Upload model

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.gguf filter=lfs diff=lfs merge=lfs -text

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "Aryanne/Astrea-RP-v1-3B",
+  "architectures": [
+    "StableLMEpochForCausalLM"
+  ],
+  "auto_map": {
+    "AutoConfig": "Aryanne/Astridboros-3B--configuration_stablelm_epoch.StableLMEpochConfig",
+    "AutoModelForCausalLM": "Aryanne/Astridboros-3B--modeling_stablelm_epoch.StableLMEpochForCausalLM"
+  },
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 6912,
+  "max_position_embeddings": 4096,
+  "model_type": "stablelm_epoch",
+  "norm_eps": 1e-05,
+  "num_attention_heads": 32,
+  "num_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "rope_pct": 0.25,
+  "rope_theta": 10000,
+  "rotary_scaling_factor": 1.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.35.2",
+  "use_cache": true,
+  "vocab_size": 50304
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:818ee8eaf42a88c2775d63623411544a4c7f787c572e4e80b74c3532e86c2b2d
+size 389960824

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:255e0b6e431b2add033ad7d65f747183c74d7da90e8745e1ce89318b5842b352
+size 378852336

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3cc066529ce07f8847854e1f92f6e2e9b8d154ac813fe4bfd9319def5ad79ea8
+size 388027288

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ac3ed800b4c04b679c18008ba32be60f09230d13859b793821a50aa46514f63
+size 369677424

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2a25df5484b59c94b5be122c11859fc4b5c9e68d5873266bb0f97da6f27820a
+size 388016824

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9604c54c0ec91a256ec733e57a5332756fb5adde1a20af95d9ad1a7f109ff72f
+size 391959664

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11f4b5882f201944e3c02b3f2716129df2ebe2e0d03e5b8a31a93f2875bbdf2a
+size 365745032

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e91f90de1c30596f6d73f101cf54161bac326da7bb3145259ebb3ad6dd323ea7
+size 388027288

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e947033e07f6fbac2fbda2f12e4b744ad350e0a20844f0582527dbfa252b73ce
+size 369677424

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fe97abc98cc2d3a45407f596e61ce6b35eeffc596bf25799b76045f0cfae54a
+size 388006368

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3678ea4b4347cd73f432fac7f58354cb0ac126819099220f50aaca1acd0968c
+size 369677400

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed7eca02a68b290a57a9e4a4bc7301962548848b99a9e64ab3b8c66ea867292b
+size 388016800

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:88d514a6106f64a6ab5a528e2244d3ab3b7187cb7ca15a390410991fb65bc2c4
+size 391959648

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9bd1c4fd01bbf82b6971a823717513c2024e7e96937ee01833af72f4a171568
+size 376863960

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc8fb581b8bd8301913f801277cc2ce969f27fc0f38f2e1d9c7df98f61eafd1a
+size 246458560

