Add files using upload-large-folder tool

README.md

@@ -2,12 +2,100 @@
 license: apache-2.0
 library_name: transformers
 pipeline_tag: text-generation
+base_model: tencent/Hy3
+base_model_relation: quantized
 tags:
 - hunyuan
 - hy3
 - moe
 - text-generation
+- mxfp4
+- compressed-tensors
+- quantized
+- vllm
 ---
+
+# Hy3 — MXFP4 (mixed precision)
+
+> **A 4-bit MXFP4 quantization of [`tencent/Hy3`](https://huggingface.co/tencent/Hy3).**
+> The original model card is preserved in full [below](#model-introduction).
+
+Weight-only MXFP4 quant produced with [**qstream**](https://github.com/olka/qstream):
+the routed MoE experts (≈95% of the weights) are quantized to 4-bit; everything
+quality-sensitive stays BF16.
+
+| | |
+|---|---|
+| **Size** | **160 GB** (down from ~590 GB BF16 source, ~27%) |
+| **Format** | compressed-tensors `mxfp4-pack-quantized` (E2M1 4-bit + E8M0 group-32 scales) |
+| **Base** | [tencent/Hy3](https://huggingface.co/tencent/Hy3) — 295B MoE (21B active, 3.8B MTP), 80 layers + 1 MTP layer, 192 experts top-8 + 1 shared, 256K context |
+
+### What is quantized to what
+
+| Component | Precision | Why |
+|---|---|---|
+| Routed experts (`…mlp.experts.{0..191}.{gate,up,down}_proj`), incl. the MTP layer | **MXFP4** (4-bit) | the bulk of the weights — the only place worth the size win |
+| Shared expert (`…mlp.shared_mlp.*`) | **BF16** | always-on path — quantizing it amplifies error across every token for little gain |
+| Attention, MoE router, dense-layer MLPs | **BF16** | sensitive / small — kept native |
+| Embeddings, `lm_head`, all norms | **BF16 / F32** | unchanged |
+
+### Quality & faithfulness
+
+Functional evals run **end-to-end on a single NVIDIA B300 (275 GB)** — the checkpoint
+serves and generates coherently, so this is validated behavior, not just numeric proximity.
+
+| Metric | Result | What it shows |
+|---|---|---|
+| **WikiText-2 perplexity** (raw test, 290,674 tokens, 2048-ctx) | **5.12** | language modeling intact — a broken quant lands in the hundreds |
+| **GSM8K** (full 1319-task, CoT, greedy) | **1270 / 1319 (96.3%)** | math/reasoning preserved |
+| **MTP acceptance** (`num_speculative_tokens=1`, 7.5k draft tokens on GSM8K) | **82.8%** | the MTP draft layer speculates well — a free decode speedup, and lossless (GSM8K unchanged with it on) |
+| **Routed-expert SQNR** (sampled, MXFP4 vs BF16) | **≈ 19.0 dB** (‖W−dequant‖/‖W‖ ≈ 11.25%) | reconstruction error is just the unavoidable 4-bit E2M1 rounding |
+
+Only the routed-expert FFN weights changed — ~95% of the weights are re-quantized to
+MXFP4; everything else (attention, shared expert, router, norms, embeddings) is
+bit-identical BF16 to the source.
+
+### Fidelity, footprint & provenance
+
+- **MTP preserved:** the multi-token-prediction draft layer (layer 80) is served with
+  `--speculative-config '{"method":"mtp","num_speculative_tokens":1}'` and reaches **82.8%**
+  draft-token acceptance. It is lossless — GSM8K is unchanged with it on (as speculative
+  decoding must be).
+- **Footprint:** ~160 GB of weights — fits a single large-VRAM GPU (verified on one
+  **B300, 275 GB**) or multi-GPU tensor parallelism (e.g. 4× 80 GB). `fastsafetensors`
+  loads it in ~160 s.
+- **Sibling NVFP4** quant of the same experts reconstructs at ≈21.3 dB (8.65% rel err) for
+  ~6% more bits (FP8 group scale vs E8M0).
+- **Provenance:** built with [qstream](https://github.com/olka/qstream) `@9f8cd0c`,
+  experts-only (`--include_layers "*experts.*proj.weight"`), MSE-optimal E8M0 scale
+  selection + data-free activation-aware γ (`input_layernorm.weight` proxy).
+
+### Serving with vLLM
+
+`HYV3ForCausalLM` is natively supported; loads via vLLM's compressed-tensors MXFP4 path.
+For the full production config (8-GPU TP, tool/reasoning parsers), see the original
+[Deployment](#deployment) section below and point it at this repo.
+
+```bash
+vllm serve olka-fi/Hy3-MXFP4 \
+  --served-model-name hy3 --tensor-parallel-size 1 \
+  --max-model-len 4096 --gpu-memory-utilization 0.90 \
+  --load-format fastsafetensors \
+  --speculative-config '{"method":"mtp","num_speculative_tokens":1}'
+```
+
+Drop `--speculative-config` for the fixed (no-MTP) path; raise `--tensor-parallel-size`
+for GPUs smaller than the ~160 GB weight footprint.
+
+> **Note on `config.json`.** The `ignore` list carries both the canonical
+> `…mlp.shared_mlp.*` module paths **and** their bare `…mlp.*` forms, so the shared
+> expert stays BF16 on vLLM's `HYV3` load path (which addresses that module by a bare
+> prefix). If you regenerate the config, keep both forms.
+
+---
+
+> ⬇️ **The original `tencent/Hy3` model card follows, unmodified.** ⬇️
+
 <p align="left">
     <a href="https://huggingface.co/tencent/Hy3/blob/main/README_CN.md">中文</a>&nbsp;｜&nbsp;English
 </p>

