Upload folder using huggingface_hub

README.md

@@ -0,0 +1,31 @@
+---
+tags:
+- MTSAIR/multi_verse_model
+- ResplendentAI/Paradigm_7B
+base_model:
+- MTSAIR/multi_verse_model
+- ResplendentAI/Paradigm_7B
+---
+
+# Multiparadigm_7B
+
+Multiparadigm_7B is a merge of the following models:
+* [MTSAIR/multi_verse_model](https://huggingface.co/MTSAIR/multi_verse_model)
+* [ResplendentAI/Paradigm_7B](https://huggingface.co/ResplendentAI/Paradigm_7B)
+slices:
+  - sources:
+      - model: MTSAIR/multi_verse_model
+        layer_range: [0, 32]
+      - model: ResplendentAI/Paradigm_7B
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: MTSAIR/multi_verse_model
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.6, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.6, 0.7, 0.3, 0]
+    - value: 0.6
+dtype: bfloat16
+rmdhirr

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "MTSAIR/multi_verse_model",
+  "add_gates": false,
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 10000.0,
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.38.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,17 @@
+
+slices:
+  - sources:
+      - model: MTSAIR/multi_verse_model
+        layer_range: [0, 32]
+      - model: ResplendentAI/Paradigm_7B
+        layer_range: [0, 32]
+merge_method: slerp
+base_model: MTSAIR/multi_verse_model
+parameters:
+  t:
+    - filter: self_attn
+      value: [0, 0.6, 0.3, 0.7, 1]
+    - filter: mlp
+      value: [1, 0.6, 0.7, 0.3, 0]
+    - value: 0.6
+dtype: bfloat16

model-00001-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4d8ad3952b55699b371134b2ffbbc791747d29ed0cdcdfd7b27e95bc91c8e98
+size 989874104

model-00002-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c252e42780c9639cbd101c61d4fde244cf441f94304296acb4980d1126529c1
+size 989899016

model-00003-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6361d249cfb08fafbc1d7b420bd927729dc70df186857d227f1085f1b86586d3
+size 956344912

model-00004-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8c9d0098ff9a905fe982c5a8adfb0af61c5d22b739ef48677cb9d199fc00fd4
+size 989890712

model-00005-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea58270f3272534e37543dfccfd00a5f77c6e2abc1fa2143a73e6276485f546e
+size 755009448

model-00006-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1b96289dccf6525b3cc77a57363c3ece30cc3f9ebc7d50e758625b6856a4a902
+size 899696344

model-00007-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:552f3eb383ef418144cf0145e4c6e6a01eb4e11189842732f5fdac95a3dd54a1
+size 989890728

model-00008-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c4c13fdf13820f2cb3ced23874507faae0f43815d777bab1f7ff6f2d83b50ff
+size 989899040

model-00009-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77f2290c7b542e0cbcbcfdf839ae72c1b0d118429b8548392328faefae63fe77
+size 956344936

model-00010-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d6058d4dbd2d0117f21c23e895f9ee25d6bd76cff62a4b533d1de3a580e048b
+size 989890728

model-00011-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1a1d280211ecbb32cb9a484bb77009ef0730c9d405ceb090ee2411d9d13c2ba0
+size 933275304

model-00012-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7856e61b9f008fde19c39d610d1462fb409f8c7cf8ab9700373c99127cdd3bb
+size 989899040

model-00013-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f852f0cf3805031b32b58d70c74419aea337ec483b15cb8a76ef867499ec81dc
+size 956344936

model-00014-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d7e5bddf7aac20f8d8ec2f88f75b134d32dca042c0a89d4fd57cad995f7e5a1
+size 989890728

model-00015-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb6e31cda31dde05d9df1516f33cbfc9a07c308c911842f690a2b3a1a74cd731
+size 989890728

model-00016-of-00016.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6876f1a5602ce8da7c368722c47883167ab4c99b47cf8e8613e47f96800bde3d
+size 117457264

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14483464192}, "weight_map": {"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00016.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.embed_tokens.weight": "model-00006-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00011-of-00016.safetensors", "lm_head.weight": "model-00011-of-00016.safetensors", "model.norm.weight": "model-00011-of-00016.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.29.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.28.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00016-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00016-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00016-of-00016.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": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{ '### Instruction:\n' + message['content'] + '\n### Response:\n' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% elif message['role'] == 'system' %}{{ '### System:\n' + message['content'] + '\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 32768,
+  "pad_token": "<unk>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}