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 +1,166 @@
+---
+base_model:
+- bamec66557/MISCHIEVOUS-12B-Mix_0.4v
+- bamec66557/MISCHIEVOUS-12B-Mix_0.5v
+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 SLERP merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [bamec66557/MISCHIEVOUS-12B-Mix_0.4v](https://huggingface.co/bamec66557/MISCHIEVOUS-12B-Mix_0.4v)
+* [bamec66557/MISCHIEVOUS-12B-Mix_0.5v](https://huggingface.co/bamec66557/MISCHIEVOUS-12B-Mix_0.5v)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+description: Merging MISCHIEVOUS-12B-Mix models with sliced slerp
+
+# Metadata and Rationale
+model_description: |
+  This configuration merges two versions of the MISCHIEVOUS-12B-Mix model: 0.4v and 0.3v.
+  0.3v was further fine-tuned on a specific dataset (ADD DATASET NAME HERE if known).
+  The sliced slerp approach allows for layer-specific control over the merging process.
+
+base_model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
+dtype: bfloat16
+merge_method: slerp
+tokenizer_source: union
+
+# Slices Configuration (Layer-Specific Merging)
+slices:
+  - sources:
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
+        layer_range: [0, 10]
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.5v
+        layer_range: [0, 10]
+    parameters:
+      t:
+        - name: self_attn
+          value: [0.8, 0.85, 0.9, 0.95, 1.0]
+        - name: mlp
+          value: [0.9, 0.95, 1.0, 1.05, 1.1]
+        - name: layer_norm
+          value: [0.6, 0.65, 0.7, 0.75, 0.8]
+        - name: embed_tokens
+          value: [1.0]
+
+  - sources:
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
+        layer_range: [10, 20]
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.5v
+        layer_range: [10, 20]
+    parameters:
+      t:
+        - name: self_attn
+          value: [0.7, 0.75, 0.8, 0.85, 0.9]
+        - name: mlp
+          value: [1.0, 0.95, 0.9, 0.85, 0.8]
+        - name: layer_norm
+          value: [0.5, 0.55, 0.6, 0.65, 0.7]
+        - name: embed_tokens
+          value: [1.0]
+
+  - sources:
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
+        layer_range: [20, 30]
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.5v
+        layer_range: [20, 30]
+    parameters:
+      t:
+        - name: self_attn
+          value: [0.6, 0.65, 0.7, 0.75, 0.8]
+        - name: mlp
+          value: [0.8, 0.75, 0.7, 0.65, 0.6]
+        - name: layer_norm
+          value: [0.4, 0.45, 0.5, 0.55, 0.6]
+        - name: embed_tokens
+          value: [1.0]
+
+  - sources:
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
+        layer_range: [30, 40]
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.5v
+        layer_range: [30, 40]
+    parameters:
+      t:
+        - name: self_attn
+          value: [0.9, 1.0, 1.1, 1.2, 1.3]
+        - name: mlp
+          value: [0.7, 0.65, 0.6, 0.55, 0.5]
+        - name: layer_norm
+          value: [0.7, 0.75, 0.8, 0.85, 0.9]
+        - name: embed_tokens
+          value: [1.0]
+
+# Regularization (Prevent Overfitting During Merging)
+regularization:
+  - method: weight_clipping
+    clip_range: [-0.2, 0.2]
+  - method: random_noise
+    scale: 0.015
+  - method: l2_norm
+    scale: 0.01
+
+# Postprocessing (Enhance Merged Model Quality)
+postprocessing:
+  - operation: random_noise
+    scale: 0.0025
+  - operation: non_linear_scaling
+    parameters:
+      function: tanh
+  - operation: sharpening
+    intensity: 0.3
+  - operation: gaussian_smoothing
+    sigma: 1.5
+  - operation: smoothing
+    parameters:
+      adaptive: true
+      range: [0.8, 1.2]
+      kernel_size: 5
+  - operation: normalize
+  - operation: dynamic_scaling
+    scale_range: [0.75, 1.25]
+
+# Evaluation (Crucial for Assessing Merge Quality)
+evaluation:
+  metrics:
+    - perplexity
+    - accuracy # If applicable (e.g., classification tasks)
+    - bleu # For translation tasks
+    - rouge # For summarization tasks
+  datasets:
+    - wikitext # General language understanding
+    - lambada # Long-range dependency modeling
+    - (ADD RELEVANT TASK-SPECIFIC DATASETS HERE)
+  prompts: # Example prompts – REPLACE WITH YOUR OWN
+    - "The quick brown fox jumps over the lazy dog."
+    - "Translate 'Thank you' to Spanish:"
+    - "Write a short summary of the French Revolution."
+
+# Logging and Output
+logging:
+  output_dir: ./merged_models
+  log_level: INFO
+
+# Optional: Ties Merging (Advanced Technique)
+# ties:
+#   enabled: true
+#   method: greedy # Or "optimal", "random"
+#   layers: [0, 10, 20, 30] # Example layers for ties merging
+
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "bamec66557/MISCHIEVOUS-12B-Mix_0.4v",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.2",
+  "use_cache": true,
+  "vocab_size": 131074
+}