config.json

@@ -1038,7 +1038,247 @@
       "model.layers.9.self_attn.q_norm",
       "model.layers.9.self_attn.q_proj",
       "model.layers.9.self_attn.v_proj",
-      "model.norm"
+      "model.norm",
+      "model.layers.1.mlp.down_proj",
+      "model.layers.1.mlp.gate_proj",
+      "model.layers.1.mlp.up_proj",
+      "model.layers.10.mlp.down_proj",
+      "model.layers.10.mlp.gate_proj",
+      "model.layers.10.mlp.up_proj",
+      "model.layers.11.mlp.down_proj",
+      "model.layers.11.mlp.gate_proj",
+      "model.layers.11.mlp.up_proj",
+      "model.layers.12.mlp.down_proj",
+      "model.layers.12.mlp.gate_proj",
+      "model.layers.12.mlp.up_proj",
+      "model.layers.13.mlp.down_proj",
+      "model.layers.13.mlp.gate_proj",
+      "model.layers.13.mlp.up_proj",
+      "model.layers.14.mlp.down_proj",
+      "model.layers.14.mlp.gate_proj",
+      "model.layers.14.mlp.up_proj",
+      "model.layers.15.mlp.down_proj",
+      "model.layers.15.mlp.gate_proj",
+      "model.layers.15.mlp.up_proj",
+      "model.layers.16.mlp.down_proj",
+      "model.layers.16.mlp.gate_proj",
+      "model.layers.16.mlp.up_proj",
+      "model.layers.17.mlp.down_proj",
+      "model.layers.17.mlp.gate_proj",
+      "model.layers.17.mlp.up_proj",
+      "model.layers.18.mlp.down_proj",
+      "model.layers.18.mlp.gate_proj",
+      "model.layers.18.mlp.up_proj",
+      "model.layers.19.mlp.down_proj",
+      "model.layers.19.mlp.gate_proj",
+      "model.layers.19.mlp.up_proj",
+      "model.layers.2.mlp.down_proj",
+      "model.layers.2.mlp.gate_proj",
+      "model.layers.2.mlp.up_proj",
+      "model.layers.20.mlp.down_proj",
+      "model.layers.20.mlp.gate_proj",
+      "model.layers.20.mlp.up_proj",
+      "model.layers.21.mlp.down_proj",
+      "model.layers.21.mlp.gate_proj",
+      "model.layers.21.mlp.up_proj",
+      "model.layers.22.mlp.down_proj",
+      "model.layers.22.mlp.gate_proj",
+      "model.layers.22.mlp.up_proj",
+      "model.layers.23.mlp.down_proj",
+      "model.layers.23.mlp.gate_proj",
+      "model.layers.23.mlp.up_proj",
+      "model.layers.24.mlp.down_proj",
+      "model.layers.24.mlp.gate_proj",
+      "model.layers.24.mlp.up_proj",
+      "model.layers.25.mlp.down_proj",
+      "model.layers.25.mlp.gate_proj",
+      "model.layers.25.mlp.up_proj",
+      "model.layers.26.mlp.down_proj",
+      "model.layers.26.mlp.gate_proj",
+      "model.layers.26.mlp.up_proj",
+      "model.layers.27.mlp.down_proj",
+      "model.layers.27.mlp.gate_proj",
+      "model.layers.27.mlp.up_proj",
+      "model.layers.28.mlp.down_proj",
+      "model.layers.28.mlp.gate_proj",
+      "model.layers.28.mlp.up_proj",
+      "model.layers.29.mlp.down_proj",
+      "model.layers.29.mlp.gate_proj",
+      "model.layers.29.mlp.up_proj",
+      "model.layers.3.mlp.down_proj",
+      "model.layers.3.mlp.gate_proj",
+      "model.layers.3.mlp.up_proj",
+      "model.layers.30.mlp.down_proj",
+      "model.layers.30.mlp.gate_proj",
+      "model.layers.30.mlp.up_proj",
+      "model.layers.31.mlp.down_proj",
+      "model.layers.31.mlp.gate_proj",
+      "model.layers.31.mlp.up_proj",
+      "model.layers.32.mlp.down_proj",
+      "model.layers.32.mlp.gate_proj",
+      "model.layers.32.mlp.up_proj",
+      "model.layers.33.mlp.down_proj",
+      "model.layers.33.mlp.gate_proj",
+      "model.layers.33.mlp.up_proj",
+      "model.layers.34.mlp.down_proj",
+      "model.layers.34.mlp.gate_proj",
+      "model.layers.34.mlp.up_proj",
+      "model.layers.35.mlp.down_proj",
+      "model.layers.35.mlp.gate_proj",
+      "model.layers.35.mlp.up_proj",
+      "model.layers.36.mlp.down_proj",
+      "model.layers.36.mlp.gate_proj",
+      "model.layers.36.mlp.up_proj",
+      "model.layers.37.mlp.down_proj",
+      "model.layers.37.mlp.gate_proj",
+      "model.layers.37.mlp.up_proj",
+      "model.layers.38.mlp.down_proj",
+      "model.layers.38.mlp.gate_proj",
+      "model.layers.38.mlp.up_proj",
+      "model.layers.39.mlp.down_proj",
+      "model.layers.39.mlp.gate_proj",
+      "model.layers.39.mlp.up_proj",
+      "model.layers.4.mlp.down_proj",
+      "model.layers.4.mlp.gate_proj",
+      "model.layers.4.mlp.up_proj",
+      "model.layers.40.mlp.down_proj",
+      "model.layers.40.mlp.gate_proj",
+      "model.layers.40.mlp.up_proj",
+      "model.layers.41.mlp.down_proj",
+      "model.layers.41.mlp.gate_proj",
+      "model.layers.41.mlp.up_proj",
+      "model.layers.42.mlp.down_proj",
+      "model.layers.42.mlp.gate_proj",
+      "model.layers.42.mlp.up_proj",
+      "model.layers.43.mlp.down_proj",
+      "model.layers.43.mlp.gate_proj",
+      "model.layers.43.mlp.up_proj",
+      "model.layers.44.mlp.down_proj",
+      "model.layers.44.mlp.gate_proj",
+      "model.layers.44.mlp.up_proj",
+      "model.layers.45.mlp.down_proj",
+      "model.layers.45.mlp.gate_proj",
+      "model.layers.45.mlp.up_proj",
+      "model.layers.46.mlp.down_proj",
+      "model.layers.46.mlp.gate_proj",
+      "model.layers.46.mlp.up_proj",
+      "model.layers.47.mlp.down_proj",
+      "model.layers.47.mlp.gate_proj",
+      "model.layers.47.mlp.up_proj",
+      "model.layers.48.mlp.down_proj",
+      "model.layers.48.mlp.gate_proj",
+      "model.layers.48.mlp.up_proj",
+      "model.layers.49.mlp.down_proj",
+      "model.layers.49.mlp.gate_proj",
+      "model.layers.49.mlp.up_proj",
+      "model.layers.5.mlp.down_proj",
+      "model.layers.5.mlp.gate_proj",
+      "model.layers.5.mlp.up_proj",
+      "model.layers.50.mlp.down_proj",
+      "model.layers.50.mlp.gate_proj",
+      "model.layers.50.mlp.up_proj",
+      "model.layers.51.mlp.down_proj",
+      "model.layers.51.mlp.gate_proj",
+      "model.layers.51.mlp.up_proj",
+      "model.layers.52.mlp.down_proj",
+      "model.layers.52.mlp.gate_proj",
+      "model.layers.52.mlp.up_proj",
+      "model.layers.53.mlp.down_proj",
+      "model.layers.53.mlp.gate_proj",
+      "model.layers.53.mlp.up_proj",
+      "model.layers.54.mlp.down_proj",
+      "model.layers.54.mlp.gate_proj",
+      "model.layers.54.mlp.up_proj",
+      "model.layers.55.mlp.down_proj",
+      "model.layers.55.mlp.gate_proj",
+      "model.layers.55.mlp.up_proj",
+      "model.layers.56.mlp.down_proj",
+      "model.layers.56.mlp.gate_proj",
+      "model.layers.56.mlp.up_proj",
+      "model.layers.57.mlp.down_proj",
+      "model.layers.57.mlp.gate_proj",
+      "model.layers.57.mlp.up_proj",
+      "model.layers.58.mlp.down_proj",
+      "model.layers.58.mlp.gate_proj",
+      "model.layers.58.mlp.up_proj",
+      "model.layers.59.mlp.down_proj",
+      "model.layers.59.mlp.gate_proj",
+      "model.layers.59.mlp.up_proj",
+      "model.layers.6.mlp.down_proj",
+      "model.layers.6.mlp.gate_proj",
+      "model.layers.6.mlp.up_proj",
+      "model.layers.60.mlp.down_proj",
+      "model.layers.60.mlp.gate_proj",
+      "model.layers.60.mlp.up_proj",
+      "model.layers.61.mlp.down_proj",
+      "model.layers.61.mlp.gate_proj",
+      "model.layers.61.mlp.up_proj",
+      "model.layers.62.mlp.down_proj",
+      "model.layers.62.mlp.gate_proj",
+      "model.layers.62.mlp.up_proj",
+      "model.layers.63.mlp.down_proj",
+      "model.layers.63.mlp.gate_proj",
+      "model.layers.63.mlp.up_proj",
+      "model.layers.64.mlp.down_proj",
+      "model.layers.64.mlp.gate_proj",
+      "model.layers.64.mlp.up_proj",
+      "model.layers.65.mlp.down_proj",
+      "model.layers.65.mlp.gate_proj",
+      "model.layers.65.mlp.up_proj",
+      "model.layers.66.mlp.down_proj",
+      "model.layers.66.mlp.gate_proj",
+      "model.layers.66.mlp.up_proj",
+      "model.layers.67.mlp.down_proj",
+      "model.layers.67.mlp.gate_proj",
+      "model.layers.67.mlp.up_proj",
+      "model.layers.68.mlp.down_proj",
+      "model.layers.68.mlp.gate_proj",
+      "model.layers.68.mlp.up_proj",
+      "model.layers.69.mlp.down_proj",
+      "model.layers.69.mlp.gate_proj",
+      "model.layers.69.mlp.up_proj",
+      "model.layers.7.mlp.down_proj",
+      "model.layers.7.mlp.gate_proj",
+      "model.layers.7.mlp.up_proj",
+      "model.layers.70.mlp.down_proj",
+      "model.layers.70.mlp.gate_proj",
+      "model.layers.70.mlp.up_proj",
+      "model.layers.71.mlp.down_proj",
+      "model.layers.71.mlp.gate_proj",
+      "model.layers.71.mlp.up_proj",
+      "model.layers.72.mlp.down_proj",
+      "model.layers.72.mlp.gate_proj",
+      "model.layers.72.mlp.up_proj",
+      "model.layers.73.mlp.down_proj",
+      "model.layers.73.mlp.gate_proj",
+      "model.layers.73.mlp.up_proj",
+      "model.layers.74.mlp.down_proj",
+      "model.layers.74.mlp.gate_proj",
+      "model.layers.74.mlp.up_proj",
+      "model.layers.75.mlp.down_proj",
+      "model.layers.75.mlp.gate_proj",
+      "model.layers.75.mlp.up_proj",
+      "model.layers.76.mlp.down_proj",
+      "model.layers.76.mlp.gate_proj",
+      "model.layers.76.mlp.up_proj",
+      "model.layers.77.mlp.down_proj",
+      "model.layers.77.mlp.gate_proj",
+      "model.layers.77.mlp.up_proj",
+      "model.layers.78.mlp.down_proj",
+      "model.layers.78.mlp.gate_proj",
+      "model.layers.78.mlp.up_proj",
+      "model.layers.79.mlp.down_proj",
+      "model.layers.79.mlp.gate_proj",
+      "model.layers.79.mlp.up_proj",
+      "model.layers.8.mlp.down_proj",
+      "model.layers.8.mlp.gate_proj",
+      "model.layers.8.mlp.up_proj",
+      "model.layers.80.mlp.down_proj",
+      "model.layers.80.mlp.gate_proj",
+      "model.layers.80.mlp.up_proj",
+      "model.layers.9.mlp.down_proj",
+      "model.layers.9.mlp.gate_proj",
+      "model.layers.9.mlp.up_proj"
     ]
   }
 }

