Upload folder using huggingface_hub

config.json

@@ -3,33 +3,8 @@
   "architectures": [
     "LlavaQwenForCausalLM"
   ],
-  "auto_map": {
-    "AutoConfig": "configuration_videoxlpro_llavaqwen.LlavaQwenConfig",
-    "AutoModelForCausalLM": "modeling_videoxlpro_llavaqwen.LlavaQwenForCausalLM"
-  },
   "attention_dropout": 0.0,
-  "beacon_accum": true,
-  "beacon_attend_prev": true,
-  "beacon_attn": "full-coverage",
-  "beacon_embed_init": "eos",
-  "beacon_parallel_window": 1,
-  "beacon_param": [
-    "q",
-    "k",
-    "v"
-  ],
-  "beacon_pos": "interleave",
-  "beacon_ratio": [
-    2,
-    4,
-    8
-  ],
-  "beacon_ratio_mix": "step-random",
-  "beacon_sink_size": 0,
-  "beacon_stride": 1440,
-  "beacon_window": 1440,
   "bos_token_id": 151643,
-  "enable_beacon": true,
   "eos_token_id": 151645,
   "freeze_mm_mlp_adapter": false,
   "freeze_mm_vision_resampler": false,
@@ -856,9 +831,9 @@
   "mm_use_im_start_end": false,
   "mm_vision_select_feature": "patch",
   "mm_vision_select_layer": -1,
-  "mm_vision_tower": "/share/LXRlxr0_0/code/videoxlturbo2.0/videoxl_adaptfps/google/siglip-so400m-patch14-384",
+  "mm_vision_tower": "/share/LXRlxr0_0/code/videoxlturbo2.0/videoxl/google/siglip-so400m-patch14-384",
   "mm_vision_tower_lr": null,
-  "model_type": "videoxlpro_llavaqwen",
+  "model_type": "qwen2",
   "num_attention_heads": 16,
   "num_hidden_layers": 36,
   "num_key_value_heads": 2,

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:482a5114f34c14d352dc9765e39c755cd3c27bd8efc4bc42886c8fdd699a5543
-size 4977615904
+oid sha256:678a5abca2f57d59d6c1e36ed6c54aceda35d61ee48ab12953d5fc1c2a54eeba
+size 4957560304

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7e8e43de53317dbe90e98a2e51554edc1cb4cdfbbf0d7f00a59f011e56f1438
-size 3198470440
+oid sha256:fe75fe3e0e44562dfff89ee6b0fbeef9116c5cfed11d9a9aac79b8e3ff30fb4b
+size 2874395936

model.safetensors.index.json

@@ -1,22 +1,23 @@
 {
   "metadata": {
-    "total_size": 8175939136
+    "total_size": 7831834176
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
-    "model.beacon_embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.WindowTimeToTokenAttention.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.WindowTimeToTokenAttention.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.WindowTimeToTokenAttention.out_proj.bias": "model-00002-of-00002.safetensors",
+    "model.WindowTimeToTokenAttention.out_proj.weight": "model-00002-of-00002.safetensors",
+    "model.WindowTimeToTokenAttention.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.WindowTimeToTokenAttention.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.WindowTimeToTokenAttention.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.WindowTimeToTokenAttention.v_proj.weight": "model-00002-of-00002.safetensors",
     "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.0.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -29,12 +30,6 @@
     "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.1.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -47,12 +42,6 @@
     "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.10.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -65,12 +54,6 @@
     "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.11.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -83,12 +66,6 @@
     "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.12.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -101,12 +78,6 @@
     "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.13.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -119,12 +90,6 @@
     "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.14.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -137,12 +102,6 @@
     "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.15.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -155,12 +114,6 @@
     "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.16.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -173,12 +126,6 @@
     "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.17.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -191,12 +138,6 @@
     "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.18.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -209,12 +150,6 @@
     "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.19.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -227,12 +162,6 @@
     "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.2.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -245,12 +174,6 @@
     "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.20.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -263,12 +186,6 @@
     "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.21.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -281,12 +198,6 @@
     "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.22.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -299,12 +210,6 @@
     "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.23.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -317,12 +222,6 @@
     "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.24.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -335,12 +234,6 @@
     "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.25.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -348,17 +241,11 @@
     "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.26.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.26.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -366,53 +253,35 @@
     "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.beacon_k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.beacon_k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.beacon_q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.beacon_q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.beacon_v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.beacon_v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.beacon_k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.beacon_k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.beacon_q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.beacon_q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.beacon_v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.beacon_v_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.beacon_k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.beacon_k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.beacon_q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.beacon_q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.beacon_v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.29.self_attn.beacon_v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
@@ -425,12 +294,6 @@
     "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.3.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -443,12 +306,6 @@
     "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.beacon_k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.beacon_k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.beacon_q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.beacon_q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.beacon_v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.30.self_attn.beacon_v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
@@ -461,12 +318,6 @@
     "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.beacon_k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.beacon_k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.beacon_q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.beacon_q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.beacon_v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.31.self_attn.beacon_v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
@@ -479,12 +330,6 @@
     "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.beacon_k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.beacon_k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.beacon_q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.beacon_q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.beacon_v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.32.self_attn.beacon_v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
@@ -497,12 +342,6 @@
     "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.beacon_k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.beacon_k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.beacon_q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.beacon_q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.beacon_v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.33.self_attn.beacon_v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
@@ -515,12 +354,6 @@
     "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.beacon_k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.beacon_k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.beacon_q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.beacon_q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.beacon_v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.34.self_attn.beacon_v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
@@ -533,12 +366,6 @@
     "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.beacon_k_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.beacon_k_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.beacon_q_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.beacon_q_proj.weight": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.beacon_v_proj.bias": "model-00002-of-00002.safetensors",
-    "model.layers.35.self_attn.beacon_v_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
     "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
@@ -551,12 +378,6 @@
     "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.4.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -569,12 +390,6 @@
     "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.5.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -587,12 +402,6 @@
     "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.6.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -605,12 +414,6 @@
     "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.7.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -623,12 +426,6 @@
     "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.8.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
@@ -641,12 +438,6 @@
     "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.beacon_k_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.beacon_k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.beacon_q_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.beacon_q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.beacon_v_proj.bias": "model-00001-of-00002.safetensors",
-    "model.layers.9.self_attn.beacon_v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75fdc26965f066ea3a3653fe2cb89637260eb67c664cc2a8c6fae40eeaa9fbc6
-size 7352
+oid sha256:939d3d6f7c4ae761cb267c01fbc875c1fe3832a72f3e48bb4c48c4a242289d59
+size 7160