初始化项目，由ModelHub XC社区提供模型

Model: groxaxo/octen-embedding-8b-w4a16
Source: Original Platform

.gitattributes

@@ -0,0 +1,53 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 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
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack 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
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* 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
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*.tfevents* filter=lfs diff=lfs merge=lfs -text
+*.db* filter=lfs diff=lfs merge=lfs -text
+*.ark* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
+**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
+ 
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.gguf* filter=lfs diff=lfs merge=lfs -text
+*.ggml filter=lfs diff=lfs merge=lfs -text
+*.llamafile* filter=lfs diff=lfs merge=lfs -text
+*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* 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
+
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,81 @@
+---
+license: apache-2.0
+base_model: Octen/Octen-Embedding-8B
+library_name: transformers
+tags:
+  - embeddings
+  - quantized
+  - w4a16
+  - auto-round
+  - auto-gptq
+---
+
+# Octen-Embedding-8B W4A16
+
+This repo contains a W4A16 quantized version of `Octen/Octen-Embedding-8B` in the validated `auto-round-auto-gptq` format.
+
+## Quantization
+
+| Item | Value |
+|---|---|
+| Base model | `Octen/Octen-Embedding-8B` |
+| Quantization | W4A16, 4-bit weights / 16-bit activations |
+| Tooling | AutoRound 0.12.2, transformers 5.6.2, torch 2.6.0+cu124 |
+| Calibration | 8 samples, seqlen 512, 200 iterations, float32 tuning |
+| Quantized size | 8.1 GB, 2 shards |
+| Base size | 15.0 GB |
+| Compression | ~1.9x |
+| Embedding dim | 4096 |
+| Layers quantized | 252/253; `lm_head` skipped |
+
+## Validation vs base model
+
+Evaluation used a small retrieval set of 5 query-document pairs, last-token pooling, L2 normalization, and cosine similarity.
+
+| Metric | Base | W4A16 | Delta |
+|---|---:|---:|---:|
+| Recall@1 | 0.8 | 1.0 | +0.2 |
+| Recall@5 | 1.0 | 1.0 | 0.0 |
+| Mean query cosine, base vs quant | — | 0.9840 | — |
+| Mean doc cosine, base vs quant | — | 0.9820 | — |
+
+Assessment: this model passed all validation gates cleanly, with >0.98 mean cosine to the base model and no retrieval degradation on the validation set.
+
+See `validation-8b-auto-round-auto-gptq.json` for the raw metrics.
+
+## RTX 3060 smoke test
+
+This quantized model was loaded and run on an RTX 3060 12GB GPU.
+
+| Result | Value |
+|---|---:|
+| VRAM after load | 4.53 GB |
+| Single short-query forward pass | 0.9s smoke test; later benchmark ~612ms |
+| Output shape | `[1, 4, 4096]` |
+| Embeddings | Valid normalized vectors; no NaNs observed |
+
+## Recommended usage
+
+```python
+import torch
+from transformers import AutoModel, AutoTokenizer
+
+model_id = "groxaxo/octen-embedding-8b-w4a16"
+tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)
+model = AutoModel.from_pretrained(
+    model_id,
+    trust_remote_code=True,
+    torch_dtype=torch.float16,
+).cuda().eval()
+
+texts = ["how to implement binary search"]
+tokens = tokenizer(texts, padding=True, truncation=True, max_length=512, return_tensors="pt")
+tokens = {k: v.cuda() for k, v in tokens.items()}
+
+with torch.no_grad():
+    out = model(**tokens)
+
+emb = torch.nn.functional.normalize(out.last_hidden_state[:, -1, :], p=2, dim=-1)
+```
+
+Note: the model card records local validation and smoke-test results. For production use, evaluate on your own retrieval distribution.

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\n\n# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,86 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": null,
+  "quantization_config": {
+    "amp": false,
+    "autoround_version": "0.12.2",
+    "batch_size": 1,
+    "bits": 4,
+    "data_type": "int",
+    "gradient_accumulate_steps": 8,
+    "group_size": 128,
+    "low_gpu_mem_usage": true,
+    "nsamples": 8,
+    "packing_format": "auto_round:auto_gptq",
+    "quant_method": "auto-round",
+    "seqlen": 512,
+    "sym": true
+  },
+  "rms_norm_eps": 1e-06,
+  "rope_parameters": {
+    "rope_theta": 1000000,
+    "rope_type": "default"
+  },
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.2",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151665
+}

configuration.json

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

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151645,
+  "transformers_version": "5.6.2",
+  "use_cache": true
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d795222e612fa2def70eb504e8993b27790a1f43e193661b444a8dcca860078
+size 4995924648

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e1b11d6268b6aca00df6e44ff7c153fc53f718c34be3d200ffa59c7dc8c93ded
+size 3583711440

model.safetensors.index.json

@@ -0,0 +1,911 @@
+{
+  "metadata": {
+    "total_parameters": 1242747904,
+    "total_size": 8579534848
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00001-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.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.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "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.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.scales": "model-00002-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.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "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.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.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "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.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.self_attn.q_norm.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.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.27.input_layernorm.weight": "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.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.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "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.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.self_attn.q_norm.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.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.28.input_layernorm.weight": "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.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.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "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.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.self_attn.q_norm.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.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.29.input_layernorm.weight": "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.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.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "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.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.self_attn.q_norm.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.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.3.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "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.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.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "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.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.self_attn.q_norm.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.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.31.input_layernorm.weight": "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.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.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "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.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.self_attn.q_norm.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.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.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

quantization_config.json

@@ -0,0 +1,15 @@
+{
+  "bits": 4,
+  "data_type": "int",
+  "group_size": 128,
+  "sym": true,
+  "amp": false,
+  "batch_size": 1,
+  "gradient_accumulate_steps": 8,
+  "low_gpu_mem_usage": true,
+  "nsamples": 8,
+  "seqlen": 512,
+  "autoround_version": "0.12.2",
+  "quant_method": "auto-round",
+  "packing_format": "auto_round:auto_gptq"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5313a7bef3012f7dab2e49f82ee0dead33fb9c864c024c673a731606409560f
+size 11423041

tokenizer_config.json

@@ -0,0 +1,15 @@
+{
+  "add_prefix_space": false,
+  "backend": "tokenizers",
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "is_local": false,
+  "local_files_only": false,
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

validation-8b-auto-round-auto-gptq.json

@@ -0,0 +1,15 @@
+{
+  "base_model": "Octen/Octen-Embedding-8B",
+  "quant_model": "quantized/octen-embedding-8b-w4a16/auto-round-auto-gptq",
+  "num_eval_rows": 5,
+  "base_embedding_dim": 4096,
+  "quant_embedding_dim": 4096,
+  "base_recall_at_1": 0.8,
+  "base_recall_at_5": 1.0,
+  "quant_recall_at_1": 1.0,
+  "quant_recall_at_5": 1.0,
+  "mean_query_cosine_base_vs_quant": 0.9839715957641602,
+  "mean_doc_cosine_base_vs_quant": 0.9820238351821899,
+  "recall_at_1_delta": 0.19999999999999996,
+  "recall_at_5_delta": 0.0
+}