config.json.bak

@@ -0,0 +1,1044 @@
+{
+  "architectures": [
+    "HYV3ForCausalLM"
+  ],
+  "bos_token_id": 120000,
+  "enable_attention_fp32_softmax": false,
+  "enable_lm_head_fp32": true,
+  "enable_moe_fp32_combine": false,
+  "eod_token_id": 120026,
+  "eos_token_id": 120025,
+  "expert_hidden_dim": 1536,
+  "moe_intermediate_size": 1536,
+  "first_k_dense_replace": 1,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.006,
+  "intermediate_size": 13312,
+  "max_position_embeddings": 262144,
+  "model_type": "hy_v3",
+  "moe_router_enable_expert_bias": true,
+  "moe_router_use_sigmoid": true,
+  "num_attention_heads": 64,
+  "num_experts": 192,
+  "num_experts_per_tok": 8,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "num_shared_experts": 1,
+  "output_router_logits": true,
+  "pad_token_id": 120002,
+  "qk_norm": true,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 11158840.0,
+    "rope_type": "default"
+  },
+  "route_norm": true,
+  "router_scaling_factor": 2.826,
+  "sep_token_id": 120007,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.6.0",
+  "use_cache": true,
+  "use_grouped_mm": false,
+  "vocab_size": 120832,
+  "num_nextn_predict_layers": 1,
+  "quantization_config": {
+    "quant_method": "compressed-tensors",
+    "format": "mxfp4-pack-quantized",
+    "config_groups": {
+      "group_0": {
+        "targets": [
+          "Linear"
+        ],
+        "weights": {
+          "num_bits": 4,
+          "type": "float",
+          "strategy": "group",
+          "group_size": 32,
+          "symmetric": true
+        }
+      }
+    },
+    "ignore": [
+      "lm_head",
+      "model.embed_tokens",
+      "model.layers.0.input_layernorm",
+      "model.layers.0.mlp.down_proj",
+      "model.layers.0.mlp.gate_proj",
+      "model.layers.0.mlp.up_proj",
+      "model.layers.0.post_attention_layernorm",
+      "model.layers.0.self_attn.k_norm",
+      "model.layers.0.self_attn.k_proj",
+      "model.layers.0.self_attn.o_proj",
+      "model.layers.0.self_attn.q_norm",
+      "model.layers.0.self_attn.q_proj",
+      "model.layers.0.self_attn.v_proj",
+      "model.layers.1.input_layernorm",
+      "model.layers.1.mlp.router.gate",
+      "model.layers.1.mlp.shared_mlp.down_proj",
+      "model.layers.1.mlp.shared_mlp.gate_proj",
+      "model.layers.1.mlp.shared_mlp.up_proj",
+      "model.layers.1.post_attention_layernorm",
+      "model.layers.1.self_attn.k_norm",
+      "model.layers.1.self_attn.k_proj",
+      "model.layers.1.self_attn.o_proj",
+      "model.layers.1.self_attn.q_norm",
+      "model.layers.1.self_attn.q_proj",
+      "model.layers.1.self_attn.v_proj",
+      "model.layers.10.input_layernorm",
+      "model.layers.10.mlp.router.gate",
+      "model.layers.10.mlp.shared_mlp.down_proj",
+      "model.layers.10.mlp.shared_mlp.gate_proj",
+      "model.layers.10.mlp.shared_mlp.up_proj",
+      "model.layers.10.post_attention_layernorm",
+      "model.layers.10.self_attn.k_norm",
+      "model.layers.10.self_attn.k_proj",
+      "model.layers.10.self_attn.o_proj",
+      "model.layers.10.self_attn.q_norm",
+      "model.layers.10.self_attn.q_proj",
+      "model.layers.10.self_attn.v_proj",
+      "model.layers.11.input_layernorm",
+      "model.layers.11.mlp.router.gate",
+      "model.layers.11.mlp.shared_mlp.down_proj",
+      "model.layers.11.mlp.shared_mlp.gate_proj",
+      "model.layers.11.mlp.shared_mlp.up_proj",
+      "model.layers.11.post_attention_layernorm",
+      "model.layers.11.self_attn.k_norm",
+      "model.layers.11.self_attn.k_proj",
+      "model.layers.11.self_attn.o_proj",
+      "model.layers.11.self_attn.q_norm",
+      "model.layers.11.self_attn.q_proj",
+      "model.layers.11.self_attn.v_proj",
+      "model.layers.12.input_layernorm",
+      "model.layers.12.mlp.router.gate",
+      "model.layers.12.mlp.shared_mlp.down_proj",
+      "model.layers.12.mlp.shared_mlp.gate_proj",
+      "model.layers.12.mlp.shared_mlp.up_proj",
+      "model.layers.12.post_attention_layernorm",
+      "model.layers.12.self_attn.k_norm",
+      "model.layers.12.self_attn.k_proj",
+      "model.layers.12.self_attn.o_proj",
+      "model.layers.12.self_attn.q_norm",
+      "model.layers.12.self_attn.q_proj",
+      "model.layers.12.self_attn.v_proj",
+      "model.layers.13.input_layernorm",
+      "model.layers.13.mlp.router.gate",
+      "model.layers.13.mlp.shared_mlp.down_proj",
+      "model.layers.13.mlp.shared_mlp.gate_proj",
+      "model.layers.13.mlp.shared_mlp.up_proj",
+      "model.layers.13.post_attention_layernorm",
+      "model.layers.13.self_attn.k_norm",
+      "model.layers.13.self_attn.k_proj",
+      "model.layers.13.self_attn.o_proj",
+      "model.layers.13.self_attn.q_norm",
+      "model.layers.13.self_attn.q_proj",
+      "model.layers.13.self_attn.v_proj",
+      "model.layers.14.input_layernorm",
+      "model.layers.14.mlp.router.gate",
+      "model.layers.14.mlp.shared_mlp.down_proj",
+      "model.layers.14.mlp.shared_mlp.gate_proj",
+      "model.layers.14.mlp.shared_mlp.up_proj",
+      "model.layers.14.post_attention_layernorm",
+      "model.layers.14.self_attn.k_norm",
+      "model.layers.14.self_attn.k_proj",
+      "model.layers.14.self_attn.o_proj",
+      "model.layers.14.self_attn.q_norm",
+      "model.layers.14.self_attn.q_proj",
+      "model.layers.14.self_attn.v_proj",
+      "model.layers.15.input_layernorm",
+      "model.layers.15.mlp.router.gate",
+      "model.layers.15.mlp.shared_mlp.down_proj",
+      "model.layers.15.mlp.shared_mlp.gate_proj",
+      "model.layers.15.mlp.shared_mlp.up_proj",
+      "model.layers.15.post_attention_layernorm",
+      "model.layers.15.self_attn.k_norm",
+      "model.layers.15.self_attn.k_proj",
+      "model.layers.15.self_attn.o_proj",
+      "model.layers.15.self_attn.q_norm",
+      "model.layers.15.self_attn.q_proj",
+      "model.layers.15.self_attn.v_proj",
+      "model.layers.16.input_layernorm",
+      "model.layers.16.mlp.router.gate",
+      "model.layers.16.mlp.shared_mlp.down_proj",
+      "model.layers.16.mlp.shared_mlp.gate_proj",
+      "model.layers.16.mlp.shared_mlp.up_proj",
+      "model.layers.16.post_attention_layernorm",
+      "model.layers.16.self_attn.k_norm",
+      "model.layers.16.self_attn.k_proj",
+      "model.layers.16.self_attn.o_proj",
+      "model.layers.16.self_attn.q_norm",
+      "model.layers.16.self_attn.q_proj",
+      "model.layers.16.self_attn.v_proj",
+      "model.layers.17.input_layernorm",
+      "model.layers.17.mlp.router.gate",
+      "model.layers.17.mlp.shared_mlp.down_proj",
+      "model.layers.17.mlp.shared_mlp.gate_proj",
+      "model.layers.17.mlp.shared_mlp.up_proj",
+      "model.layers.17.post_attention_layernorm",
+      "model.layers.17.self_attn.k_norm",
+      "model.layers.17.self_attn.k_proj",
+      "model.layers.17.self_attn.o_proj",
+      "model.layers.17.self_attn.q_norm",
+      "model.layers.17.self_attn.q_proj",
+      "model.layers.17.self_attn.v_proj",
+      "model.layers.18.input_layernorm",
+      "model.layers.18.mlp.router.gate",
+      "model.layers.18.mlp.shared_mlp.down_proj",
+      "model.layers.18.mlp.shared_mlp.gate_proj",
+      "model.layers.18.mlp.shared_mlp.up_proj",
+      "model.layers.18.post_attention_layernorm",
+      "model.layers.18.self_attn.k_norm",
+      "model.layers.18.self_attn.k_proj",
+      "model.layers.18.self_attn.o_proj",
+      "model.layers.18.self_attn.q_norm",
+      "model.layers.18.self_attn.q_proj",
+      "model.layers.18.self_attn.v_proj",
+      "model.layers.19.input_layernorm",
+      "model.layers.19.mlp.router.gate",
+      "model.layers.19.mlp.shared_mlp.down_proj",
+      "model.layers.19.mlp.shared_mlp.gate_proj",
+      "model.layers.19.mlp.shared_mlp.up_proj",
+      "model.layers.19.post_attention_layernorm",
+      "model.layers.19.self_attn.k_norm",
+      "model.layers.19.self_attn.k_proj",
+      "model.layers.19.self_attn.o_proj",
+      "model.layers.19.self_attn.q_norm",
+      "model.layers.19.self_attn.q_proj",
+      "model.layers.19.self_attn.v_proj",
+      "model.layers.2.input_layernorm",
+      "model.layers.2.mlp.router.gate",
+      "model.layers.2.mlp.shared_mlp.down_proj",
+      "model.layers.2.mlp.shared_mlp.gate_proj",
+      "model.layers.2.mlp.shared_mlp.up_proj",
+      "model.layers.2.post_attention_layernorm",
+      "model.layers.2.self_attn.k_norm",
+      "model.layers.2.self_attn.k_proj",
+      "model.layers.2.self_attn.o_proj",
+      "model.layers.2.self_attn.q_norm",
+      "model.layers.2.self_attn.q_proj",
+      "model.layers.2.self_attn.v_proj",
+      "model.layers.20.input_layernorm",
+      "model.layers.20.mlp.router.gate",
+      "model.layers.20.mlp.shared_mlp.down_proj",
+      "model.layers.20.mlp.shared_mlp.gate_proj",
+      "model.layers.20.mlp.shared_mlp.up_proj",
+      "model.layers.20.post_attention_layernorm",
+      "model.layers.20.self_attn.k_norm",
+      "model.layers.20.self_attn.k_proj",
+      "model.layers.20.self_attn.o_proj",
+      "model.layers.20.self_attn.q_norm",
+      "model.layers.20.self_attn.q_proj",