mergekit_config.yml

@@ -0,0 +1,134 @@
+description: Merging MISCHIEVOUS-12B-Mix models with sliced slerp
+
+# Metadata and Rationale
+model_description: |
+  This configuration merges two versions of the MISCHIEVOUS-12B-Mix model: 0.4v and 0.3v.
+  0.3v was further fine-tuned on a specific dataset (ADD DATASET NAME HERE if known).
+  The sliced slerp approach allows for layer-specific control over the merging process.
+
+base_model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
+dtype: bfloat16
+merge_method: slerp
+tokenizer_source: union
+
+# Slices Configuration (Layer-Specific Merging)
+slices:
+  - sources:
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
+        layer_range: [0, 10]
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.5v
+        layer_range: [0, 10]
+    parameters:
+      t:
+        - name: self_attn
+          value: [0.8, 0.85, 0.9, 0.95, 1.0]
+        - name: mlp
+          value: [0.9, 0.95, 1.0, 1.05, 1.1]
+        - name: layer_norm
+          value: [0.6, 0.65, 0.7, 0.75, 0.8]
+        - name: embed_tokens
+          value: [1.0]
+
+  - sources:
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
+        layer_range: [10, 20]
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.5v
+        layer_range: [10, 20]
+    parameters:
+      t:
+        - name: self_attn
+          value: [0.7, 0.75, 0.8, 0.85, 0.9]
+        - name: mlp
+          value: [1.0, 0.95, 0.9, 0.85, 0.8]
+        - name: layer_norm
+          value: [0.5, 0.55, 0.6, 0.65, 0.7]
+        - name: embed_tokens
+          value: [1.0]
+
+  - sources:
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
+        layer_range: [20, 30]
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.5v
+        layer_range: [20, 30]
+    parameters:
+      t:
+        - name: self_attn
+          value: [0.6, 0.65, 0.7, 0.75, 0.8]
+        - name: mlp
+          value: [0.8, 0.75, 0.7, 0.65, 0.6]
+        - name: layer_norm
+          value: [0.4, 0.45, 0.5, 0.55, 0.6]
+        - name: embed_tokens
+          value: [1.0]
+
+  - sources:
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.4v
+        layer_range: [30, 40]
+      - model: bamec66557/MISCHIEVOUS-12B-Mix_0.5v
+        layer_range: [30, 40]
+    parameters:
+      t:
+        - name: self_attn
+          value: [0.9, 1.0, 1.1, 1.2, 1.3]
+        - name: mlp
+          value: [0.7, 0.65, 0.6, 0.55, 0.5]
+        - name: layer_norm
+          value: [0.7, 0.75, 0.8, 0.85, 0.9]
+        - name: embed_tokens
+          value: [1.0]
+
+# Regularization (Prevent Overfitting During Merging)
+regularization:
+  - method: weight_clipping
+    clip_range: [-0.2, 0.2]
+  - method: random_noise
+    scale: 0.015
+  - method: l2_norm
+    scale: 0.01
+
+# Postprocessing (Enhance Merged Model Quality)
+postprocessing:
+  - operation: random_noise
+    scale: 0.0025
+  - operation: non_linear_scaling
+    parameters:
+      function: tanh
+  - operation: sharpening
+    intensity: 0.3
+  - operation: gaussian_smoothing
+    sigma: 1.5
+  - operation: smoothing
+    parameters:
+      adaptive: true
+      range: [0.8, 1.2]
+      kernel_size: 5
+  - operation: normalize
+  - operation: dynamic_scaling
+    scale_range: [0.75, 1.25]
+
+# Evaluation (Crucial for Assessing Merge Quality)
+evaluation:
+  metrics:
+    - perplexity
+    - accuracy # If applicable (e.g., classification tasks)
+    - bleu # For translation tasks
+    - rouge # For summarization tasks
+  datasets:
+    - wikitext # General language understanding
+    - lambada # Long-range dependency modeling
+    - (ADD RELEVANT TASK-SPECIFIC DATASETS HERE)
+  prompts: # Example prompts – REPLACE WITH YOUR OWN
+    - "The quick brown fox jumps over the lazy dog."
+    - "Translate 'Thank you' to Spanish:"
+    - "Write a short summary of the French Revolution."
+
+# Logging and Output
+logging:
+  output_dir: ./merged_models
+  log_level: INFO
+
+# Optional: Ties Merging (Advanced Technique)
+# ties:
+#   enabled: true
+#   method: greedy # Or "optimal", "random"
+#   layers: [0, 10, 20, 30] # Example layers for ties merging

model-00001-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72e28e2d1289efa4ba568ccd5b82bc08f4fa873d090f7444a0980aef0f245c02
+size 4865530296

model-00002-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:525cbbf7656675160f9f87d6822fbbdf5b4b63a48f3b7fc2c4fdf113b98d6b29
+size 4907529456

model-00003-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d7c16de1e46b270aecdaeab2e8ef98be5719ff5606b70738b90231a4d441f64
+size 4907529464

model-00004-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fb578923d20b4078d1aa87bbd201dd94467be9adbb93ce2ff04882117209817
+size 4907529456

model-00005-of-00005.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2b43ce5e86120320600bca24f66f3259a2bfdea68b4346a62709dc9b6b6e765
+size 4907529392

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 24495605760}, "weight_map": {"lm_head.weight": "model-00001-of-00005.safetensors", "model.embed_tokens.weight": "model-00001-of-00005.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00005.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00005.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00005.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00005.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00005.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00005.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00005.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00005.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00004-of-00005.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00004-of-00005.safetensors", "model.layers.37.input_layernorm.weight": "model-00004-of-00005.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00005.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00005.safetensors", "model.norm.weight": "model-00005-of-00005.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