kev-4b-mlx-4bit: AbstractCore decision checkpoint

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* 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

README.md

@@ -0,0 +1,56 @@
+---
+license: apache-2.0
+base_model: jaredpalmer/kev-4b
+tags:
+- decision-model
+- mlx
+- abstractcore
+- kev
+library_name: mlx
+pipeline_tag: text-classification
+---
+
+# Kev-4B for MLX, 4-bit, group 32, with the Gated DeltaNet projections (in_proj_qkv / in_proj_z / in_proj_a / in_proj_b / out_proj) kept at 8-bit
+
+A decision model: it reads a document (the *state*) and answers typed questions about it — `choice`
+over named options, `noul` (the probability a statement is true), `score` over ordered levels — with
+calibrated probabilities, in one forward pass, without generating text.
+
+This is [jaredpalmer/kev-4b](https://huggingface.co/jaredpalmer/kev-4b) (Jared Palmer, Apache-2.0: a rank-16 LoRA plus a
+pointer head on a Qwen3.5 base) with the adapter folded into the base and the backbone quantized for
+[mlx-lm](https://github.com/ml-explore/mlx-lm) at 4-bit, group 32, with the Gated DeltaNet projections (in_proj_qkv / in_proj_z / in_proj_a / in_proj_b / out_proj) kept at 8-bit (3.0 GB). The pointer head
+(`head.safetensors`) stays in float32; `decision.json` records the recipe and the source checkpoint.
+
+## Measured
+
+public-pool-v6 development set (1,328 records): accuracy 0.847 (bf16 0.846), Brier 0.226, ECE 0.024; argmax agreement with bf16 0.973, mean |Δp| 0.023, 3.1 % of questions moved by more than 0.10; 113 ms per record on an M5 Max. A plain 4-bit conversion (every linear at 4 bits, group 64) loses a point of accuracy and moves 10.6 % of the answers; this recipe is the measured compromise. Use the 8-bit checkpoint when you threshold probabilities.
+
+## Use with AbstractCore
+
+```python
+from abstractcore import create_llm
+
+llm = create_llm("mlx", model="AbstractFramework/kev-4b-mlx-4bit")
+result = llm.generate(
+    "Shoes arrived two weeks late and in the wrong size. Also I see two charges on my card.",
+    output="decision",
+    questions={
+        "department": {"type": "choice", "instructions": "Which team should handle this?",
+                       "criteria": {"returns": "Exchanges, refunds, wrong or damaged items",
+                                    "shipping": "Delivery status, delays, lost packages",
+                                    "billing": "Charges, invoices, payment problems"}},
+        "escalate": {"type": "noul", "instructions": "Does this need urgent human attention?"},
+        "frustration": {"type": "score", "instructions": "How frustrated is the customer?",
+                        "criteria": ["Calm", "Frustrated", "Very angry"]},
+    },
+)
+result.decisions["department"].choice, result.decisions["escalate"].noul
+```
+
+Or over HTTP on an AbstractCore server: `POST /v1/decisions` with `{"model": "mlx/AbstractFramework/kev-4b-mlx-4bit", "state": ..., "questions": ...}`.
+Docs: https://github.com/lpalbou/AbstractCore/blob/main/docs/decision-models.md
+
+## Attribution
+
+Weights derived from jaredpalmer/kev-4b (Jared Palmer) on Qwen/Qwen3.5 base models (Alibaba), both Apache-2.0.
+Converted with `python -m abstractcore.decision.convert`.