+      "model.layers.20.self_attn.v_proj",
+      "model.layers.21.input_layernorm",
+      "model.layers.21.mlp.router.gate",
+      "model.layers.21.mlp.shared_mlp.down_proj",
+      "model.layers.21.mlp.shared_mlp.gate_proj",
+      "model.layers.21.mlp.shared_mlp.up_proj",
+      "model.layers.21.post_attention_layernorm",
+      "model.layers.21.self_attn.k_norm",
+      "model.layers.21.self_attn.k_proj",
+      "model.layers.21.self_attn.o_proj",
+      "model.layers.21.self_attn.q_norm",
+      "model.layers.21.self_attn.q_proj",
+      "model.layers.21.self_attn.v_proj",
+      "model.layers.22.input_layernorm",
+      "model.layers.22.mlp.router.gate",
+      "model.layers.22.mlp.shared_mlp.down_proj",
+      "model.layers.22.mlp.shared_mlp.gate_proj",
+      "model.layers.22.mlp.shared_mlp.up_proj",
+      "model.layers.22.post_attention_layernorm",
+      "model.layers.22.self_attn.k_norm",
+      "model.layers.22.self_attn.k_proj",
+      "model.layers.22.self_attn.o_proj",
+      "model.layers.22.self_attn.q_norm",
+      "model.layers.22.self_attn.q_proj",
+      "model.layers.22.self_attn.v_proj",
+      "model.layers.23.input_layernorm",
+      "model.layers.23.mlp.router.gate",
+      "model.layers.23.mlp.shared_mlp.down_proj",
+      "model.layers.23.mlp.shared_mlp.gate_proj",
+      "model.layers.23.mlp.shared_mlp.up_proj",
+      "model.layers.23.post_attention_layernorm",
+      "model.layers.23.self_attn.k_norm",
+      "model.layers.23.self_attn.k_proj",
+      "model.layers.23.self_attn.o_proj",
+      "model.layers.23.self_attn.q_norm",
+      "model.layers.23.self_attn.q_proj",
+      "model.layers.23.self_attn.v_proj",
+      "model.layers.24.input_layernorm",
+      "model.layers.24.mlp.router.gate",
+      "model.layers.24.mlp.shared_mlp.down_proj",
+      "model.layers.24.mlp.shared_mlp.gate_proj",
+      "model.layers.24.mlp.shared_mlp.up_proj",
+      "model.layers.24.post_attention_layernorm",
+      "model.layers.24.self_attn.k_norm",
+      "model.layers.24.self_attn.k_proj",
+      "model.layers.24.self_attn.o_proj",
+      "model.layers.24.self_attn.q_norm",
+      "model.layers.24.self_attn.q_proj",
+      "model.layers.24.self_attn.v_proj",
+      "model.layers.25.input_layernorm",
+      "model.layers.25.mlp.router.gate",
+      "model.layers.25.mlp.shared_mlp.down_proj",
+      "model.layers.25.mlp.shared_mlp.gate_proj",
+      "model.layers.25.mlp.shared_mlp.up_proj",
+      "model.layers.25.post_attention_layernorm",
+      "model.layers.25.self_attn.k_norm",
+      "model.layers.25.self_attn.k_proj",
+      "model.layers.25.self_attn.o_proj",
+      "model.layers.25.self_attn.q_norm",
+      "model.layers.25.self_attn.q_proj",
+      "model.layers.25.self_attn.v_proj",
+      "model.layers.26.input_layernorm",
+      "model.layers.26.mlp.router.gate",
+      "model.layers.26.mlp.shared_mlp.down_proj",
+      "model.layers.26.mlp.shared_mlp.gate_proj",
+      "model.layers.26.mlp.shared_mlp.up_proj",
+      "model.layers.26.post_attention_layernorm",
+      "model.layers.26.self_attn.k_norm",
+      "model.layers.26.self_attn.k_proj",
+      "model.layers.26.self_attn.o_proj",
+      "model.layers.26.self_attn.q_norm",
+      "model.layers.26.self_attn.q_proj",
+      "model.layers.26.self_attn.v_proj",
+      "model.layers.27.input_layernorm",
+      "model.layers.27.mlp.router.gate",
+      "model.layers.27.mlp.shared_mlp.down_proj",
+      "model.layers.27.mlp.shared_mlp.gate_proj",
+      "model.layers.27.mlp.shared_mlp.up_proj",
+      "model.layers.27.post_attention_layernorm",
+      "model.layers.27.self_attn.k_norm",
+      "model.layers.27.self_attn.k_proj",
+      "model.layers.27.self_attn.o_proj",
+      "model.layers.27.self_attn.q_norm",
+      "model.layers.27.self_attn.q_proj",
+      "model.layers.27.self_attn.v_proj",
+      "model.layers.28.input_layernorm",
+      "model.layers.28.mlp.router.gate",
+      "model.layers.28.mlp.shared_mlp.down_proj",
+      "model.layers.28.mlp.shared_mlp.gate_proj",
+      "model.layers.28.mlp.shared_mlp.up_proj",
+      "model.layers.28.post_attention_layernorm",
+      "model.layers.28.self_attn.k_norm",
+      "model.layers.28.self_attn.k_proj",
+      "model.layers.28.self_attn.o_proj",
+      "model.layers.28.self_attn.q_norm",
+      "model.layers.28.self_attn.q_proj",
+      "model.layers.28.self_attn.v_proj",
+      "model.layers.29.input_layernorm",
+      "model.layers.29.mlp.router.gate",
+      "model.layers.29.mlp.shared_mlp.down_proj",
+      "model.layers.29.mlp.shared_mlp.gate_proj",
+      "model.layers.29.mlp.shared_mlp.up_proj",
+      "model.layers.29.post_attention_layernorm",
+      "model.layers.29.self_attn.k_norm",
+      "model.layers.29.self_attn.k_proj",
+      "model.layers.29.self_attn.o_proj",
+      "model.layers.29.self_attn.q_norm",
+      "model.layers.29.self_attn.q_proj",
+      "model.layers.29.self_attn.v_proj",
+      "model.layers.3.input_layernorm",
+      "model.layers.3.mlp.router.gate",
+      "model.layers.3.mlp.shared_mlp.down_proj",
+      "model.layers.3.mlp.shared_mlp.gate_proj",
+      "model.layers.3.mlp.shared_mlp.up_proj",
+      "model.layers.3.post_attention_layernorm",
+      "model.layers.3.self_attn.k_norm",
+      "model.layers.3.self_attn.k_proj",
+      "model.layers.3.self_attn.o_proj",
+      "model.layers.3.self_attn.q_norm",
+      "model.layers.3.self_attn.q_proj",
+      "model.layers.3.self_attn.v_proj",
+      "model.layers.30.input_layernorm",
+      "model.layers.30.mlp.router.gate",
+      "model.layers.30.mlp.shared_mlp.down_proj",
+      "model.layers.30.mlp.shared_mlp.gate_proj",
+      "model.layers.30.mlp.shared_mlp.up_proj",
+      "model.layers.30.post_attention_layernorm",
+      "model.layers.30.self_attn.k_norm",
+      "model.layers.30.self_attn.k_proj",
+      "model.layers.30.self_attn.o_proj",
+      "model.layers.30.self_attn.q_norm",
+      "model.layers.30.self_attn.q_proj",
+      "model.layers.30.self_attn.v_proj",
+      "model.layers.31.input_layernorm",
+      "model.layers.31.mlp.router.gate",
+      "model.layers.31.mlp.shared_mlp.down_proj",
+      "model.layers.31.mlp.shared_mlp.gate_proj",
+      "model.layers.31.mlp.shared_mlp.up_proj",
+      "model.layers.31.post_attention_layernorm",
+      "model.layers.31.self_attn.k_norm",
+      "model.layers.31.self_attn.k_proj",
+      "model.layers.31.self_attn.o_proj",
+      "model.layers.31.self_attn.q_norm",
+      "model.layers.31.self_attn.q_proj",
+      "model.layers.31.self_attn.v_proj",
+      "model.layers.32.input_layernorm",
+      "model.layers.32.mlp.router.gate",
+      "model.layers.32.mlp.shared_mlp.down_proj",
+      "model.layers.32.mlp.shared_mlp.gate_proj",
+      "model.layers.32.mlp.shared_mlp.up_proj",
+      "model.layers.32.post_attention_layernorm",
+      "model.layers.32.self_attn.k_norm",
+      "model.layers.32.self_attn.k_proj",
+      "model.layers.32.self_attn.o_proj",
+      "model.layers.32.self_attn.q_norm",
+      "model.layers.32.self_attn.q_proj",
+      "model.layers.32.self_attn.v_proj",
+      "model.layers.33.input_layernorm",
+      "model.layers.33.mlp.router.gate",
+      "model.layers.33.mlp.shared_mlp.down_proj",
+      "model.layers.33.mlp.shared_mlp.gate_proj",
+      "model.layers.33.mlp.shared_mlp.up_proj",
+      "model.layers.33.post_attention_layernorm",
+      "model.layers.33.self_attn.k_norm",
+      "model.layers.33.self_attn.k_proj",
+      "model.layers.33.self_attn.o_proj",
+      "model.layers.33.self_attn.q_norm",
+      "model.layers.33.self_attn.q_proj",
+      "model.layers.33.self_attn.v_proj",
+      "model.layers.34.input_layernorm",
+      "model.layers.34.mlp.router.gate",
+      "model.layers.34.mlp.shared_mlp.down_proj",
+      "model.layers.34.mlp.shared_mlp.gate_proj",
+      "model.layers.34.mlp.shared_mlp.up_proj",
+      "model.layers.34.post_attention_layernorm",
+      "model.layers.34.self_attn.k_norm",
+      "model.layers.34.self_attn.k_proj",
+      "model.layers.34.self_attn.o_proj",
+      "model.layers.34.self_attn.q_norm",
+      "model.layers.34.self_attn.q_proj",
+      "model.layers.34.self_attn.v_proj",
+      "model.layers.35.input_layernorm",
+      "model.layers.35.mlp.router.gate",
+      "model.layers.35.mlp.shared_mlp.down_proj",
+      "model.layers.35.mlp.shared_mlp.gate_proj",
+      "model.layers.35.mlp.shared_mlp.up_proj",
+      "model.layers.35.post_attention_layernorm",
+      "model.layers.35.self_attn.k_norm",
+      "model.layers.35.self_attn.k_proj",
+      "model.layers.35.self_attn.o_proj",
+      "model.layers.35.self_attn.q_norm",
+      "model.layers.35.self_attn.q_proj",
+      "model.layers.35.self_attn.v_proj",
+      "model.layers.36.input_layernorm",
+      "model.layers.36.mlp.router.gate",
+      "model.layers.36.mlp.shared_mlp.down_proj",
+      "model.layers.36.mlp.shared_mlp.gate_proj",
+      "model.layers.36.mlp.shared_mlp.up_proj",
+      "model.layers.36.post_attention_layernorm",
+      "model.layers.36.self_attn.k_norm",
+      "model.layers.36.self_attn.k_proj",
+      "model.layers.36.self_attn.o_proj",
