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 +1,93 @@
+---
+base_model:
+- DavidAU/MN-Dark-Planet-TITAN-12B
+- DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS
+- IlyaGusev/saiga_nemo_12b
+- DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-MADNESS
+- win10/Mistral-Nemo-abliterated-Nemo-Pro-v2
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+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 [TIES](https://arxiv.org/abs/2306.01708) merge method using [win10/Mistral-Nemo-abliterated-Nemo-Pro-v2](https://huggingface.co/win10/Mistral-Nemo-abliterated-Nemo-Pro-v2) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [DavidAU/MN-Dark-Planet-TITAN-12B](https://huggingface.co/DavidAU/MN-Dark-Planet-TITAN-12B)
+* [DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS](https://huggingface.co/DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS)
+* [IlyaGusev/saiga_nemo_12b](https://huggingface.co/IlyaGusev/saiga_nemo_12b)
+* [DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-MADNESS](https://huggingface.co/DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-MADNESS)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:      
+  - model: DavidAU/MN-Dark-Planet-TITAN-12B
+    parameters:
+      density: 1
+      weight: 1
+
+  - model: DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-MADNESS
+    parameters:
+      density: 1
+      weight: 1
+
+  - model: DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS
+    parameters:
+      density: 1
+      weight: 1
+
+  - model: IlyaGusev/saiga_nemo_12b
+    parameters:
+      density: 1
+      weight: 1    
+
+merge_method: ties
+base_model: win10/Mistral-Nemo-abliterated-Nemo-Pro-v2
+  
+dtype: float32
+chat_template: chatml
+# Regularization
+regularization:
+  - method: gradient_penalty
+    scale: 0.05  # Increased influence for gradient control
+  - method: weight_clipping
+    clip_range: [-0.2, 0.2]  # Broader clipping range for flexibility
+  - method: random_noise
+    scale: 0.01  # Stronger noise injection
+  - method: attention_dropout
+    scale: 0.1  # Higher dropout to reduce attention fixation
+
+# Postprocessing
+postprocessing:
+  - operation: entropy_regularization
+    scale: 0.05  # Stronger encouragement for diverse outputs
+  - operation: non_linear_scaling
+    parameters:
+      function: tanh
+  - operation: sharpening
+    intensity: 0.5  # Enhanced sharpening for precise outputs
+  - operation: gaussian_smoothing
+    sigma: 1.5  # Increased smoothing for stable outputs
+  - operation: normalize
+  - operation: dynamic_scaling
+    scale_range: [0.8, 1.2]  # Expanded dynamic range for scaling
+  - operation: smoothing
+    parameters:
+      adaptive: true
+      range: [0.85, 1.15]  # Wider adaptive smoothing range
+      kernel_size: 5
+
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "win10/Mistral-Nemo-abliterated-Nemo-Pro-v2",
+  "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,
+  "pad_token_id": 10,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.46.2",
+  "unsloth_version": "2024.8",
+  "use_cache": true,
+  "vocab_size": 131072
+}

mergekit_config.yml

@@ -0,0 +1,56 @@
+models:      
+  - model: DavidAU/MN-Dark-Planet-TITAN-12B
+    parameters:
+      density: 1
+      weight: 1
+
+  - model: DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-MADNESS
+    parameters:
+      density: 1
+      weight: 1
+
+  - model: DavidAU/MN-GRAND-Gutenberg-Lyra4-Lyra-12B-DARKNESS
+    parameters:
+      density: 1
+      weight: 1
+
+  - model: IlyaGusev/saiga_nemo_12b
+    parameters:
+      density: 1
+      weight: 1    
+
+merge_method: ties
+base_model: win10/Mistral-Nemo-abliterated-Nemo-Pro-v2
+  
+dtype: float32
+chat_template: chatml
+# Regularization
+regularization:
+  - method: gradient_penalty
+    scale: 0.05  # Increased influence for gradient control
+  - method: weight_clipping
+    clip_range: [-0.2, 0.2]  # Broader clipping range for flexibility
+  - method: random_noise
+    scale: 0.01  # Stronger noise injection
+  - method: attention_dropout
+    scale: 0.1  # Higher dropout to reduce attention fixation
+
+# Postprocessing
+postprocessing:
+  - operation: entropy_regularization
+    scale: 0.05  # Stronger encouragement for diverse outputs
+  - operation: non_linear_scaling
+    parameters:
+      function: tanh
+  - operation: sharpening
+    intensity: 0.5  # Enhanced sharpening for precise outputs
+  - operation: gaussian_smoothing
+    sigma: 1.5  # Increased smoothing for stable outputs
+  - operation: normalize
+  - operation: dynamic_scaling
+    scale_range: [0.8, 1.2]  # Expanded dynamic range for scaling
+  - operation: smoothing
+    parameters:
+      adaptive: true
+      range: [0.85, 1.15]  # Wider adaptive smoothing range
+      kernel_size: 5

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:727816beab15bd099ffbf25934d5035198ef2e62c1df754297b17291226ac2a4
+size 2684354688

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:352bee5df08b2e8f635644d47416e4dbe6c336699d620f2eccf0440075701555
+size 4865497360

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:347282598ebc4089239262818a3543a8768e006bd2217e371030650af5200df3
+size 4949446984

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33baceb8fdb33ce45647d9c7ba4143921e5129eb383d7c3728eb2f3e21d1778b
+size 4865602440

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260ad753258d5413baf38d8e89a94ffed102dc41e80814cd7d0fd1ddfae971d3
+size 4949446968

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:593fd2f51bed96772b4a86c8c813cad88ca381f93ed41a0ab0e98ae5bec95a80
+size 4865602440

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:931023723157c3c7887eebea025a252da008b05e4d0e8eb6badfb9403690a602
+size 4949446968

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8de721b9a39605fcda64adcd1c28b87f73472f4aaafd82a9a9a9c68d76169597
+size 4865602440

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e4930cc3e3fc7c638afaca59605e07ea5102d6c25403bd64f9dc682b6e39e9c
+size 4949446984

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5554db7f79b3389d019b5c171ba33fce7cb23a2768010aa699eefaf5cd84ab23
+size 4865602400

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f9869980ab89c971781eeffd1f139f47c7ed9aa4873b92e24feaf52dc940b11f
+size 2181122072

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 48991129600}, "weight_map": {"lm_head.weight": "model-00001-of-00011.safetensors", "model.embed_tokens.weight": "model-00002-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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