Upload folder using huggingface_hub

README.md

@@ -0,0 +1,46 @@
+---
+base_model:
+- NeverSleep/Noromaid-13b-v0.1.1
+- CalderaAI/13B-Thorns-l2
+- WizardLM/WizardLM-13B-V1.2
+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 [linear](https://arxiv.org/abs/2203.05482) merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [NeverSleep/Noromaid-13b-v0.1.1](https://huggingface.co/NeverSleep/Noromaid-13b-v0.1.1)
+* [CalderaAI/13B-Thorns-l2](https://huggingface.co/CalderaAI/13B-Thorns-l2)
+* [WizardLM/WizardLM-13B-V1.2](https://huggingface.co/WizardLM/WizardLM-13B-V1.2)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+
+models:
+  - model: NeverSleep/Noromaid-13b-v0.1.1
+    parameters:
+      weight: 1.0
+  - model: WizardLM/WizardLM-13B-V1.2
+    parameters:
+      weight: 0.3
+  - model: CalderaAI/13B-Thorns-l2
+    parameters:
+      weight: 0.5
+merge_method: linear
+dtype: float16
+
+```

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32000
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "NeverSleep/Noromaid-13b-v0.1.1",
+  "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": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 40,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 40,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.37.2",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,13 @@
+
+models:
+  - model: NeverSleep/Noromaid-13b-v0.1.1
+    parameters:
+      weight: 1.0
+  - model: WizardLM/WizardLM-13B-V1.2
+    parameters:
+      weight: 0.3
+  - model: CalderaAI/13B-Thorns-l2
+    parameters:
+      weight: 0.5
+merge_method: linear
+dtype: float16

model-00001-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:01092c0e72eb3bea881137f25db0d14bda10af338bd3bb5b8ba2f4fef60094ba
+size 1971377432

model-00002-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b5234ae98632f4a95a5c1f991ca78edc8de99ebc678a0e4575654b86ec07331
+size 1903229984

model-00003-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c45b8371ead274468931c39b4a2c8de36c976c16db705e13a2614a2f7a2ed59c
+size 1947784000

model-00004-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b722b685f8e8bbf6be529999ca3c0ef505b170f00b5304897d95b307be81bc1c
+size 1955658928

model-00005-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bb3d12931aa4960d1f6e1e9c471ec8c51bb800f91d3f659f4c450fa6af359f14
+size 1887511472

model-00006-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:984e699190540d1a42e99802f4c19037f091a45e7b716b668340a1006c5082c1
+size 1903230008

model-00007-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38e43a83167d65f9a0d835ae4885db47e80306c1ddb6f0ec70097d2a5a122bc3
+size 1903230008

model-00008-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f812710e2ae1e7fe5dd600b3ecd2feb8c85b1748dc11a891bfcb9cea5a462f78
+size 1992348608

model-00009-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:060087c16373c45d9fd6ec3b92db5daed711e7f51cc87d3b61131bfed0625b32
+size 1955658928

model-00010-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12a424d86318812c552d176b94b68e2571fa1f38da0cf0df5a4e9883b21cd85e
+size 1955658928

model-00011-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6113481bd849aca85375541b33bf53428badc1baaf60f9ea6d78c5ebe2efbd17
+size 1955648576

model-00012-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8c9404fb879013a01807662f2afb51e79d345a57c9746a9390dadcb9534183b2
+size 1903230016

model-00013-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b484a1394d8452cdbca8e2068bf3287b8b5192d7313de820b1eb810db9c16c9
+size 1984515080

model-00014-of-00014.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df4c86d1fd749aa86585596ec027b71220e4ecd860537cd08c6e74655a77b411
+size 812688632

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00014.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00014.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00014.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00014.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00014.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.embed_tokens.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00014.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00014.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00014.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00014.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00014.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00014.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00014.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.10.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.9.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00005-of-00014.safetensors", "model.layers.8.input_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00014.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00014.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.7.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00014.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00014.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00014.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00014.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00014.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00014.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00014.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00014.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.28.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00009-of-00014.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00014.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.25.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00010-of-00014.safetensors", "model.layers.24.input_layernorm.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00014.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.23.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00011-of-00014.safetensors", "model.layers.37.input_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00011-of-00014.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.36.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.35.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00012-of-00014.safetensors", "model.layers.34.input_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00012-of-00014.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00012-of-00014.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00013-of-00014.safetensors", "model.layers.31.input_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00013-of-00014.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00013-of-00014.safetensors", "model.layers.30.input_layernorm.weight": "model-00013-of-00014.safetensors", "lm_head.weight": "model-00013-of-00014.safetensors", "model.norm.weight": "model-00013-of-00014.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00014.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00014.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.39.input_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00014.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00014-of-00014.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00014-of-00014.safetensors", "model.layers.38.input_layernorm.weight": "model-00014-of-00014.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "[PAD]",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32000": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 2048,
+  "pad_token": "[PAD]",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}