+      "model.layers.36.self_attn.q_norm",
+      "model.layers.36.self_attn.q_proj",
+      "model.layers.36.self_attn.v_proj",
+      "model.layers.37.input_layernorm",
+      "model.layers.37.mlp.router.gate",
+      "model.layers.37.mlp.shared_mlp.down_proj",
+      "model.layers.37.mlp.shared_mlp.gate_proj",
+      "model.layers.37.mlp.shared_mlp.up_proj",
+      "model.layers.37.post_attention_layernorm",
+      "model.layers.37.self_attn.k_norm",
+      "model.layers.37.self_attn.k_proj",
+      "model.layers.37.self_attn.o_proj",
+      "model.layers.37.self_attn.q_norm",
+      "model.layers.37.self_attn.q_proj",
+      "model.layers.37.self_attn.v_proj",
+      "model.layers.38.input_layernorm",
+      "model.layers.38.mlp.router.gate",
+      "model.layers.38.mlp.shared_mlp.down_proj",
+      "model.layers.38.mlp.shared_mlp.gate_proj",
+      "model.layers.38.mlp.shared_mlp.up_proj",
+      "model.layers.38.post_attention_layernorm",
+      "model.layers.38.self_attn.k_norm",
+      "model.layers.38.self_attn.k_proj",
+      "model.layers.38.self_attn.o_proj",
+      "model.layers.38.self_attn.q_norm",
+      "model.layers.38.self_attn.q_proj",
+      "model.layers.38.self_attn.v_proj",
+      "model.layers.39.input_layernorm",
+      "model.layers.39.mlp.router.gate",
+      "model.layers.39.mlp.shared_mlp.down_proj",
+      "model.layers.39.mlp.shared_mlp.gate_proj",
+      "model.layers.39.mlp.shared_mlp.up_proj",
+      "model.layers.39.post_attention_layernorm",
+      "model.layers.39.self_attn.k_norm",
+      "model.layers.39.self_attn.k_proj",
+      "model.layers.39.self_attn.o_proj",
+      "model.layers.39.self_attn.q_norm",
+      "model.layers.39.self_attn.q_proj",
+      "model.layers.39.self_attn.v_proj",
+      "model.layers.4.input_layernorm",
+      "model.layers.4.mlp.router.gate",
+      "model.layers.4.mlp.shared_mlp.down_proj",
+      "model.layers.4.mlp.shared_mlp.gate_proj",
+      "model.layers.4.mlp.shared_mlp.up_proj",
+      "model.layers.4.post_attention_layernorm",
+      "model.layers.4.self_attn.k_norm",
+      "model.layers.4.self_attn.k_proj",
+      "model.layers.4.self_attn.o_proj",
+      "model.layers.4.self_attn.q_norm",
+      "model.layers.4.self_attn.q_proj",
+      "model.layers.4.self_attn.v_proj",
+      "model.layers.40.input_layernorm",
+      "model.layers.40.mlp.router.gate",
+      "model.layers.40.mlp.shared_mlp.down_proj",
+      "model.layers.40.mlp.shared_mlp.gate_proj",
+      "model.layers.40.mlp.shared_mlp.up_proj",
+      "model.layers.40.post_attention_layernorm",
+      "model.layers.40.self_attn.k_norm",
+      "model.layers.40.self_attn.k_proj",
+      "model.layers.40.self_attn.o_proj",
+      "model.layers.40.self_attn.q_norm",
+      "model.layers.40.self_attn.q_proj",
+      "model.layers.40.self_attn.v_proj",
+      "model.layers.41.input_layernorm",
+      "model.layers.41.mlp.router.gate",
+      "model.layers.41.mlp.shared_mlp.down_proj",
+      "model.layers.41.mlp.shared_mlp.gate_proj",
+      "model.layers.41.mlp.shared_mlp.up_proj",
+      "model.layers.41.post_attention_layernorm",
+      "model.layers.41.self_attn.k_norm",
+      "model.layers.41.self_attn.k_proj",
+      "model.layers.41.self_attn.o_proj",
+      "model.layers.41.self_attn.q_norm",
+      "model.layers.41.self_attn.q_proj",
+      "model.layers.41.self_attn.v_proj",
+      "model.layers.42.input_layernorm",
+      "model.layers.42.mlp.router.gate",
+      "model.layers.42.mlp.shared_mlp.down_proj",
+      "model.layers.42.mlp.shared_mlp.gate_proj",
+      "model.layers.42.mlp.shared_mlp.up_proj",
+      "model.layers.42.post_attention_layernorm",
+      "model.layers.42.self_attn.k_norm",
+      "model.layers.42.self_attn.k_proj",
+      "model.layers.42.self_attn.o_proj",
+      "model.layers.42.self_attn.q_norm",
+      "model.layers.42.self_attn.q_proj",
+      "model.layers.42.self_attn.v_proj",
+      "model.layers.43.input_layernorm",
+      "model.layers.43.mlp.router.gate",
+      "model.layers.43.mlp.shared_mlp.down_proj",
+      "model.layers.43.mlp.shared_mlp.gate_proj",
+      "model.layers.43.mlp.shared_mlp.up_proj",
+      "model.layers.43.post_attention_layernorm",
+      "model.layers.43.self_attn.k_norm",
+      "model.layers.43.self_attn.k_proj",
+      "model.layers.43.self_attn.o_proj",
+      "model.layers.43.self_attn.q_norm",
+      "model.layers.43.self_attn.q_proj",
+      "model.layers.43.self_attn.v_proj",
+      "model.layers.44.input_layernorm",
+      "model.layers.44.mlp.router.gate",
+      "model.layers.44.mlp.shared_mlp.down_proj",
+      "model.layers.44.mlp.shared_mlp.gate_proj",
+      "model.layers.44.mlp.shared_mlp.up_proj",
+      "model.layers.44.post_attention_layernorm",
+      "model.layers.44.self_attn.k_norm",
+      "model.layers.44.self_attn.k_proj",
+      "model.layers.44.self_attn.o_proj",
+      "model.layers.44.self_attn.q_norm",
+      "model.layers.44.self_attn.q_proj",
+      "model.layers.44.self_attn.v_proj",
+      "model.layers.45.input_layernorm",
+      "model.layers.45.mlp.router.gate",
+      "model.layers.45.mlp.shared_mlp.down_proj",
+      "model.layers.45.mlp.shared_mlp.gate_proj",
+      "model.layers.45.mlp.shared_mlp.up_proj",
+      "model.layers.45.post_attention_layernorm",
+      "model.layers.45.self_attn.k_norm",
+      "model.layers.45.self_attn.k_proj",
+      "model.layers.45.self_attn.o_proj",
+      "model.layers.45.self_attn.q_norm",
+      "model.layers.45.self_attn.q_proj",
+      "model.layers.45.self_attn.v_proj",
+      "model.layers.46.input_layernorm",
+      "model.layers.46.mlp.router.gate",
+      "model.layers.46.mlp.shared_mlp.down_proj",
+      "model.layers.46.mlp.shared_mlp.gate_proj",
+      "model.layers.46.mlp.shared_mlp.up_proj",
+      "model.layers.46.post_attention_layernorm",
+      "model.layers.46.self_attn.k_norm",
+      "model.layers.46.self_attn.k_proj",
+      "model.layers.46.self_attn.o_proj",
+      "model.layers.46.self_attn.q_norm",
+      "model.layers.46.self_attn.q_proj",
+      "model.layers.46.self_attn.v_proj",
+      "model.layers.47.input_layernorm",
+      "model.layers.47.mlp.router.gate",
+      "model.layers.47.mlp.shared_mlp.down_proj",
+      "model.layers.47.mlp.shared_mlp.gate_proj",
+      "model.layers.47.mlp.shared_mlp.up_proj",
+      "model.layers.47.post_attention_layernorm",
+      "model.layers.47.self_attn.k_norm",
+      "model.layers.47.self_attn.k_proj",
+      "model.layers.47.self_attn.o_proj",
+      "model.layers.47.self_attn.q_norm",
+      "model.layers.47.self_attn.q_proj",
+      "model.layers.47.self_attn.v_proj",
+      "model.layers.48.input_layernorm",
+      "model.layers.48.mlp.router.gate",
+      "model.layers.48.mlp.shared_mlp.down_proj",
+      "model.layers.48.mlp.shared_mlp.gate_proj",
+      "model.layers.48.mlp.shared_mlp.up_proj",
+      "model.layers.48.post_attention_layernorm",
+      "model.layers.48.self_attn.k_norm",
+      "model.layers.48.self_attn.k_proj",
+      "model.layers.48.self_attn.o_proj",
+      "model.layers.48.self_attn.q_norm",
+      "model.layers.48.self_attn.q_proj",
+      "model.layers.48.self_attn.v_proj",
+      "model.layers.49.input_layernorm",
+      "model.layers.49.mlp.router.gate",
+      "model.layers.49.mlp.shared_mlp.down_proj",
+      "model.layers.49.mlp.shared_mlp.gate_proj",
+      "model.layers.49.mlp.shared_mlp.up_proj",
+      "model.layers.49.post_attention_layernorm",
+      "model.layers.49.self_attn.k_norm",
+      "model.layers.49.self_attn.k_proj",
+      "model.layers.49.self_attn.o_proj",
+      "model.layers.49.self_attn.q_norm",
+      "model.layers.49.self_attn.q_proj",
+      "model.layers.49.self_attn.v_proj",
+      "model.layers.5.input_layernorm",
+      "model.layers.5.mlp.router.gate",
+      "model.layers.5.mlp.shared_mlp.down_proj",
+      "model.layers.5.mlp.shared_mlp.gate_proj",
+      "model.layers.5.mlp.shared_mlp.up_proj",
+      "model.layers.5.post_attention_layernorm",
+      "model.layers.5.self_attn.k_norm",
+      "model.layers.5.self_attn.k_proj",
+      "model.layers.5.self_attn.o_proj",
+      "model.layers.5.self_attn.q_norm",
+      "model.layers.5.self_attn.q_proj",
+      "model.layers.5.self_attn.v_proj",
+      "model.layers.50.input_layernorm",
+      "model.layers.50.mlp.router.gate",
+      "model.layers.50.mlp.shared_mlp.down_proj",
+      "model.layers.50.mlp.shared_mlp.gate_proj",
+      "model.layers.50.mlp.shared_mlp.up_proj",
+      "model.layers.50.post_attention_layernorm",
+      "model.layers.50.self_attn.k_norm",
+      "model.layers.50.self_attn.k_proj",
+      "model.layers.50.self_attn.o_proj",
+      "model.layers.50.self_attn.q_norm",
+      "model.layers.50.self_attn.q_proj",
+      "model.layers.50.self_attn.v_proj",
+      "model.layers.51.input_layernorm",
+      "model.layers.51.mlp.router.gate",
+      "model.layers.51.mlp.shared_mlp.down_proj",
+      "model.layers.51.mlp.shared_mlp.gate_proj",
+      "model.layers.51.mlp.shared_mlp.up_proj",
+      "model.layers.51.post_attention_layernorm",
+      "model.layers.51.self_attn.k_norm",