config.json

@@ -0,0 +1,2090 @@
+{
+    "architectures": [
+        "Qwen3_5ForConditionalGeneration"
+    ],
+    "image_token_id": 248056,
+    "model_type": "qwen3_5",
+    "quantization": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.embed_tokens": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        }
+    },
+    "quantization_config": {
+        "group_size": 32,
+        "bits": 4,
+        "mode": "affine",
+        "language_model.model.embed_tokens": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.0.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.1.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.2.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.3.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.4.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.5.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.6.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.7.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.8.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.9.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.10.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.11.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.12.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.13.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.14.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.15.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.16.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.17.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.18.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.19.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.20.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.21.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.22.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.23.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.24.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.25.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.26.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.27.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.28.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.29.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_qkv": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_z": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_b": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.in_proj_a": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.linear_attn.out_proj": {
+            "bits": 8,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.30.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.q_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.k_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.v_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.self_attn.o_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.gate_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.down_proj": {
+            "bits": 4,
+            "group_size": 32
+        },
+        "language_model.model.layers.31.mlp.up_proj": {
+            "bits": 4,
+            "group_size": 32
+        }
+    },
+    "text_config": {
+        "attention_bias": false,
+        "attention_dropout": 0.0,
+        "attn_output_gate": true,
+        "dtype": "bfloat16",
+        "eos_token_id": 248044,
+        "full_attention_interval": 4,
+        "head_dim": 256,
+        "hidden_act": "silu",
+        "hidden_size": 2560,
+        "initializer_range": 0.02,
+        "intermediate_size": 9216,
+        "layer_types": [
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention",
+            "linear_attention",
+            "linear_attention",
+            "linear_attention",
+            "full_attention"
+        ],
+        "linear_conv_kernel_dim": 4,
+        "linear_key_head_dim": 128,
+        "linear_num_key_heads": 16,
+        "linear_num_value_heads": 32,
+        "linear_value_head_dim": 128,
+        "max_position_embeddings": 262144,
+        "mlp_only_layers": [],
+        "model_type": "qwen3_5_text",
+        "mtp_num_hidden_layers": 1,
+        "mtp_use_dedicated_embeddings": false,
+        "num_attention_heads": 16,
+        "num_hidden_layers": 32,
+        "num_key_value_heads": 4,
+        "rms_norm_eps": 1e-06,
+        "tie_word_embeddings": true,
+        "use_cache": true,
+        "vocab_size": 248320,
+        "mamba_ssm_dtype": "float32",
+        "rope_parameters": {
+            "mrope_interleaved": true,
+            "mrope_section": [
+                11,
+                11,
+                10
+            ],
+            "rope_theta": 10000000,
+            "partial_rotary_factor": 0.25,
+            "type": "default"
+        }
+    },
+    "tie_word_embeddings": true,
+    "transformers_version": "4.57.0.dev0",
+    "video_token_id": 248057,
+    "vision_end_token_id": 248054,
+    "vision_start_token_id": 248053
+}

decision.json

@@ -0,0 +1,51 @@
+{
+  "format": "abstractcore-decision/1",
+  "kind": "kev",
+  "head_dim": 256,
+  "hidden_size": 2560,
+  "temperature": 2.406050072164233,
+  "head_file": "head.safetensors",
+  "runtime": "mlx",
+  "base": "Qwen/Qwen3.5-4B-Base",
+  "base_revision": "1001bb4d826a52d1f399e183466143f4da7b741b",
+  "lora_rank": 16,
+  "backbone": "merged",
+  "delimiters": [
+    "<|fim_prefix|>",
+    "<|fim_middle|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|fim_suffix|>"
+  ],
+  "question_types": [
+    "choice",
+    "noul",
+    "score"
+  ],
+  "max_state_tokens": 65536,
+  "max_row_tokens": 73728,
+  "source": {
+    "adapter_dir": "/Users/albou/.cache/huggingface/hub/models--jaredpalmer--kev-4b/snapshots/6cfce5c2fa4b4bd64026336ab649c5ca78857d52",
+    "base_dir": "/Users/albou/.cache/huggingface/hub/models--Qwen--Qwen3.5-4B-Base/snapshots/1001bb4d826a52d1f399e183466143f4da7b741b",
+    "adapter_sha256": "90e817356246e7f18bfa7ca3d31794cd4fbeb3332a66a84cb51d9ceae925f2b2",
+    "head_sha256": "dd633435998ecc751ac538717a3742e32149500fabf7d7276287dbf0693f347c",
+    "repos": {
+      "jaredpalmer/kev-4b": "6cfce5c2fa4b4bd64026336ab649c5ca78857d52",
+      "Qwen/Qwen3.5-4B-Base": "1001bb4d826a52d1f399e183466143f4da7b741b"
+    }
+  },
+  "license": "apache-2.0",
+  "quantization_recipe": {
+    "bits": 4,
+    "group_size": 32,
+    "upgrade": {
+      "linear_attn.in_proj_qkv": 8,
+      "linear_attn.in_proj_z": 8,
+      "linear_attn.in_proj_a": 8,
+      "linear_attn.in_proj_b": 8,
+      "linear_attn.out_proj": 8
+    }
+  },
+  "merged_tensors": 248,
+  "tensor_count": 924
+}

