Upload 16 files

.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 +1,36 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# Violet-Lyra-Gutenberg-v3-12b
+
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: Chronos-Gold-12B-1.0
+    parameters:
+      weight: 0.4
+      density: 0.4
+  - model: Violet-Lyra-Gutenberg-12b
+    parameters:
+      weight: 0.9
+      density: 0.6
+base_model: Mistral-Nemo-Base-2407
+parameters:
+  epsilon: 0.1
+  lambda: 1.1
+  normalize: false
+  rescale: true
+merge_method: della_linear
+tokenizer:
+  source: union
+dtype: bfloat16
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "Violet-Lyra-Gutenberg-v3",
+  "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": "4.45.1",
+  "use_cache": true,
+  "vocab_size": 131074
+}

mergekit_config.yml

@@ -0,0 +1,19 @@
+models:
+  - model: Chronos-Gold-12B-1.0
+    parameters:
+      weight: 0.4
+      density: 0.4
+  - model: Violet-Lyra-Gutenberg-12b
+    parameters:
+      weight: 0.9
+      density: 0.6
+base_model: Mistral-Nemo-Base-2407
+parameters:
+  epsilon: 0.1
+  lambda: 1.1
+  normalize: false
+  rescale: true
+merge_method: della_linear
+tokenizer:
+  source: union
+dtype: bfloat16

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99004f9381dbc4e2503619c26d09032ebf7434aeb4a2a0070c34641d07167660
+size 2978007616

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d19d06cbeaf38327ac762790afab634463d5017fe616b72786dee0e255b8f4df
+size 2978084776

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:434ffeeae98c75a46450dcee0719a053f9e85fa239d5dc8b03527534f372d168
+size 2873206016

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc895d5ddfac2142c2d5386b962be69a00982e92b7c5c06666750c85c872a2af
+size 2873206000

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6077506f3f9f5bd240bfe789c003149a9c8608fd2f224128853689d9161599f5
+size 2978084792

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9a67528fc53c58d37629632a761096e3639ba2c219984425424fdaabf3489f9
+size 2873206008

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1bab6e6c7d649feaf1bc442fe624c0a134d53265c5053ac74a345bfe09e4b45d
+size 2873206008

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e573afc9e1934811cc000f409ffb0de1439ee3a1fdb58d7e8bc59541a6ad5904
+size 2978084760

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b005d3f4e9491eceb28140692fd19df57eb754310d09ff4953da2dd09e52ae29
+size 1090562072

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.2", "total_size": 24495605760}, "weight_map": {"lm_head.weight": "model-00001-of-00009.safetensors", "model.embed_tokens.weight": "model-00001-of-00009.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00009.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00009.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00009.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00009.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00009.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00009.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00009.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00009.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00009.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00009.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00009.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00006-of-00009.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00007-of-00009.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.input_layernorm.weight": "model-00007-of-00009.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00009.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00009.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00009.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00009.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00009-of-00009.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00009-of-00009.safetensors", "model.norm.weight": "model-00009-of-00009.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 sha256:48130f8c042761b84abbfbf10ad07efa7c26108a14e7a2a0402daa06e447a47a
+size 17078668