+      "model.layers.51.self_attn.k_proj",
+      "model.layers.51.self_attn.o_proj",
+      "model.layers.51.self_attn.q_norm",
+      "model.layers.51.self_attn.q_proj",
+      "model.layers.51.self_attn.v_proj",
+      "model.layers.52.input_layernorm",
+      "model.layers.52.mlp.router.gate",
+      "model.layers.52.mlp.shared_mlp.down_proj",
+      "model.layers.52.mlp.shared_mlp.gate_proj",
+      "model.layers.52.mlp.shared_mlp.up_proj",
+      "model.layers.52.post_attention_layernorm",
+      "model.layers.52.self_attn.k_norm",
+      "model.layers.52.self_attn.k_proj",
+      "model.layers.52.self_attn.o_proj",
+      "model.layers.52.self_attn.q_norm",
+      "model.layers.52.self_attn.q_proj",
+      "model.layers.52.self_attn.v_proj",
+      "model.layers.53.input_layernorm",
+      "model.layers.53.mlp.router.gate",
+      "model.layers.53.mlp.shared_mlp.down_proj",
+      "model.layers.53.mlp.shared_mlp.gate_proj",
+      "model.layers.53.mlp.shared_mlp.up_proj",
+      "model.layers.53.post_attention_layernorm",
+      "model.layers.53.self_attn.k_norm",
+      "model.layers.53.self_attn.k_proj",
+      "model.layers.53.self_attn.o_proj",
+      "model.layers.53.self_attn.q_norm",
+      "model.layers.53.self_attn.q_proj",
+      "model.layers.53.self_attn.v_proj",
+      "model.layers.54.input_layernorm",
+      "model.layers.54.mlp.router.gate",
+      "model.layers.54.mlp.shared_mlp.down_proj",
+      "model.layers.54.mlp.shared_mlp.gate_proj",
+      "model.layers.54.mlp.shared_mlp.up_proj",
+      "model.layers.54.post_attention_layernorm",
+      "model.layers.54.self_attn.k_norm",
+      "model.layers.54.self_attn.k_proj",
+      "model.layers.54.self_attn.o_proj",
+      "model.layers.54.self_attn.q_norm",
+      "model.layers.54.self_attn.q_proj",
+      "model.layers.54.self_attn.v_proj",
+      "model.layers.55.input_layernorm",
+      "model.layers.55.mlp.router.gate",
+      "model.layers.55.mlp.shared_mlp.down_proj",
+      "model.layers.55.mlp.shared_mlp.gate_proj",
+      "model.layers.55.mlp.shared_mlp.up_proj",
+      "model.layers.55.post_attention_layernorm",
+      "model.layers.55.self_attn.k_norm",
+      "model.layers.55.self_attn.k_proj",
+      "model.layers.55.self_attn.o_proj",
+      "model.layers.55.self_attn.q_norm",
+      "model.layers.55.self_attn.q_proj",
+      "model.layers.55.self_attn.v_proj",
+      "model.layers.56.input_layernorm",
+      "model.layers.56.mlp.router.gate",
+      "model.layers.56.mlp.shared_mlp.down_proj",
+      "model.layers.56.mlp.shared_mlp.gate_proj",
+      "model.layers.56.mlp.shared_mlp.up_proj",
+      "model.layers.56.post_attention_layernorm",
+      "model.layers.56.self_attn.k_norm",
+      "model.layers.56.self_attn.k_proj",
+      "model.layers.56.self_attn.o_proj",
+      "model.layers.56.self_attn.q_norm",
+      "model.layers.56.self_attn.q_proj",
+      "model.layers.56.self_attn.v_proj",
+      "model.layers.57.input_layernorm",
+      "model.layers.57.mlp.router.gate",
+      "model.layers.57.mlp.shared_mlp.down_proj",
+      "model.layers.57.mlp.shared_mlp.gate_proj",
+      "model.layers.57.mlp.shared_mlp.up_proj",
+      "model.layers.57.post_attention_layernorm",
+      "model.layers.57.self_attn.k_norm",
+      "model.layers.57.self_attn.k_proj",
+      "model.layers.57.self_attn.o_proj",
+      "model.layers.57.self_attn.q_norm",
+      "model.layers.57.self_attn.q_proj",
+      "model.layers.57.self_attn.v_proj",
+      "model.layers.58.input_layernorm",
+      "model.layers.58.mlp.router.gate",
+      "model.layers.58.mlp.shared_mlp.down_proj",
+      "model.layers.58.mlp.shared_mlp.gate_proj",
+      "model.layers.58.mlp.shared_mlp.up_proj",
+      "model.layers.58.post_attention_layernorm",
+      "model.layers.58.self_attn.k_norm",
+      "model.layers.58.self_attn.k_proj",
+      "model.layers.58.self_attn.o_proj",
+      "model.layers.58.self_attn.q_norm",
+      "model.layers.58.self_attn.q_proj",
+      "model.layers.58.self_attn.v_proj",
+      "model.layers.59.input_layernorm",
+      "model.layers.59.mlp.router.gate",
+      "model.layers.59.mlp.shared_mlp.down_proj",
+      "model.layers.59.mlp.shared_mlp.gate_proj",
+      "model.layers.59.mlp.shared_mlp.up_proj",
+      "model.layers.59.post_attention_layernorm",
+      "model.layers.59.self_attn.k_norm",
+      "model.layers.59.self_attn.k_proj",
+      "model.layers.59.self_attn.o_proj",
+      "model.layers.59.self_attn.q_norm",
+      "model.layers.59.self_attn.q_proj",
+      "model.layers.59.self_attn.v_proj",
+      "model.layers.6.input_layernorm",
+      "model.layers.6.mlp.router.gate",
+      "model.layers.6.mlp.shared_mlp.down_proj",
+      "model.layers.6.mlp.shared_mlp.gate_proj",
+      "model.layers.6.mlp.shared_mlp.up_proj",
+      "model.layers.6.post_attention_layernorm",
+      "model.layers.6.self_attn.k_norm",
+      "model.layers.6.self_attn.k_proj",
+      "model.layers.6.self_attn.o_proj",
+      "model.layers.6.self_attn.q_norm",
+      "model.layers.6.self_attn.q_proj",
+      "model.layers.6.self_attn.v_proj",
+      "model.layers.60.input_layernorm",
+      "model.layers.60.mlp.router.gate",
+      "model.layers.60.mlp.shared_mlp.down_proj",
+      "model.layers.60.mlp.shared_mlp.gate_proj",
+      "model.layers.60.mlp.shared_mlp.up_proj",
+      "model.layers.60.post_attention_layernorm",
+      "model.layers.60.self_attn.k_norm",
+      "model.layers.60.self_attn.k_proj",
+      "model.layers.60.self_attn.o_proj",
+      "model.layers.60.self_attn.q_norm",
+      "model.layers.60.self_attn.q_proj",
+      "model.layers.60.self_attn.v_proj",
+      "model.layers.61.input_layernorm",
+      "model.layers.61.mlp.router.gate",
+      "model.layers.61.mlp.shared_mlp.down_proj",
+      "model.layers.61.mlp.shared_mlp.gate_proj",
+      "model.layers.61.mlp.shared_mlp.up_proj",
+      "model.layers.61.post_attention_layernorm",
+      "model.layers.61.self_attn.k_norm",
+      "model.layers.61.self_attn.k_proj",
+      "model.layers.61.self_attn.o_proj",
+      "model.layers.61.self_attn.q_norm",
+      "model.layers.61.self_attn.q_proj",
+      "model.layers.61.self_attn.v_proj",
+      "model.layers.62.input_layernorm",
+      "model.layers.62.mlp.router.gate",
+      "model.layers.62.mlp.shared_mlp.down_proj",
+      "model.layers.62.mlp.shared_mlp.gate_proj",
+      "model.layers.62.mlp.shared_mlp.up_proj",
+      "model.layers.62.post_attention_layernorm",
+      "model.layers.62.self_attn.k_norm",
+      "model.layers.62.self_attn.k_proj",
+      "model.layers.62.self_attn.o_proj",
+      "model.layers.62.self_attn.q_norm",
+      "model.layers.62.self_attn.q_proj",
+      "model.layers.62.self_attn.v_proj",
+      "model.layers.63.input_layernorm",
+      "model.layers.63.mlp.router.gate",
+      "model.layers.63.mlp.shared_mlp.down_proj",
+      "model.layers.63.mlp.shared_mlp.gate_proj",
+      "model.layers.63.mlp.shared_mlp.up_proj",
+      "model.layers.63.post_attention_layernorm",
+      "model.layers.63.self_attn.k_norm",
+      "model.layers.63.self_attn.k_proj",
+      "model.layers.63.self_attn.o_proj",
+      "model.layers.63.self_attn.q_norm",
+      "model.layers.63.self_attn.q_proj",
+      "model.layers.63.self_attn.v_proj",
+      "model.layers.64.input_layernorm",
+      "model.layers.64.mlp.router.gate",
+      "model.layers.64.mlp.shared_mlp.down_proj",
+      "model.layers.64.mlp.shared_mlp.gate_proj",
+      "model.layers.64.mlp.shared_mlp.up_proj",
+      "model.layers.64.post_attention_layernorm",
+      "model.layers.64.self_attn.k_norm",
+      "model.layers.64.self_attn.k_proj",
+      "model.layers.64.self_attn.o_proj",
+      "model.layers.64.self_attn.q_norm",
+      "model.layers.64.self_attn.q_proj",
+      "model.layers.64.self_attn.v_proj",
+      "model.layers.65.input_layernorm",
+      "model.layers.65.mlp.router.gate",
+      "model.layers.65.mlp.shared_mlp.down_proj",
+      "model.layers.65.mlp.shared_mlp.gate_proj",
+      "model.layers.65.mlp.shared_mlp.up_proj",
+      "model.layers.65.post_attention_layernorm",
+      "model.layers.65.self_attn.k_norm",
+      "model.layers.65.self_attn.k_proj",
+      "model.layers.65.self_attn.o_proj",
+      "model.layers.65.self_attn.q_norm",
+      "model.layers.65.self_attn.q_proj",
+      "model.layers.65.self_attn.v_proj",
+      "model.layers.66.input_layernorm",
+      "model.layers.66.mlp.router.gate",
+      "model.layers.66.mlp.shared_mlp.down_proj",
+      "model.layers.66.mlp.shared_mlp.gate_proj",
+      "model.layers.66.mlp.shared_mlp.up_proj",
+      "model.layers.66.post_attention_layernorm",
+      "model.layers.66.self_attn.k_norm",
+      "model.layers.66.self_attn.k_proj",
+      "model.layers.66.self_attn.o_proj",
+      "model.layers.66.self_attn.q_norm",
+      "model.layers.66.self_attn.q_proj",
+      "model.layers.66.self_attn.v_proj",
+      "model.layers.67.input_layernorm",
+      "model.layers.67.mlp.router.gate",
+      "model.layers.67.mlp.shared_mlp.down_proj",
+      "model.layers.67.mlp.shared_mlp.gate_proj",
+      "model.layers.67.mlp.shared_mlp.up_proj",
