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 +1,38 @@
+---
+base_model:
+- yamatazen/ForgottenMaid-12B
+- yamatazen/LinearWriter-12B
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# EsotericSage-12B
+
+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 [NearSwap](https://huggingface.co/alchemonaut/QuartetAnemoi-70B-t0.0001) merge method using [yamatazen/LinearWriter-12B](https://huggingface.co/yamatazen/LinearWriter-12B) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [yamatazen/ForgottenMaid-12B](https://huggingface.co/yamatazen/ForgottenMaid-12B)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+merge_method: nearswap
+dtype: bfloat16
+out_dtype: bfloat16
+base_model: yamatazen/LinearWriter-12B
+models:
+  - model: yamatazen/ForgottenMaid-12B
+parameters:
+  t: [0.0001, 0.0003, 0.0005, 0.0003, 0.0001]
+```

config.json

@@ -0,0 +1,26 @@
+{
+  "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": 131072,
+  "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": "4.51.3",
+  "use_cache": false,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,8 @@
+merge_method: nearswap
+dtype: bfloat16
+out_dtype: bfloat16
+base_model: yamatazen/LinearWriter-12B
+models:
+  - model: yamatazen/ForgottenMaid-12B
+parameters:
+  t: [0.0001, 0.0003, 0.0005, 0.0003, 0.0001]

model-00001-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d2167f73fd468ae9882795aca42762bd97ee0f711e22a97337be669259d36dda
+size 1342177408

model-00002-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3db119cc4cd6f619ea75ed4086b85a66a69cdb11f758c20616991393ab79fe4
+size 1342177424

model-00003-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da2b70699ad4384dccc85eca42cd576323b4dc6a2bd12e37dfe3541ac79b9be6
+size 996189888

model-00004-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:275333f2fcb0f94598ac61d3160a5add9b4837ced246d69b06c931cc7a62b30c
+size 933265104

model-00005-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47605f5e02c6d51979b593154b7c2f90b4a04dbe5f381af696eec03e1776c35b
+size 943761344

model-00006-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5caed8c79244f5a21291a721a71dff4fe481696a5564fe565cc4e526e6fa19b6
+size 943761344

model-00007-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95c51411e2118b0a4ede5a260588a79204b934d4336848e5ba73ee6a8c913b16
+size 996179560

model-00008-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbae90b614a35b412046cd9bef7371d8f1cddf834f3e13d2c696e6d0232a078e
+size 933265104

model-00009-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2fca976a3a40c80c5edfcf8e5d60b41964e60b5b0cf25b432315c59e95bb32a0
+size 943761344

model-00010-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8014ca5fbc7c0c1f3b6e7667b72e12876c5f0cefc2228dd2a6684d4460b10b6
+size 943761344

model-00011-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22d58db13412080a60004d12a935f9c16c336e59e86ac5d4b1b7fbb33faecd4c
+size 996179560

model-00012-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c45cb87aa866c33ee8cb27d6ee9a51c25e4d828714859939ced37176dd92c3d6
+size 933265104

model-00013-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13dfd8c07ea3cc6fc2b2e9dfe227b3ed7ca52acc259b2422fa211799c5f5e6d1
+size 943761344

model-00014-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01dd9d09e3f595b9c5b3fa3f4dc03045b4510e9c90e745ab2ec038167a6ba382
+size 943761344

model-00015-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7461d49feee79147f501414aa80a4a389e9bc2b94354721585715c98a88b8dff
+size 996179560

model-00016-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4b4365b0b510f0b16bbadce5860deaceb2c264ce8eed65c469988a0c5d93045c
+size 933265096

model-00017-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d8ae53a1e784416f7e694a2cfadc5200758bf4799d819e74f1305bd7ab027c3
+size 943761344

model-00018-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff525d115a50219c512ff03a73583cfe29cc0bef3398e883f5bd27c9fc70a6e6
+size 943761344

model-00019-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fd77a391907490ac4d6ab788714efdb8f8f7d5145b80ed3446d81e3ac6de667
+size 996179560

model-00020-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:498b5128faa2febe04b47815de64ba62a28316ececa80d45bfeebc31c33ed0cc
+size 933265104

model-00021-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dec2bdb43e1b3f8a4c517233cfe248ed539bd119a90bef30edd36c2eb4211c83
+size 943761344

model-00022-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c992720a03963db1778142bef72bdbca6ed241b71e127f21f3b31e78f87c59fb
+size 943761336

model-00023-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbb8a0df6f08fdae52d08e28918fc6b08335bd7d03d6da0992564b31fd99a04a
+size 996179552

model-00024-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5ee7592c7208883dcc9a7ba75432ecaa6b85705a69a2b4fe1f329c556375b4
+size 933265088

model-00025-of-00025.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3c0a871b677c3c091c83c482db468d15a1ed97b36dfa2b23e5788f2a5aaf4e66
+size 796960560

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.1.2"}, "weight_map": {"lm_head.weight": "model-00001-of-00025.safetensors", "model.embed_tokens.weight": "model-00002-of-00025.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00025.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00025.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00025.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00025.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00025.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00025.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00025.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00025.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00025.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00025.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00025.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00025.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00025.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.input_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00025.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00025.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00025.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00025.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00025.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00025.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00025.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00009-of-00025.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00009-of-00025.safetensors", "model.layers.2.input_layernorm.weight": "model-00009-of-00025.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00009-of-00025.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00025.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00025.safetensors", "model.layers.21.input_layernorm.weight": "model-00010-of-00025.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00025.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.input_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00025.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00025.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00012-of-00025.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00012-of-00025.safetensors", "model.layers.24.input_layernorm.weight": "model-00012-of-00025.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00012-of-00025.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00025.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00013-of-00025.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00025.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00025.safetensors", "model.layers.26.input_layernorm.weight": "model-00013-of-00025.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00013-of-00025.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00014-of-00025.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00014-of-00025.safetensors", "model.layers.28.input_layernorm.weight": "model-00014-of-00025.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00015-of-00025.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.input_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00015-of-00025.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00015-of-00025.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00016-of-00025.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00016-of-00025.safetensors", "model.layers.30.input_layernorm.weight": "model-00016-of-00025.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00016-of-00025.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00016-of-00025.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00017-of-00025.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00017-of-00025.safetensors", "model.layers.32.input_layernorm.weight": "model-00017-of-00025.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00017-of-00025.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00025.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00018-of-00025.safetensors", "model.layers.34.input_layernorm.weight": "model-00018-of-00025.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00019-of-00025.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.input_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00019-of-00025.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00019-of-00025.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00020-of-00025.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00020-of-00025.safetensors", "model.layers.37.input_layernorm.weight": "model-00020-of-00025.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00020-of-00025.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00020-of-00025.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00021-of-00025.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00021-of-00025.safetensors", "model.layers.39.input_layernorm.weight": "model-00021-of-00025.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00021-of-00025.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00022-of-00025.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00022-of-00025.safetensors", "model.layers.5.input_layernorm.weight": "model-00022-of-00025.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00023-of-00025.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.input_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00023-of-00025.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00023-of-00025.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00024-of-00025.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.input_layernorm.weight": "model-00024-of-00025.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00024-of-00025.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00025-of-00025.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00025-of-00025.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00025-of-00025.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.input_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00025-of-00025.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00025-of-00025.safetensors", "model.norm.weight": "model-00025-of-00025.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0240ce510f08e6c2041724e9043e33be9d251d1e4a4d94eb68cd47b954b61d2
+size 17078292