Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,41 @@
+---
+base_model:
+- tsbiosky/gemma-3-27b-it-hok
+- tsbiosky/gemma3_27B_pubg
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# gemma3_merge_linear
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [Linear](https://arxiv.org/abs/2203.05482) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [tsbiosky/gemma-3-27b-it-hok](https://huggingface.co/tsbiosky/gemma-3-27b-it-hok)
+* [tsbiosky/gemma3_27B_pubg](https://huggingface.co/tsbiosky/gemma3_27B_pubg)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: tsbiosky/gemma3_27B_pubg
+    parameters:
+      weight: 0.5
+  - model: tsbiosky/gemma-3-27b-it-hok
+    parameters:
+      weight: 0.5
+merge_method: linear
+dtype: float16
+
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "<image_soft_token>": 262144
+}

config.json

@@ -0,0 +1,37 @@
+{
+  "architectures": [
+    "Gemma3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "attn_logit_softcapping": null,
+  "bos_token_id": 2,
+  "cache_implementation": "hybrid",
+  "eos_token_id": 1,
+  "final_logit_softcapping": null,
+  "head_dim": 128,
+  "hidden_activation": "gelu_pytorch_tanh",
+  "hidden_size": 5376,
+  "initializer_range": 0.02,
+  "intermediate_size": 21504,
+  "max_position_embeddings": 131072,
+  "model_type": "gemma3_text",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 16,
+  "pad_token_id": 0,
+  "query_pre_attn_scalar": 168,
+  "rms_norm_eps": 1e-06,
+  "rope_local_base_freq": 10000.0,
+  "rope_scaling": {
+    "factor": 8.0,
+    "rope_type": "linear"
+  },
+  "rope_theta": 1000000.0,
+  "sliding_window": 1024,
+  "sliding_window_pattern": 6,
+  "torch_dtype": "float16",
+  "transformers_version": "4.50.3",
+  "use_cache": false,
+  "vocab_size": 262208
+}

mergekit_config.yml

@@ -0,0 +1,9 @@
+models:
+  - model: tsbiosky/gemma3_27B_pubg
+    parameters:
+      weight: 0.5
+  - model: tsbiosky/gemma-3-27b-it-hok
+    parameters:
+      weight: 0.5
+merge_method: linear
+dtype: float16

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef2d35e3f1d5de764564115ea4d575d0794b2be6d1ed0c9b4006633adfa0a002
+size 4933290896

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:960b8091951ebc8e7028bfbceb890418da5c03891a9862cde66f47adfc3110b2
+size 4954791768

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:368726d798962fab6855ea441bc685bc34c1b2f6f47afd2f9eb763f2169beed6
+size 4954791760

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6ecd6847bb7d4322f62300fac0646587d8cf981f52b74fdeb2e360f4fb5e94c
+size 4954791768

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06cd4e4859e555cc9f70c6630d04e0a29f4b75d76d9662a43309cae790069ee8
+size 4954791760

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9daa2b76c98e5e6deb367b5115b76f70af4999a43a5aa973730070ad7d26013
+size 4954791768

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f89fcdfee33c5620ba034c545b56671308caa8b2d784a541285790d449c8b6f
+size 4954791760

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ef3b6317fe2dd64d4c5fa57e648362c632b08b14e62a8d82b1d28297f0e14f7
+size 4954791768

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aca6e71329d06c336d59f6b7d6be839aea1a8a073105785895a9ce511366e294
+size 4954791760

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8110876f6a8393f8404bbee5497948c4a30430d0111b0a02056bd4c400aa64d5
+size 4954791768

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a672192899b3e0910701683d0ae57ba1da4fd47a3453bded641fb18d2f48b05b
+size 4492369456

