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:
+- Delta-Vector/Rei-V1-32B-Base
+- allura-org/GLM4-32B-Neon-v2
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# glm-merge-0-2
+
+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 [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Delta-Vector/Rei-V1-32B-Base](https://huggingface.co/Delta-Vector/Rei-V1-32B-Base)
+* [allura-org/GLM4-32B-Neon-v2](https://huggingface.co/allura-org/GLM4-32B-Neon-v2)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: allura-org/GLM4-32B-Neon-v2
+  - model: Delta-Vector/Rei-V1-32B-Base
+merge_method: slerp
+base_model: allura-org/GLM4-32B-Neon-v2
+parameters:
+  t:
+   - value: 0.2
+dtype: bfloat16
+tokenizer_source: base
+```

chat_template.jinja

@@ -0,0 +1,4 @@
+[gMASK]<sop>{%- for msg in messages %}{%- if msg.role == 'system' %}<|system|>
+{{ msg.content }}{%- elif msg.role == 'user' %}<|user|>
+{{ msg.content }}{%- elif msg.role == 'assistant' %}<|assistant|>
+{{ msg.content }}{%- endif %}{%- endfor %}{% if add_generation_prompt %}<|assistant|>{% endif %}

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Glm4ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "eos_token_id": 151336,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 6144,
+  "initializer_range": 0.02,
+  "intermediate_size": 23040,
+  "max_position_embeddings": 32768,
+  "model_type": "glm4",
+  "num_attention_heads": 48,
+  "num_hidden_layers": 61,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151329,
+  "partial_rotary_factor": 0.5,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.3",
+  "use_cache": true,
+  "vocab_size": 151343
+}

mergekit_config.yml

@@ -0,0 +1,10 @@
+models:
+  - model: allura-org/GLM4-32B-Neon-v2
+  - model: Delta-Vector/Rei-V1-32B-Base
+merge_method: slerp
+base_model: allura-org/GLM4-32B-Neon-v2
+parameters:
+  t:
+   - value: 0.2
+dtype: bfloat16
+tokenizer_source: base

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce055f4ddf194c3efc4b00b5cc6c32c319604e4c35d49e19f095dd2ea3c80977
+size 4726101480

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:504f93f4545569da3483eac9accbf5200aeb0e4e142ec5a11b55387b96ae6655
+size 4954760608

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:584ad2287656304d342c2993c8f2a924ad64f4b80fe52dcb2902d7d7ae183f32
+size 4957918848

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e77699ec992be2c43a04482ff98773634455ed7b707769675d66f3f0d15c9e4c
+size 4464002216

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c9c941df1db4ed424806c72c73028e3d76bdc196235868beb62b4501bc982b4
+size 4750300808

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:717e4348f0cb9c9a28d8b7055054b3246c48253414d3840625b239ae3970955d
+size 4954760608

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd611a208f263b55589f18a35061e9a4f9842cc1d7eb5f97fefa15470af95976
+size 4957918848

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4fea3c15bcc36d94ccf6b0ff2a7c87959b01f8259bcdbfeb9cd13ee1035fdf1
+size 4464002224

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0fd2e4cc1f12439aab25d2609c2537d96ef44e32b75a7e562508719201cf7d33
+size 4750300800

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25de5a7e2695e2e3d2658a0ada4c5614466012e0773a45f3b9b0868f093e3d35
+size 4954760616

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51139280ffc422405286d0f4053d33f0eaa7f798dcc291426d3353535972dac1
+size 4957918840

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b01688ea8c1198ae4a3b5f00b226e368face83451376a38891fec0dea8a5d7a
+size 4464002224

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02e3e90b72931a3fce983147dc6807f88dd2add5f7a8cb3b6f172ee4e15742bf
+size 4750300800

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b95e570622d294257d553ecf00ad8bb4203162053c578e0e68419f7dc5bce94
+size 3020049832

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"lm_head.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00001-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_mlp_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.post_self_attn_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.post_mlp_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.post_self_attn_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.mlp.gate_up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.post_mlp_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.post_self_attn_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.19.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.19.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.mlp.gate_up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.post_mlp_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.post_self_attn_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.22.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.22.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.22.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.mlp.gate_up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.post_mlp_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.post_self_attn_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.27.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.27.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.mlp.gate_up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.post_mlp_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.post_self_attn_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.31.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.31.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.mlp.gate_up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.35.post_mlp_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.35.post_self_attn_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.36.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.36.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.mlp.gate_up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.39.post_mlp_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.39.post_self_attn_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.4.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.4.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.4.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.40.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.40.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.41.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.41.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.42.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.42.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.mlp.gate_up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.43.post_mlp_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.43.post_self_attn_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.44.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.44.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.44.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.45.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.45.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.46.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.46.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.47.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.47.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.mlp.gate_up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.post_mlp_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.post_self_attn_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.49.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.49.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.5.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.5.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.50.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.50.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.51.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.51.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.mlp.gate_up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.post_mlp_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.post_self_attn_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.53.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.53.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.54.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.54.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.mlp.gate_up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.56.post_mlp_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.56.post_self_attn_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.57.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.57.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.57.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.58.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.58.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.59.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.59.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.mlp.gate_up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.60.post_mlp_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.60.post_self_attn_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.mlp.gate_up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.7.post_mlp_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.7.post_self_attn_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.mlp.gate_up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_mlp_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.post_self_attn_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.mlp.gate_up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_mlp_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_self_attn_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00014.safetensors", "model.norm.weight": "model-00014-of-00014.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,32 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "eos_token": {
+    "content": "<|user|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76ebeac0d8bd7879ead7b43c16b44981f277e47225de2bd7de9ae1a6cc664a8c
+size 19966496

tokenizer_config.json

@@ -0,0 +1,145 @@
+{
+  "added_tokens_decoder": {
+    "151329": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151330": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151331": {
+      "content": "[gMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151332": {
+      "content": "[sMASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151333": {
+      "content": "<sop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151334": {
+      "content": "<eop>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151335": {
+      "content": "<|system|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151336": {
+      "content": "<|user|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151337": {
+      "content": "<|assistant|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151338": {
+      "content": "<|observation|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151339": {
+      "content": "<|begin_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151340": {
+      "content": "<|end_of_image|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151341": {
+      "content": "<|begin_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151342": {
+      "content": "<|end_of_video|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "[MASK]",
+    "[gMASK]",
+    "[sMASK]",
+    "<sop>",
+    "<eop>",
+    "<|system|>",
+    "<|user|>",
+    "<|assistant|>",
+    "<|observation|>",
+    "<|begin_of_image|>",
+    "<|end_of_image|>",
+    "<|begin_of_video|>",
+    "<|end_of_video|>"
+  ],
+  "clean_up_tokenization_spaces": false,
+  "do_lower_case": false,
+  "eos_token": "<|user|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 128000,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "remove_space": false,
+  "tokenizer_class": "PreTrainedTokenizer"
+}