+      "model.layers.67.post_attention_layernorm",
+      "model.layers.67.self_attn.k_norm",
+      "model.layers.67.self_attn.k_proj",
+      "model.layers.67.self_attn.o_proj",
+      "model.layers.67.self_attn.q_norm",
+      "model.layers.67.self_attn.q_proj",
+      "model.layers.67.self_attn.v_proj",
+      "model.layers.68.input_layernorm",
+      "model.layers.68.mlp.router.gate",
+      "model.layers.68.mlp.shared_mlp.down_proj",
+      "model.layers.68.mlp.shared_mlp.gate_proj",
+      "model.layers.68.mlp.shared_mlp.up_proj",
+      "model.layers.68.post_attention_layernorm",
+      "model.layers.68.self_attn.k_norm",
+      "model.layers.68.self_attn.k_proj",
+      "model.layers.68.self_attn.o_proj",
+      "model.layers.68.self_attn.q_norm",
+      "model.layers.68.self_attn.q_proj",
+      "model.layers.68.self_attn.v_proj",
+      "model.layers.69.input_layernorm",
+      "model.layers.69.mlp.router.gate",
+      "model.layers.69.mlp.shared_mlp.down_proj",
+      "model.layers.69.mlp.shared_mlp.gate_proj",
+      "model.layers.69.mlp.shared_mlp.up_proj",
+      "model.layers.69.post_attention_layernorm",
+      "model.layers.69.self_attn.k_norm",
+      "model.layers.69.self_attn.k_proj",
+      "model.layers.69.self_attn.o_proj",
+      "model.layers.69.self_attn.q_norm",
+      "model.layers.69.self_attn.q_proj",
+      "model.layers.69.self_attn.v_proj",
+      "model.layers.7.input_layernorm",
+      "model.layers.7.mlp.router.gate",
+      "model.layers.7.mlp.shared_mlp.down_proj",
+      "model.layers.7.mlp.shared_mlp.gate_proj",
+      "model.layers.7.mlp.shared_mlp.up_proj",
+      "model.layers.7.post_attention_layernorm",
+      "model.layers.7.self_attn.k_norm",
+      "model.layers.7.self_attn.k_proj",
+      "model.layers.7.self_attn.o_proj",
+      "model.layers.7.self_attn.q_norm",
+      "model.layers.7.self_attn.q_proj",
+      "model.layers.7.self_attn.v_proj",
+      "model.layers.70.input_layernorm",
+      "model.layers.70.mlp.router.gate",
+      "model.layers.70.mlp.shared_mlp.down_proj",
+      "model.layers.70.mlp.shared_mlp.gate_proj",
+      "model.layers.70.mlp.shared_mlp.up_proj",
+      "model.layers.70.post_attention_layernorm",
+      "model.layers.70.self_attn.k_norm",
+      "model.layers.70.self_attn.k_proj",
+      "model.layers.70.self_attn.o_proj",
+      "model.layers.70.self_attn.q_norm",
+      "model.layers.70.self_attn.q_proj",
+      "model.layers.70.self_attn.v_proj",
+      "model.layers.71.input_layernorm",
+      "model.layers.71.mlp.router.gate",
+      "model.layers.71.mlp.shared_mlp.down_proj",
+      "model.layers.71.mlp.shared_mlp.gate_proj",
+      "model.layers.71.mlp.shared_mlp.up_proj",
+      "model.layers.71.post_attention_layernorm",
+      "model.layers.71.self_attn.k_norm",
+      "model.layers.71.self_attn.k_proj",
+      "model.layers.71.self_attn.o_proj",
+      "model.layers.71.self_attn.q_norm",
+      "model.layers.71.self_attn.q_proj",
+      "model.layers.71.self_attn.v_proj",
+      "model.layers.72.input_layernorm",
+      "model.layers.72.mlp.router.gate",
+      "model.layers.72.mlp.shared_mlp.down_proj",
+      "model.layers.72.mlp.shared_mlp.gate_proj",
+      "model.layers.72.mlp.shared_mlp.up_proj",
+      "model.layers.72.post_attention_layernorm",
+      "model.layers.72.self_attn.k_norm",
+      "model.layers.72.self_attn.k_proj",
+      "model.layers.72.self_attn.o_proj",
+      "model.layers.72.self_attn.q_norm",
+      "model.layers.72.self_attn.q_proj",
+      "model.layers.72.self_attn.v_proj",
+      "model.layers.73.input_layernorm",
+      "model.layers.73.mlp.router.gate",
+      "model.layers.73.mlp.shared_mlp.down_proj",
+      "model.layers.73.mlp.shared_mlp.gate_proj",
+      "model.layers.73.mlp.shared_mlp.up_proj",
+      "model.layers.73.post_attention_layernorm",
+      "model.layers.73.self_attn.k_norm",
+      "model.layers.73.self_attn.k_proj",
+      "model.layers.73.self_attn.o_proj",
+      "model.layers.73.self_attn.q_norm",
+      "model.layers.73.self_attn.q_proj",
+      "model.layers.73.self_attn.v_proj",
+      "model.layers.74.input_layernorm",
+      "model.layers.74.mlp.router.gate",
+      "model.layers.74.mlp.shared_mlp.down_proj",
+      "model.layers.74.mlp.shared_mlp.gate_proj",
+      "model.layers.74.mlp.shared_mlp.up_proj",
+      "model.layers.74.post_attention_layernorm",
+      "model.layers.74.self_attn.k_norm",
+      "model.layers.74.self_attn.k_proj",
+      "model.layers.74.self_attn.o_proj",
+      "model.layers.74.self_attn.q_norm",
+      "model.layers.74.self_attn.q_proj",
+      "model.layers.74.self_attn.v_proj",
+      "model.layers.75.input_layernorm",
+      "model.layers.75.mlp.router.gate",
+      "model.layers.75.mlp.shared_mlp.down_proj",
+      "model.layers.75.mlp.shared_mlp.gate_proj",
+      "model.layers.75.mlp.shared_mlp.up_proj",
+      "model.layers.75.post_attention_layernorm",
+      "model.layers.75.self_attn.k_norm",
+      "model.layers.75.self_attn.k_proj",
+      "model.layers.75.self_attn.o_proj",
+      "model.layers.75.self_attn.q_norm",
+      "model.layers.75.self_attn.q_proj",
+      "model.layers.75.self_attn.v_proj",
+      "model.layers.76.input_layernorm",
+      "model.layers.76.mlp.router.gate",
+      "model.layers.76.mlp.shared_mlp.down_proj",
+      "model.layers.76.mlp.shared_mlp.gate_proj",
+      "model.layers.76.mlp.shared_mlp.up_proj",
+      "model.layers.76.post_attention_layernorm",
+      "model.layers.76.self_attn.k_norm",
+      "model.layers.76.self_attn.k_proj",
+      "model.layers.76.self_attn.o_proj",
+      "model.layers.76.self_attn.q_norm",
+      "model.layers.76.self_attn.q_proj",
+      "model.layers.76.self_attn.v_proj",
+      "model.layers.77.input_layernorm",
+      "model.layers.77.mlp.router.gate",
+      "model.layers.77.mlp.shared_mlp.down_proj",
+      "model.layers.77.mlp.shared_mlp.gate_proj",
+      "model.layers.77.mlp.shared_mlp.up_proj",
+      "model.layers.77.post_attention_layernorm",
+      "model.layers.77.self_attn.k_norm",
+      "model.layers.77.self_attn.k_proj",
+      "model.layers.77.self_attn.o_proj",
+      "model.layers.77.self_attn.q_norm",
+      "model.layers.77.self_attn.q_proj",
+      "model.layers.77.self_attn.v_proj",
+      "model.layers.78.input_layernorm",
+      "model.layers.78.mlp.router.gate",
+      "model.layers.78.mlp.shared_mlp.down_proj",
+      "model.layers.78.mlp.shared_mlp.gate_proj",
+      "model.layers.78.mlp.shared_mlp.up_proj",
+      "model.layers.78.post_attention_layernorm",
+      "model.layers.78.self_attn.k_norm",
+      "model.layers.78.self_attn.k_proj",
+      "model.layers.78.self_attn.o_proj",
+      "model.layers.78.self_attn.q_norm",
+      "model.layers.78.self_attn.q_proj",
+      "model.layers.78.self_attn.v_proj",
+      "model.layers.79.input_layernorm",
+      "model.layers.79.mlp.router.gate",
+      "model.layers.79.mlp.shared_mlp.down_proj",
+      "model.layers.79.mlp.shared_mlp.gate_proj",
+      "model.layers.79.mlp.shared_mlp.up_proj",
+      "model.layers.79.post_attention_layernorm",
+      "model.layers.79.self_attn.k_norm",
+      "model.layers.79.self_attn.k_proj",
+      "model.layers.79.self_attn.o_proj",
+      "model.layers.79.self_attn.q_norm",
+      "model.layers.79.self_attn.q_proj",
+      "model.layers.79.self_attn.v_proj",
+      "model.layers.8.input_layernorm",
+      "model.layers.8.mlp.router.gate",
+      "model.layers.8.mlp.shared_mlp.down_proj",
+      "model.layers.8.mlp.shared_mlp.gate_proj",
+      "model.layers.8.mlp.shared_mlp.up_proj",
+      "model.layers.8.post_attention_layernorm",
+      "model.layers.8.self_attn.k_norm",
+      "model.layers.8.self_attn.k_proj",
+      "model.layers.8.self_attn.o_proj",
+      "model.layers.8.self_attn.q_norm",
+      "model.layers.8.self_attn.q_proj",
+      "model.layers.8.self_attn.v_proj",
+      "model.layers.80.eh_proj",
+      "model.layers.80.enorm",
+      "model.layers.80.final_layernorm",
+      "model.layers.80.hnorm",
+      "model.layers.80.input_layernorm",
+      "model.layers.80.mlp.router.gate",
+      "model.layers.80.mlp.shared_mlp.down_proj",
+      "model.layers.80.mlp.shared_mlp.gate_proj",
+      "model.layers.80.mlp.shared_mlp.up_proj",
+      "model.layers.80.post_attention_layernorm",
+      "model.layers.80.self_attn.k_norm",
+      "model.layers.80.self_attn.k_proj",
+      "model.layers.80.self_attn.o_proj",
+      "model.layers.80.self_attn.q_norm",
+      "model.layers.80.self_attn.q_proj",
+      "model.layers.80.self_attn.v_proj",
+      "model.layers.9.input_layernorm",
+      "model.layers.9.mlp.router.gate",
+      "model.layers.9.mlp.shared_mlp.down_proj",
+      "model.layers.9.mlp.shared_mlp.gate_proj",
+      "model.layers.9.mlp.shared_mlp.up_proj",
+      "model.layers.9.post_attention_layernorm",
+      "model.layers.9.self_attn.k_norm",
+      "model.layers.9.self_attn.k_proj",
+      "model.layers.9.self_attn.o_proj",
+      "model.layers.9.self_attn.q_norm",
+      "model.layers.9.self_attn.q_proj",
+      "model.layers.9.self_attn.v_proj",
+      "model.norm"
+    ]
+  }
+}