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_feedforward_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.pre_feedforward_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_feedforward_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.pre_feedforward_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.10.post_feedforward_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.10.pre_feedforward_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.11.post_feedforward_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.11.pre_feedforward_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.post_feedforward_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.pre_feedforward_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.post_feedforward_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.pre_feedforward_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.post_feedforward_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.pre_feedforward_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.15.post_feedforward_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.15.pre_feedforward_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.16.post_feedforward_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.16.pre_feedforward_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.k_norm.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.q_norm.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.post_feedforward_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.pre_feedforward_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.k_norm.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.q_norm.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.post_feedforward_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.pre_feedforward_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.k_norm.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.q_norm.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.19.post_feedforward_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.19.pre_feedforward_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.k_norm.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.q_norm.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.post_feedforward_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.pre_feedforward_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.k_norm.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.q_norm.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.20.post_feedforward_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.20.pre_feedforward_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.20.self_attn.k_norm.weight": "model-00003-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.20.self_attn.q_norm.weight": "model-00003-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.21.post_feedforward_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.21.pre_feedforward_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.k_norm.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.q_norm.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.22.post_feedforward_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.22.pre_feedforward_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.k_norm.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.q_norm.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.23.post_feedforward_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.23.pre_feedforward_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.k_norm.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.q_norm.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.24.post_feedforward_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.24.pre_feedforward_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.24.self_attn.k_norm.weight": "model-00004-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.self_attn.q_norm.weight": "model-00004-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.25.post_feedforward_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.25.pre_feedforward_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.k_norm.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.q_norm.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.26.post_feedforward_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.26.pre_feedforward_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.k_norm.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.q_norm.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.27.post_feedforward_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.27.pre_feedforward_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.27.self_attn.k_norm.weight": "model-00005-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.27.self_attn.q_norm.weight": "model-00005-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.28.post_feedforward_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.28.pre_feedforward_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.k_norm.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.q_norm.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.29.post_feedforward_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.29.pre_feedforward_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.k_norm.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.q_norm.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.3.post_feedforward_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.3.pre_feedforward_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.3.self_attn.k_norm.weight": "model-00005-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.3.self_attn.q_norm.weight": "model-00005-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.30.post_feedforward_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.30.pre_feedforward_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.k_norm.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.q_norm.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.31.post_feedforward_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.31.pre_feedforward_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.k_norm.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.q_norm.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.32.post_feedforward_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.32.pre_feedforward_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.32.self_attn.k_norm.weight": "model-00006-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.32.self_attn.q_norm.weight": "model-00006-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.33.post_feedforward_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.33.pre_feedforward_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.33.self_attn.k_norm.weight": "model-00006-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.33.self_attn.q_norm.weight": "model-00006-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.34.post_feedforward_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.34.pre_feedforward_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.34.self_attn.k_norm.weight": "model-00006-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.self_attn.q_norm.weight": "model-00006-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.35.post_feedforward_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.35.pre_feedforward_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.35.self_attn.k_norm.weight": "model-00006-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.self_attn.q_norm.weight": "model-00006-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.36.post_feedforward_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.36.pre_feedforward_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.36.self_attn.k_norm.weight": "model-00006-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.self_attn.q_norm.weight": "model-00006-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.37.post_feedforward_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.37.pre_feedforward_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.37.self_attn.k_norm.weight": "model-00006-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.37.self_attn.q_norm.weight": "model-00006-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.38.post_feedforward_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.38.pre_feedforward_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.38.self_attn.k_norm.weight": "model-00007-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.38.self_attn.q_norm.weight": "model-00007-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.39.post_feedforward_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.39.pre_feedforward_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.39.self_attn.k_norm.weight": "model-00007-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.39.self_attn.q_norm.weight": "model-00007-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.4.post_feedforward_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.4.pre_feedforward_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.4.self_attn.k_norm.weight": "model-00007-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.4.self_attn.q_norm.weight": "model-00007-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.40.post_feedforward_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.40.pre_feedforward_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.40.self_attn.k_norm.weight": "model-00007-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.self_attn.q_norm.weight": "model-00007-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.41.post_feedforward_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.41.pre_feedforward_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.41.self_attn.k_norm.weight": "model-00007-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.self_attn.q_norm.weight": "model-00007-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.42.post_feedforward_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.42.pre_feedforward_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.k_norm.