head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9bcee16d959731faf041557831b3cafb026b6f3ddbff2acd8b1acbb10ee411f
+size 5245264

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac05ecbc6ebac0564bfc8d8cb0c913fda9348f25737a5f9746bdef47e31ca188
+size 3135326997

model.safetensors.index.json

@@ -0,0 +1,932 @@
+{
+    "metadata": {
+        "total_size": 3135206912,
+        "total_parameters": 4205749760
+    },
+    "weight_map": {
+        "language_model.model.embed_tokens.biases": "model.safetensors",
+        "language_model.model.embed_tokens.scales": "model.safetensors",
+        "language_model.model.embed_tokens.weight": "model.safetensors",
+        "language_model.model.layers.0.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.0.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.0.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.0.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.0.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.0.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.1.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.1.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.1.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.1.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.1.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.1.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.10.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.10.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.10.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.10.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.10.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.10.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.11.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.11.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.12.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.12.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.12.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.12.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.12.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.13.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.13.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.13.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.13.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.13.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.13.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.14.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.14.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.14.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.14.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.14.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.14.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.15.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.15.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.16.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.16.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.16.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.16.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.16.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.17.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.17.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.17.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.17.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.17.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.17.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.18.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.18.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.18.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.18.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.18.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.18.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.19.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.19.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.2.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.2.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.2.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.2.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.2.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.20.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.20.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.20.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.20.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.20.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.20.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.21.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.21.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.21.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.21.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.21.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.21.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.22.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.22.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.22.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.22.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.22.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.22.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.23.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.23.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.24.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.24.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.24.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.24.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.24.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.24.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.25.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.25.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.25.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.25.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.25.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.25.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.26.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.26.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.26.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.26.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.26.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.26.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.27.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.27.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.27.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.27.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.27.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.28.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.28.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.28.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.28.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.28.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.28.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.28.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.28.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.28.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.28.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.28.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.28.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.29.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.29.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.29.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.29.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.29.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.29.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.29.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.29.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.29.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.29.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.29.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.29.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.3.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.3.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.30.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.30.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.30.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.30.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.30.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.30.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.30.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.30.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.30.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.30.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.30.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.30.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.31.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.31.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.31.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.31.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.31.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.31.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.31.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.31.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.31.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.31.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.31.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.31.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.31.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.31.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.31.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.31.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.31.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.31.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.31.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.31.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.31.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.31.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.31.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.31.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.31.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.4.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.4.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.4.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.4.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.4.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.5.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.5.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.5.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.5.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.5.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.5.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.6.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.6.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.6.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.6.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.6.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.6.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.7.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_norm.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.self_attn.k_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.self_attn.o_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_norm.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.self_attn.q_proj.weight": "model.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.biases": "model.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.scales": "model.safetensors",
+        "language_model.model.layers.7.self_attn.v_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.8.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.8.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.8.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.8.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.8.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.9.input_layernorm.weight": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.A_log": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.conv1d.weight": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.dt_bias": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_a.biases": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_a.scales": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_a.weight": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_b.biases": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_b.scales": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_b.weight": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_qkv.biases": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_qkv.scales": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_qkv.weight": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_z.biases": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_z.scales": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.in_proj_z.weight": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.norm.weight": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.out_proj.biases": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.out_proj.scales": "model.safetensors",
+        "language_model.model.layers.9.linear_attn.out_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.biases": "model.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.scales": "model.safetensors",
+        "language_model.model.layers.9.mlp.down_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.biases": "model.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.scales": "model.safetensors",
+        "language_model.model.layers.9.mlp.gate_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.biases": "model.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.scales": "model.safetensors",
+        "language_model.model.layers.9.mlp.up_proj.weight": "model.safetensors",
+        "language_model.model.layers.9.post_attention_layernorm.weight": "model.safetensors",
+        "language_model.model.norm.weight": "model.safetensors"
+    }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe000e3ed39ed12b8d2481d527d44f93c65d37e87645d2dcc80d1bf9d50d2927
+size 12807196