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.3.1"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00015.safetensors", "model.layers.0.input_layernorm.bias": "model-00001-of-00015.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00015.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.input_layernorm.bias": "model-00002-of-00015.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.post_attention_layernorm.bias": "model-00002-of-00015.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.input_layernorm.bias": "model-00002-of-00015.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.post_attention_layernorm.bias": "model-00002-of-00015.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.input_layernorm.bias": "model-00002-of-00015.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.post_attention_layernorm.bias": "model-00003-of-00015.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.input_layernorm.bias": "model-00003-of-00015.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.post_attention_layernorm.bias": "model-00003-of-00015.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.input_layernorm.bias": "model-00003-of-00015.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.post_attention_layernorm.bias": "model-00003-of-00015.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.input_layernorm.bias": "model-00004-of-00015.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.post_attention_layernorm.bias": "model-00004-of-00015.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.input_layernorm.bias": "model-00004-of-00015.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.post_attention_layernorm.bias": "model-00004-of-00015.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.16.input_layernorm.bias": "model-00004-of-00015.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.post_attention_layernorm.bias": "model-00005-of-00015.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.input_layernorm.bias": "model-00005-of-00015.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.post_attention_layernorm.bias": "model-00005-of-00015.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.18.input_layernorm.bias": "model-00005-of-00015.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.post_attention_layernorm.bias": "model-00006-of-00015.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.input_layernorm.bias": "model-00006-of-00015.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.post_attention_layernorm.bias": "model-00006-of-00015.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.2.input_layernorm.bias": "model-00006-of-00015.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.2.post_attention_layernorm.bias": "model-00006-of-00015.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.input_layernorm.bias": "model-00007-of-00015.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.post_attention_layernorm.bias": "model-00007-of-00015.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.input_layernorm.bias": "model-00007-of-00015.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.post_attention_layernorm.bias": "model-00007-of-00015.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.22.input_layernorm.bias": "model-00007-of-00015.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.post_attention_layernorm.bias": "model-00008-of-00015.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.input_layernorm.bias": "model-00008-of-00015.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.post_attention_layernorm.bias": "model-00008-of-00015.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.24.input_layernorm.bias": "model-00008-of-00015.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.24.post_attention_layernorm.bias": "model-00008-of-00015.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.input_layernorm.bias": "model-00009-of-00015.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.post_attention_layernorm.bias": "model-00009-of-00015.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.26.input_layernorm.bias": "model-00009-of-00015.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.26.post_attention_layernorm.bias": "model-00009-of-00015.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.27.input_layernorm.bias": "model-00009-of-00015.safetensors", "model.layers.27.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.post_attention_layernorm.bias": "model-00010-of-00015.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.28.input_layernorm.bias": "model-00010-of-00015.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.28.post_attention_layernorm.bias": "model-00010-of-00015.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.input_layernorm.bias": "model-00011-of-00015.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.post_attention_layernorm.bias": "model-00011-of-00015.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.4.input_layernorm.bias": "model-00011-of-00015.safetensors", "model.layers.4.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.4.post_attention_layernorm.bias": "model-00011-of-00015.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.5.input_layernorm.bias": "model-00011-of-00015.safetensors", "model.layers.5.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.5.post_attention_layernorm.bias": "model-00012-of-00015.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.6.input_layernorm.bias": "model-00012-of-00015.safetensors", "model.layers.6.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.6.post_attention_layernorm.bias": "model-00012-of-00015.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.7.input_layernorm.bias": "model-00012-of-00015.safetensors", "model.layers.7.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.7.post_attention_layernorm.bias": "model-00013-of-00015.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.8.input_layernorm.bias": "model-00013-of-00015.safetensors", "model.layers.8.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.8.post_attention_layernorm.bias": "model-00013-of-00015.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.9.input_layernorm.bias": "model-00013-of-00015.safetensors", "model.layers.9.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.9.post_attention_layernorm.bias": "model-00013-of-00015.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "lm_head.weight": "model-00014-of-00015.safetensors", "model.layers.29.input_layernorm.bias": "model-00014-of-00015.safetensors", "model.layers.29.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.29.post_attention_layernorm.bias": "model-00014-of-00015.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.30.input_layernorm.bias": "model-00014-of-00015.safetensors", "model.layers.30.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.30.post_attention_layernorm.bias": "model-00015-of-00015.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.layers.31.input_layernorm.bias": "model-00015-of-00015.safetensors", "model.layers.31.input_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00015-of-00015.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00015.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.31.post_attention_layernorm.bias": "model-00015-of-00015.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.norm.bias": "model-00015-of-00015.safetensors", "model.norm.weight": "model-00015-of-00015.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,213 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "50254": {
+      "content": "                        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50255": {
+      "content": "                       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50256": {
+      "content": "                      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50257": {
+      "content": "                     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50258": {
+      "content": "                    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50259": {
+      "content": "                   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50260": {
+      "content": "                  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50261": {
+      "content": "                 ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50262": {
+      "content": "                ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50263": {
+      "content": "               ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50264": {
+      "content": "              ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50265": {
+      "content": "             ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50266": {
+      "content": "            ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50267": {
+      "content": "           ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50268": {
+      "content": "          ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50269": {
+      "content": "         ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50270": {
+      "content": "        ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50271": {
+      "content": "       ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50272": {
+      "content": "      ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50273": {
+      "content": "     ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50274": {
+      "content": "    ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50275": {
+      "content": "   ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "50276": {
+      "content": "  ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}