b` model using the [AWQ](https://huggingface.co/docs/transformers/en/quantization/awq) method in 4-bit precision.
+
+## Model Summary
+
+- **Quantized Model**: [kevinbazira/aya-expanse-8b-awq-4bit](https://huggingface.co/kevinbazira/aya-expanse-8b-awq-4bit)
+- **Quantization Method**: [AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration](https://arxiv.org/pdf/2306.00978)
+- **AWQ Version**: [GEMM](https://github.com/casper-hansen/AutoAWQ/tree/f1abb8ef8e261db78eb6c603f691801797fbb293?tab=readme-ov-file#int4-gemm-vs-int4-gemv-vs-fp16)
+- **Precision**: 4-bit
+- **Original Model**: [CohereForAI/aya-expanse-8b](https://huggingface.co/CohereForAI/aya-expanse-8b)
+
+## How to Use the Quantized Model
+
+### 1. Install the necessary packages
+
+Before using the quantized model, please ensure your environment has:
+- [AutoAWQ_kernels](https://github.com/casper-hansen/AutoAWQ_kernels)
+- [AutoAWQ](https://github.com/casper-hansen/AutoAWQ)
+
+### 2. Run inference
+Load and use the quantized model as shown below in Python:
+
+```python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer, AwqConfig
+
+# Set up device
+device = torch.device('cuda:1') # Remember to use the correct device here
+
+# Load model and tokenizer
+model_name = "kevinbazira/aya-expanse-8b-awq-4bit"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+quantization_config = AwqConfig(version="exllama")
+model = AutoModelForCausalLM.from_pretrained(
+    model_name, 
+    device_map={"": device.index},
+    quantization_config=quantization_config
+)
+
+# Prepare input
+# https://huggingface.co/docs/transformers/en/pad_truncation
+input_text = "Add your prompt here."
+inputs = tokenizer(input_text, return_tensors="pt", truncation=True, padding="max_length", max_length=64)
+inputs = {key: value.to(device) for key, value in inputs.items()}
+
+# Perform text generation 
+# https://huggingface.co/docs/transformers/en/main_classes/text_generation
+outputs = model.generate(
+    **inputs,
+    num_return_sequences=1,
+    min_new_tokens=64,
+    max_new_tokens=64,
+    do_sample=False,
+    use_cache=True,
+    num_beams=1
+)
+
+# Decode and print the output
+print(tokenizer.decode(outputs[0], skip_special_tokens=True))
+```
+
+## Benchmark Results
+
+To evaluate the performance of the quantized model, we run benchmarks using the Hugging Face [Optimum Benchmark](https://github.com/huggingface/optimum-benchmark/tree/7cec62e016d76fe612308e4c2c074fc7f09289fd) tool on an AMD MI200 GPU with ROCm 6.1 and below are the results:
+
+### Unquantized Model Results:
+<img src="unquantized-model-results.png" alt="Unquantized Model Results" style="width: 100%; object-fit: cover; display: block;">
+
+### AWQ Quantized Model Results:
+<img src="awq-quantized-model-results.png" alt="AWQ Quantized Model Results" style="width: 100%; object-fit: cover; display: block;">
+
+These results show that the AWQ quantized model offers significant speed advantages during critical inference stages (decode and per-token), outweighing the higher latencies encountered during the load and prefill phases. For deployment scenarios where inference speed is paramount, you can preload the quantized model to eliminate initial latency concerns.
+
+## More Information
+
+- **Original Model**: For details about the original model's architecture, training dataset, and performance, please visit the CohereForAI [aya-expanse-8b model card](https://huggingface.co/CohereForAI/aya-expanse-8b).
+- **Support or inquiries**: If you run into any issues or have questions about the quantized model, feel free to reach me via email:`contact@kevinbazira.com`. I'll be happy to help!
