Upload folder using huggingface_hub

README.md

@@ -0,0 +1,117 @@
+---
+base_model: []
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# final_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 [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863 as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* /content/drive/MyDrive/evolve-merge-v2/input_models/llama3_sft_many_chat_3038212730
+* /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_not_our_data_rope_1173759365
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+base_model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863
+dtype: bfloat16
+merge_method: dare_ties
+parameters:
+  int8_mask: 1.0
+  normalize: 1.0
+slices:
+- sources:
+  - layer_range: [0, 8]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863
+    parameters:
+      density: 0.7653375506603464
+      weight: 0.13767610478325062
+  - layer_range: [0, 8]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_not_our_data_rope_1173759365
+    parameters:
+      density: 0.7336602489449524
+      weight: 0.3666639544856324
+  - layer_range: [0, 8]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llama3_sft_many_chat_3038212730
+    parameters:
+      density: 1.0
+      weight: 0.3030835610677404
+- sources:
+  - layer_range: [8, 16]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863
+    parameters:
+      density: 0.9861387586510485
+      weight: 0.3948174181228292
+  - layer_range: [8, 16]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_not_our_data_rope_1173759365
+    parameters:
+      density: 0.8413699662162298
+      weight: 0.45739982954282526
+  - layer_range: [8, 16]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llama3_sft_many_chat_3038212730
+    parameters:
+      density: 1.0
+      weight: 0.30274586211044396
+- sources:
+  - layer_range: [16, 24]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863
+    parameters:
+      density: 0.9503146891835705
+      weight: 0.2849061463174477
+  - layer_range: [16, 24]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_not_our_data_rope_1173759365
+    parameters:
+      density: 0.832031377573231
+      weight: 0.6047693096979141
+  - layer_range: [16, 24]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llama3_sft_many_chat_3038212730
+    parameters:
+      density: 0.9442991059236329
+      weight: 0.4002445342115458
+- sources:
+  - layer_range: [24, 32]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863
+    parameters:
+      density: 0.8517897851608993
+      weight: 0.3362716927810899
+  - layer_range: [24, 32]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_not_our_data_rope_1173759365
+    parameters:
+      density: 1.0
+      weight: 0.2909336827183003
+  - layer_range: [24, 32]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llama3_sft_many_chat_3038212730
+    parameters:
+      density: 1.0
+      weight: 0.3474712168573882
+- sources:
+  - layer_range: [32, 40]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863
+    parameters:
+      density: 1.0
+      weight: 0.27727322046805786
+  - layer_range: [32, 40]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_not_our_data_rope_1173759365
+    parameters:
+      density: 0.8394275769864135
+      weight: 0.4724670213437233
+  - layer_range: [32, 40]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llama3_sft_many_chat_3038212730
+    parameters:
+      density: 1.0
+      weight: 0.31333702280148296
+tokenizer_source: base
+```

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": "/content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 13824,
+  "max_position_embeddings": 2048,
+  "max_sequence_length": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "dynamic"
+  },
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0",
+  "use_cache": true,
+  "vocab_size": 100021
+}

mergekit_config.yml

@@ -0,0 +1,88 @@
+base_model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863
+dtype: bfloat16
+merge_method: dare_ties
+parameters:
+  int8_mask: 1.0
+  normalize: 1.0
+slices:
+- sources:
+  - layer_range: [0, 8]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863
+    parameters:
+      density: 0.7653375506603464
+      weight: 0.13767610478325062
+  - layer_range: [0, 8]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_not_our_data_rope_1173759365
+    parameters:
+      density: 0.7336602489449524
+      weight: 0.3666639544856324
+  - layer_range: [0, 8]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llama3_sft_many_chat_3038212730
+    parameters:
+      density: 1.0
+      weight: 0.3030835610677404
+- sources:
+  - layer_range: [8, 16]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863
+    parameters:
+      density: 0.9861387586510485
+      weight: 0.3948174181228292
+  - layer_range: [8, 16]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_not_our_data_rope_1173759365
+    parameters:
+      density: 0.8413699662162298
+      weight: 0.45739982954282526
+  - layer_range: [8, 16]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llama3_sft_many_chat_3038212730
+    parameters:
+      density: 1.0
+      weight: 0.30274586211044396
+- sources:
+  - layer_range: [16, 24]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863
+    parameters:
+      density: 0.9503146891835705
+      weight: 0.2849061463174477
+  - layer_range: [16, 24]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_not_our_data_rope_1173759365
+    parameters:
+      density: 0.832031377573231
+      weight: 0.6047693096979141
+  - layer_range: [16, 24]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llama3_sft_many_chat_3038212730
+    parameters:
+      density: 0.9442991059236329
+      weight: 0.4002445342115458
+- sources:
+  - layer_range: [24, 32]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863
+    parameters:
+      density: 0.8517897851608993
+      weight: 0.3362716927810899
+  - layer_range: [24, 32]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_not_our_data_rope_1173759365
+    parameters:
+      density: 1.0
+      weight: 0.2909336827183003
+  - layer_range: [24, 32]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llama3_sft_many_chat_3038212730
+    parameters:
+      density: 1.0
+      weight: 0.3474712168573882
+- sources:
+  - layer_range: [32, 40]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_our_data_rope_3108389863
+    parameters:
+      density: 1.0
+      weight: 0.27727322046805786
+  - layer_range: [32, 40]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llma3_manydata_not_our_data_rope_1173759365
+    parameters:
+      density: 0.8394275769864135
+      weight: 0.4724670213437233
+  - layer_range: [32, 40]
+    model: /content/drive/MyDrive/evolve-merge-v2/input_models/llama3_sft_many_chat_3038212730
+    parameters:
+      density: 1.0
+      weight: 0.31333702280148296
+tokenizer_source: base

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70fa221826a1d0898d6d763c3d3f0d864840ae8421129eb2a4af7c6219d32ba3
+size 9897333552

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:011801b94aa9c15582eae132587da7b62d59ab33bdfc4e66ebd5f6643478b96a
+size 9909430752

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e4f410cd8d487889ee1aa111ab31a91f1ee100a54eb4079aad331c5985251d5
+size 4262633496

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 24069355520}, "weight_map": {"lm_head.weight": "model-00001-of-00003.safetensors", "model.embed_tokens.weight": "model-00001-of-00003.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00003.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00003.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00002-of-00003.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.input_layernorm.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00002-of-00003.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00003.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00003.safetensors", "model.norm.weight": "model-00003-of-00003.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,51 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "cls_token": {
+    "content": "<CLS>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "mask_token": {
+    "content": "<mask>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "sep_token": {
+    "content": "<SEP>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,86 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<mask>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<CLS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<SEP>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<EOD>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "cls_token": "<CLS>",
+  "eod_token": "<EOD>",
+  "eos_token": "</s>",
+  "extra_ids": 0,
+  "mask_token": "<mask>",
+  "max_length": 2048,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<pad>",
+  "sep_token": "<SEP>",
+  "sp_model_kwargs": {},
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>"
+}