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 +1,47 @@
+---
+base_model:
+- inflatebot/MN-12B-Mag-Mell-R1
+- ChaoticNeutrals/Captain-Eris_Twilight-V0.420-12B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# outs
+
+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:
+* [inflatebot/MN-12B-Mag-Mell-R1](https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1)
+* [ChaoticNeutrals/Captain-Eris_Twilight-V0.420-12B](https://huggingface.co/ChaoticNeutrals/Captain-Eris_Twilight-V0.420-12B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources:
+      - model: ChaoticNeutrals/Captain-Eris_Twilight-V0.420-12B
+        layer_range: [0, 40]
+      - model: inflatebot/MN-12B-Mag-Mell-R1
+        layer_range: [0, 40]
+merge_method: slerp
+base_model: ChaoticNeutrals/Captain-Eris_Twilight-V0.420-12B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.3
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "ChaoticNeutrals/Captain-Eris_Twilight-V0.420-12B",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,16 @@
+slices:
+  - sources:
+      - model: ChaoticNeutrals/Captain-Eris_Twilight-V0.420-12B
+        layer_range: [0, 40]
+      - model: inflatebot/MN-12B-Mag-Mell-R1
+        layer_range: [0, 40]
+merge_method: slerp
+base_model: ChaoticNeutrals/Captain-Eris_Twilight-V0.420-12B
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.5, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.5, 0.7, 0.3, 0]
+    - value: 0.3
+dtype: bfloat16

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:53413802e48904cb256ed80842663f3c636d27bdd39b6f82186045c1db557055
+size 1342177408

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3c633fbd6f80e52618b1aa67f61befd8376eaf2fa429d9ca261755bace579f9
+size 1887468816

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a130c623700efa6178abb204f5302ba05df3b6c4e46ae049b216d8c888fcf098
+size 1929444664

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f52af934eef92ea466d5076af633156c26d2bd584e490d639bdfc9528f774e6c
+size 1887522696

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc1948fcd6982056357d2045d489a73dbeb0da41036941300d0e44af645fd4b2
+size 1929444672

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:758f7fa90749c71b5fe2f8c459d6483a538538434b37b5205a7510cf84a19030
+size 1887522680

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a8a31aaa81c39babc10463c5ed1a833744f0c1e538615a52c342e4b785b210
+size 1929444672

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af03ecd31b9f9d35f879053864fc810f4731e8d615e2c7a2555ed5dfa253bacc
+size 1887522696

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69cc6408ead4a61550dcd7ce4e1541e62c8f7362456d60461a46a509ef8cc2f1
+size 1929444664

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7afd4d6598882e6408756c1631ccf2ae48ecdc9f129ac44b4a386644999dce21
+size 1887522696

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f48b885e7f6b9a13cd99385948cd2d19c7e9f99212d2014cb8dfe1fb40505f0
+size 1929444672

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5aad4128625f218edc0de058ca694578eacb3e31fc3e5e37a8e1c453affe1f5
+size 1887522672

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9f82f732e2fc86c4c4dc16747e8638d0977e0f66e506e9f738c1732cf4c9ef8
+size 1929444640

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced035c84f49919b3e9c1dea6e789c91230d301dfb48705e8b3bbe3ff9a35dc5
+size 251679536

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.0"}, "weight_map": {"lm_head.weight": "model-00001-of-00014.safetensors", "model.embed_tokens.weight": "model-00002-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.6.post_attention_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.7.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.9.post_attention_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 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "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:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292