Upload folder using huggingface_hub

README.md

@@ -0,0 +1,87 @@
+---
+base_model:
+- lilmeaty/ksksksk
+library_name: transformers
+tags:
+- mergekit
+- merge
+
+---
+# merge
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the passthrough merge method.
+
+### Models Merged
+
+The following models were included in the merge:
+* [lilmeaty/ksksksk](https://huggingface.co/lilmeaty/ksksksk)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+slices:
+  - sources: 
+      - layer_range: [0, 40]
+        model: lilmeaty/ksksksk
+        parameters:
+          normalize: true
+          int8_mask: true
+          density: 0.5
+          weight: 0.1
+          random_seed: 0
+          temperature: 0.5
+          top_p: 0.65
+          inference: true
+          max_tokens: 999999999
+          stream: true
+          quantization:
+            method: int8
+            value: 100
+          quantization:
+            method: int4
+            value: 100
+  - sources: 
+      - layer_range: [0, 3]
+        model: lilmeaty/ksksksk
+        parameters:
+          normalize: true
+          int8_mask: true
+          density: 0.5
+          weight: 0.1
+          random_seed: 0
+          temperature: 0.5
+          top_p: 0.65
+          inference: true
+          max_tokens: 999999999
+          stream: true
+          quantization:
+            method: int8
+            value: 100
+          quantization:
+            method: int4
+            value: 100
+parameters:
+  normalize: true
+  int8_mask: true
+  density: 0.5
+  weight: 0.1
+  random_seed: 0
+  temperature: 0.5
+  top_p: 0.65
+  inference: true
+  max_tokens: 999999999
+  stream: true
+  convert_to:
+    type: 
+      - gguf
+    value: 100.0
+merge_method: passthrough
+
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "lilmeaty/ksksksk",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 43,
+  "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": "4.46.1",
+  "use_cache": false,
+  "vocab_size": 32000
+}

mergekit_config.yml

@@ -0,0 +1,57 @@
+slices:
+  - sources: 
+      - layer_range: [0, 40]
+        model: lilmeaty/ksksksk
+        parameters:
+          normalize: true
+          int8_mask: true
+          density: 0.5
+          weight: 0.1
+          random_seed: 0
+          temperature: 0.5
+          top_p: 0.65
+          inference: true
+          max_tokens: 999999999
+          stream: true
+          quantization:
+            method: int8
+            value: 100
+          quantization:
+            method: int4
+            value: 100
+  - sources: 
+      - layer_range: [0, 3]
+        model: lilmeaty/ksksksk
+        parameters:
+          normalize: true
+          int8_mask: true
+          density: 0.5
+          weight: 0.1
+          random_seed: 0
+          temperature: 0.5
+          top_p: 0.65
+          inference: true
+          max_tokens: 999999999
+          stream: true
+          quantization:
+            method: int8
+            value: 100
+          quantization:
+            method: int4
+            value: 100
+parameters:
+  normalize: true
+  int8_mask: true
+  density: 0.5
+  weight: 0.1
+  random_seed: 0
+  temperature: 0.5
+  top_p: 0.65
+  inference: true
+  max_tokens: 999999999
+  stream: true
+  convert_to:
+    type: 
+      - gguf
+    value: 100.0
+merge_method: passthrough

model-00001-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5185abe13ebae1252de64723c6c9af0cdcebe38e49028fcd7c93973d7c171cee
+size 262144128

model-00002-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95a22dd8561e01b711618123d69019f01e63a3b3f84a02afbfb43a4b51b27ff1
+size 989344544

model-00003-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bef54b565e565d31cddfa40b40a74fde38014d188c3f6f2c0a1cfbce6257c6f
+size 981533832

model-00004-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24670e56196500b6a99182b778713efc18bd39dfac18cec82fc86ca4223475e7
+size 987825096

model-00005-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cdb300d9398288e200ee5ab20abb0020d346125424b42910b9a7e5ad12a98ec
+size 956366312

model-00006-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5896199f7eedb48f2151b92b1f9031ea267ea6e9f9518822fd1e13a7c6701c2c
+size 981527232

model-00007-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eab814b2dd9edefea10411e6ef20669d3632da0f0a3d974830fdcc303ea2aa0b
+size 987825048

model-00008-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f8a88dd2e54726069c96b1b412a9a372cab21fb8dac4a476c145947a89ffd30
+size 950069960

model-00009-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7a03170a1ff4d749622f156bb5413490372f05778046567c40576603b659fe21
+size 996211768

model-00010-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6b4783147e7df97abc78fd8e5582ab92f2f5c41fe5b2e389fa0331e377e7a24
+size 998311360

model-00011-of-00011.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e44557e60bcd237eceac899e694d80ae2ed9b324b3429030e5dc5050b9df422c
+size 427854152

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.5.1", "total_size": 9518968832}, "weight_map": {"lm_head.weight": "model-00001-of-00011.safetensors", "model.embed_tokens.weight": "model-00002-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,35 @@
+{
+  "additional_special_tokens": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "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": "</s>",
+    "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 +1,55 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": null,
+  "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": [
+    "<unk>",
+    "<s>",
+    "</s>"
+  ],
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{bos_token + message['role'] + '\n' + message['content'] + eos_token + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "max_length": 512,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_to_multiple_of": null,
+  "pad_token": "</s>",
+  "pad_token_type_id": 0,
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "stride": 0,
+  "tokenizer_class": "LlamaTokenizer",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}