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.q_norm.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.43.post_feedforward_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.43.pre_feedforward_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.43.self_attn.k_norm.weight": "model-00008-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.43.self_attn.q_norm.weight": "model-00008-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.44.post_feedforward_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.44.pre_feedforward_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.44.self_attn.k_norm.weight": "model-00008-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.44.self_attn.q_norm.weight": "model-00008-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.45.post_feedforward_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.45.pre_feedforward_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.k_norm.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.q_norm.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.46.post_feedforward_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.46.pre_feedforward_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.46.self_attn.k_norm.weight": "model-00008-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.self_attn.q_norm.weight": "model-00008-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.47.post_feedforward_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.47.pre_feedforward_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.47.self_attn.k_norm.weight": "model-00008-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.47.self_attn.q_norm.weight": "model-00008-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.48.post_feedforward_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.48.pre_feedforward_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.48.self_attn.k_norm.weight": "model-00008-of-00011.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.self_attn.q_norm.weight": "model-00008-of-00011.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.49.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.49.post_feedforward_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.49.pre_feedforward_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.49.self_attn.k_norm.weight": "model-00009-of-00011.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.49.self_attn.q_norm.weight": "model-00009-of-00011.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.5.post_feedforward_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.5.pre_feedforward_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.5.self_attn.k_norm.weight": "model-00009-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.5.self_attn.q_norm.weight": "model-00009-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.50.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.50.post_feedforward_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.50.pre_feedforward_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.50.self_attn.k_norm.weight": "model-00009-of-00011.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.50.self_attn.q_norm.weight": "model-00009-of-00011.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.51.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.51.post_feedforward_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.51.pre_feedforward_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.51.self_attn.k_norm.weight": "model-00009-of-00011.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.51.self_attn.q_norm.weight": "model-00009-of-00011.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.52.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.52.post_feedforward_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.52.pre_feedforward_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.52.self_attn.k_norm.weight": "model-00009-of-00011.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.52.self_attn.q_norm.weight": "model-00009-of-00011.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.53.post_feedforward_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.53.pre_feedforward_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.53.self_attn.k_norm.weight": "model-00009-of-00011.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.self_attn.q_norm.weight": "model-00009-of-00011.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.54.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.54.post_feedforward_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.54.pre_feedforward_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.54.self_attn.k_norm.weight": "model-00010-of-00011.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.54.self_attn.q_norm.weight": "model-00010-of-00011.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.55.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.55.post_feedforward_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.55.pre_feedforward_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.55.self_attn.k_norm.weight": "model-00010-of-00011.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.55.self_attn.q_norm.weight": "model-00010-of-00011.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.56.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.56.post_feedforward_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.56.pre_feedforward_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.56.self_attn.k_norm.weight": "model-00010-of-00011.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.56.self_attn.q_norm.weight": "model-00010-of-00011.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.57.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.57.post_feedforward_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.57.pre_feedforward_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.57.self_attn.k_norm.weight": "model-00010-of-00011.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.57.self_attn.q_norm.weight": "model-00010-of-00011.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.58.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.58.post_feedforward_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.58.pre_feedforward_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.58.self_attn.k_norm.weight": "model-00010-of-00011.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.58.self_attn.q_norm.weight": "model-00010-of-00011.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.59.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.59.post_feedforward_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.59.pre_feedforward_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.59.self_attn.k_norm.weight": "model-00010-of-00011.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.59.self_attn.q_norm.weight": "model-00010-of-00011.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.6.post_feedforward_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.6.pre_feedforward_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.6.self_attn.k_norm.weight": "model-00011-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.6.self_attn.q_norm.weight": "model-00011-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.60.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.60.post_feedforward_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.60.pre_feedforward_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.60.self_attn.k_norm.weight": "model-00011-of-00011.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.60.self_attn.q_norm.weight": "model-00011-of-00011.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.61.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.61.post_feedforward_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.61.pre_feedforward_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.61.self_attn.k_norm.weight": "model-00011-of-00011.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.61.self_attn.q_norm.weight": "model-00011-of-00011.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.7.post_feedforward_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.7.pre_feedforward_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.7.self_attn.k_norm.weight": "model-00011-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.self_attn.q_norm.weight": "model-00011-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.8.post_feedforward_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.8.pre_feedforward_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.k_norm.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.q_norm.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.post_feedforward_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.pre_feedforward_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.k_norm.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.q_norm.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "boi_token": "<start_of_image>",
+  "bos_token": {
+    "content": "<bos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eoi_token": "<end_of_image>",
+  "eos_token": {
+    "content": "<eos>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "image_token": "<image_soft_token>",
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4667f2089529e8e7657cfb6d1c19910ae71ff5f28aa7ab2ff2763330affad795
+size 33384568

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1299c11d7cf632ef3b4e11937501358ada021bbdf7c47638d13c0ee982f2e79c
+size 4689074