tokenizer_config.json

@@ -0,0 +1,305 @@
+{
+    "add_prefix_space": false,
+    "added_tokens_decoder": {
+        "248044": {
+            "content": "<|endoftext|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248045": {
+            "content": "<|im_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248046": {
+            "content": "<|im_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248047": {
+            "content": "<|object_ref_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248048": {
+            "content": "<|object_ref_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248049": {
+            "content": "<|box_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248050": {
+            "content": "<|box_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248051": {
+            "content": "<|quad_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248052": {
+            "content": "<|quad_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248053": {
+            "content": "<|vision_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248054": {
+            "content": "<|vision_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248055": {
+            "content": "<|vision_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248056": {
+            "content": "<|image_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248057": {
+            "content": "<|video_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248058": {
+            "content": "<tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248059": {
+            "content": "</tool_call>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248060": {
+            "content": "<|fim_prefix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248061": {
+            "content": "<|fim_middle|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248062": {
+            "content": "<|fim_suffix|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248063": {
+            "content": "<|fim_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248064": {
+            "content": "<|repo_name|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248065": {
+            "content": "<|file_sep|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248066": {
+            "content": "<tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248067": {
+            "content": "</tool_response>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248068": {
+            "content": "<think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248069": {
+            "content": "</think>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": false
+        },
+        "248070": {
+            "content": "<|audio_start|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248071": {
+            "content": "<|audio_end|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248072": {
+            "content": "<tts_pad>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248073": {
+            "content": "<tts_text_bos>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248074": {
+            "content": "<tts_text_eod>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248075": {
+            "content": "<tts_text_bos_single>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        },
+        "248076": {
+            "content": "<|audio_pad|>",
+            "lstrip": false,
+            "normalized": false,
+            "rstrip": false,
+            "single_word": false,
+            "special": true
+        }
+    },
+    "additional_special_tokens": [
+        "<|im_start|>",
+        "<|im_end|>",
+        "<|object_ref_start|>",
+        "<|object_ref_end|>",
+        "<|box_start|>",
+        "<|box_end|>",
+        "<|quad_start|>",
+        "<|quad_end|>",
+        "<|vision_start|>",
+        "<|vision_end|>",
+        "<|vision_pad|>",
+        "<|image_pad|>",
+        "<|video_pad|>"
+    ],
+    "bos_token": null,
+    "chat_template": "{%- set image_count = namespace(value=0) %}\n{%- set video_count = namespace(value=0) %}\n{%- macro render_content(content, do_vision_count, is_system_content=false) %}\n    {%- if content is string %}\n        {{- content }}\n    {%- elif content is iterable and content is not mapping %}\n        {%- for item in content %}\n            {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain images.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set image_count.value = image_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Picture ' ~ image_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|image_pad|><|vision_end|>' }}\n            {%- elif 'video' in item or item.type == 'video' %}\n                {%- if is_system_content %}\n                    {{- raise_exception('System message cannot contain videos.') }}\n                {%- endif %}\n                {%- if do_vision_count %}\n                    {%- set video_count.value = video_count.value + 1 %}\n                {%- endif %}\n                {%- if add_vision_id %}\n                    {{- 'Video ' ~ video_count.value ~ ': ' }}\n                {%- endif %}\n                {{- '<|vision_start|><|video_pad|><|vision_end|>' }}\n            {%- elif 'text' in item %}\n                {{- item.text }}\n            {%- else %}\n                {{- raise_exception('Unexpected item type in content.') }}\n            {%- endif %}\n        {%- endfor %}\n    {%- elif content is none or content is undefined %}\n        {{- '' }}\n    {%- else %}\n        {{- raise_exception('Unexpected content type.') }}\n    {%- endif %}\n{%- endmacro %}\n{%- if not messages %}\n    {{- raise_exception('No messages provided.') }}\n{%- endif %}\n{%- if tools and tools is iterable and tools is not mapping %}\n    {{- '<|im_start|>system\\n' }}\n    {{- \"# Tools\\n\\nYou have access to the following functions:\\n\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\" }}\n    {{- '\\n\\nIf you choose to call a function ONLY reply in the following format with NO suffix:\\n\\n<tool_call>\\n<function=example_function_name>\\n<parameter=example_parameter_1>\\nvalue_1\\n</parameter>\\n<parameter=example_parameter_2>\\nThis is the value for the second parameter\\nthat can span\\nmultiple lines\\n</parameter>\\n</function>\\n</tool_call>\\n\\n<IMPORTANT>\\nReminder:\\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\\n- Required parameters MUST be specified\\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\\n</IMPORTANT>' }}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {%- if content %}\n            {{- '\\n\\n' + content }}\n        {%- endif %}\n    {%- endif %}\n    {{- '<|im_end|>\\n' }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {%- set content = render_content(messages[0].content, false, true)|trim %}\n        {{- '<|im_start|>system\\n' + content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" %}\n        {%- set content = render_content(message.content, false)|trim %}\n        {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}\n            {%- set ns.multi_step_tool = false %}\n            {%- set ns.last_query_index = index %}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if ns.multi_step_tool %}\n    {{- raise_exception('No user query found in messages.') }}\n{%- endif %}\n{%- for message in messages %}\n    {%- set content = render_content(message.content, true)|trim %}\n    {%- if message.role == \"system\" %}\n        {%- if not loop.first %}\n            {{- raise_exception('System message must be at the beginning.') }}\n        {%- endif %}\n    {%- elif message.role == \"user\" %}\n        {{- '<|im_start|>' + message.role + '\\n' + content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is string %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in content %}\n                {%- set reasoning_content = content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n                {%- set content = content.split('</think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- set reasoning_content = reasoning_content|trim %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content + '\\n</think>\\n\\n' + content }}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if tool_call.function is defined %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {%- if loop.first %}\n                    {%- if content|trim %}\n                        {{- '\\n\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- else %}\n                        {{- '<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                    {%- endif %}\n                {%- else %}\n                    {{- '\\n<tool_call>\\n<function=' + tool_call.name + '>\\n' }}\n                {%- endif %}\n                {%- if tool_call.arguments is defined %}\n                    {%- for args_name, args_value in tool_call.arguments|items %}\n                        {{- '<parameter=' + args_name + '>\\n' }}\n                        {%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}\n                        {{- args_value }}\n                        {{- '\\n</parameter>\\n' }}\n                    {%- endfor %}\n                {%- endif %}\n                {{- '</function>\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.previtem and loop.previtem.role != \"tool\" %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- content }}\n        {{- '\\n</tool_response>' }}\n        {%- if not loop.last and loop.nextitem.role != \"tool\" %}\n            {{- '<|im_end|>\\n' }}\n        {%- elif loop.last %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- else %}\n        {{- raise_exception('Unexpected message role.') }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- else %}\n        {{- '<think>\\n' }}\n    {%- endif %}\n{%- endif %}",
+    "clean_up_tokenization_spaces": false,
+    "eos_token": "<|endoftext|>",
+    "errors": "replace",
+    "model_max_length": 262144,
+    "pad_token": "<|endoftext|>",
+    "split_special_tokens": false,
+    "tokenizer_class": "Qwen2Tokenizer",
+    "unk_token": null,
+    "add_bos_token": false,
+    "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
+    "extra_special_tokens": {
+        "audio_bos_token": "<|audio_start|>",
+        "audio_eos_token": "<|audio_end|>",
+        "audio_token": "<|audio_pad|>",
+        "image_token": "<|image_pad|>",
+        "video_token": "<|video_pad|>",
+        "vision_bos_token": "<|vision_start|>",
+        "vision_eos_token": "<|vision_end|>"
+    }
+}