diff --git a/awq-quantized-model-results.png b/awq-quantized-model-results.png
new file mode 100644
index 0000000..c194195
Binary files /dev/null and b/awq-quantized-model-results.png differ
diff --git a/config.json b/config.json
new file mode 100644
index 0000000..fc99251
--- /dev/null
+++ b/config.json
@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "/srv/hf-cache/hub/models--CohereForAI--aya-expanse-8b/snapshots/d10159f8405826732641ce11c6892459d447d48c",
+  "architectures": [
+    "CohereForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 5,
+  "eos_token_id": 255001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "layer_norm_eps": 1e-05,
+  "logit_scale": 0.125,
+  "max_position_embeddings": 8192,
+  "model_type": "cohere",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "quantization_config": {
+    "bits": 4,
+    "group_size": 128,
+    "modules_to_not_convert": null,
+    "quant_method": "awq",
+    "version": "gemm",
+    "zero_point": true
+  },
+  "rope_scaling": null,
+  "rope_theta": 10000,
+  "torch_dtype": "float16",
+  "transformers_version": "4.47.1",
+  "use_cache": false,
+  "use_qk_norm": false,
+  "vocab_size": 256000
+}
diff --git a/generation_config.json b/generation_config.json
new file mode 100644
index 0000000..5e7b748
--- /dev/null
+++ b/generation_config.json
@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 5,
+  "do_sample": true,
+  "eos_token_id": 255001,
+  "pad_token_id": 0,
+  "transformers_version": "4.47.1"
+}
diff --git a/model-00001-of-00002.safetensors b/model-00001-of-00002.safetensors
new file mode 100644
index 0000000..f2b1bd1
--- /dev/null
+++ b/model-00001-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:965fa31cc8962cd59f7ee2ee220f10b19e3946de4686626618b047af3676a2b2
+size 4982512224
diff --git a/model-00002-of-00002.safetensors b/model-00002-of-00002.safetensors
new file mode 100644
index 0000000..7e6097c
--- /dev/null
+++ b/model-00002-of-00002.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f91ac8161370f30cf6dc4e08ab1f4e3e344fc31a5d1e4e72aa5543a577798e
+size 740965688
diff --git a/model.safetensors.index.json b/model.safetensors.index.json
new file mode 100644
index 0000000..b5fb18c
--- /dev/null
+++ b/model.safetensors.index.json
@@ -0,0 +1,714 @@
+{
+  "metadata": {
+    "total_size": 5723398144,
+    "lm_head.weight": "model.embed_tokens.weight"
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}
\ No newline at end of file
diff --git a/special_tokens_map.json b/special_tokens_map.json
new file mode 100644
index 0000000..cf33f2e
--- /dev/null
+++ b/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<BOS_TOKEN>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|END_OF_TURN_TOKEN|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<PAD>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/tokenizer.json b/tokenizer.json
new file mode 100644
index 0000000..8f7ad2b
--- /dev/null
+++ b/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:345ccf04a5257f473e331715ecc69365c5ac8fc2490923fe7155560af809ec1a
+size 20124090
diff --git a/tokenizer_config.json b/tokenizer_config.json
new file mode 100644
index 0000000..024a611
--- /dev/null
+++ b/tokenizer_config.json
@@ -0,0 +1,323 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<PAD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<UNK>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<MASK_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<BOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<EOS_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOP_TOKEN>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255000": {
+      "content": "<|START_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255001": {
+      "content": "<|END_OF_TURN_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "255002": {
+      "content": "<|YES_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255003": {
+      "content": "<|NO_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255004": {
+      "content": "<|GOOD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255005": {
+      "content": "<|BAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255006": {
+      "content": "<|USER_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255007": {
+      "content": "<|CHATBOT_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255008": {
+      "content": "<|SYSTEM_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255009": {
+      "content": "<|USER_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255010": {
+      "content": "<|USER_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255011": {
+      "content": "<|USER_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255012": {
+      "content": "<|USER_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255013": {
+      "content": "<|USER_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255014": {
+      "content": "<|USER_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255015": {
+      "content": "<|USER_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255016": {
+      "content": "<|USER_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255017": {
+      "content": "<|USER_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255018": {
+      "content": "<|USER_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255019": {
+      "content": "<|EXTRA_0_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255020": {
+      "content": "<|EXTRA_1_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255021": {
+      "content": "<|EXTRA_2_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255022": {
+      "content": "<|EXTRA_3_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255023": {
+      "content": "<|EXTRA_4_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255024": {
+      "content": "<|EXTRA_5_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255025": {
+      "content": "<|EXTRA_6_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255026": {
+      "content": "<|EXTRA_7_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255027": {
+      "content": "<|EXTRA_8_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "255028": {
+      "content": "<|EXTRA_9_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<BOS_TOKEN>",
+  "chat_template": [
+    {
+      "name": "default",
+      "template": "{{ bos_token }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% elif false == true %}{% set loop_messages = messages %}{% set system_message = 'You are Aya, a brilliant, sophisticated, multilingual AI-assistant trained to assist human users by providing thorough responses. You are able to interact and respond to questions in 23 languages and you are powered by a multilingual model built by Cohere For AI.' %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% if system_message != false %}{{ '<|START_OF_TURN_TOKEN|><|SYSTEM_TOKEN|>' + system_message + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|START_OF_TURN_TOKEN|><|USER_TOKEN|>' + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% elif message['role'] == 'assistant' %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>'  + content.strip() + '<|END_OF_TURN_TOKEN|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>' }}{% endif %}"
+    }
+  ],
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|END_OF_TURN_TOKEN|>",
+  "extra_special_tokens": {},
+  "legacy": true,
+  "merges_file": null,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<PAD>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "CohereTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false,
+  "vocab_file": null
+}
diff --git a/unquantized-model-results.png b/unquantized-model-results.png
new file mode 100644
index 0000000..8fb5d3a
Binary files /dev/null and b/unquantized-model-results.png differ