model-00001-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46f89b1092fdf93ca64af12b0559e6898d76ce37a0ab86100bdbb34b483af8f0
+size 1925332168

model-00011-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10666221e220d845dda6dfcd526679bc57ef9d0b615e1a4eff9e752076cb5953
+size 1925333320

model-00019-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acecb5cdfc0cd31855168f490707598cd484b3ca04cef677af45bf8e563c8dce
+size 1925332168

model-00030-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9a4c2cec9b58f0bd9b4907596fefd4d8c18808158f8abd4bb7c7d8810491581
+size 1065220848

model-00034-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2d75b9239738fc43b49b1e765ec0add6f3b0a867c1d582d3fc4d5766edbd8f4
+size 1925333320

model-00037-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a2b7276f7223d0eb764b7d7d2862aaab8924192f791cc295c76e7eaf7290c41
+size 1925332168

model-00040-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b84a19be845d98cccf272d2abecf2a72d719f926e168e5b10df8f054505c4c6
+size 1925333320

model-00045-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73306c877c471f133c803cd393e98cc1125791175b40c0b1b2ff8a6c7f018f7e
+size 1925333320

model-00047-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bdd17c179aa8e1b81dda5bc0a809c2717563e3126861ac755a088c132023e907
+size 1925333320

model-00056-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98eaabdcdbb2cff90c55cd60fa0124293bb370cd192aa7a15cb0a91e5caecd57
+size 1925333320

model-00059-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68d00cb457720e87db1ab2ef0684c0c3d35064668dd44969b8f11398f829273f
+size 1925333320

model-00065-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:832233744d355312c814c975a0739753b30f64cd00bf4b32c5a33a19b1768a97
+size 1925333320

model-00066-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53f8091d391170df1df036b4d30573f4d6f034b9817d1a27e84fe6c25c8f772c
+size 1023412968

model-00067-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53954f627283e65a34d582438cf2b678926bbe8f2438f0f71f4db3d49dd54b3f
+size 1925333320

model-00071-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7aa13d3576b8569453054d6ed1f187844a7a3a7c1dc7dbc1c1dea010cace3884
+size 1925333320

model-00073-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c17bd56c95c8351056f46087ff156066df67b9ba474ffcc9c3e8b303ae21d345
+size 1925333320

model-00099-of-00099.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe9bc39636ac0fb248b350b8be9804c96820e5816047402e7f6b65bb94da15a6
+size 822086024