Upload folder using huggingface_hub

config.json

@@ -3,8 +3,9 @@
   "architectures": [
     "MistralForCausalLM"
   ],
+  "attention_dropout": 0.0,
   "bos_token_id": 1,
-  "eos_token_id": 32000,
+  "eos_token_id": 2,
   "hidden_act": "silu",
   "hidden_size": 4096,
   "initializer_range": 0.02,
@@ -15,11 +16,11 @@
   "num_hidden_layers": 32,
   "num_key_value_heads": 8,
   "rms_norm_eps": 1e-05,
-  "rope_theta": 10000.0,
-  "sliding_window": 4096,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.35.2",
-  "use_cache": false,
-  "vocab_size": 32002
+  "use_cache": true,
+  "vocab_size": 32000
 }

model-00001-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5edcfa492eca83b45ccaab7961fb784c43dcc7ac1ae83d2a440197ad7ad5ee08
-size 1912681584
+oid sha256:6b019712a0901b945e79f49916fc8387cc7352a5af14405ebfaf752a166ce5fc
+size 1979773128

model-00002-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37a675415256fb7208f136e15b96f5149e077c759879e4056e99913fb3b157a1
-size 1979781456
+oid sha256:25e62de223c762a97a80f983217bfcd6817c7c838d0b502655fb497263d191fd
+size 1996567640

model-00003-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:db14e5f240273853ded26a6eabaae54c23aa94b0d38913a2afee3bc2a4169825
-size 1946243968
+oid sha256:d949b16310d2726b1c97fec1fd311e887b540aefb7b2dcabeae754aec810ff06
+size 1923158216

model-00004-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b00a871a625c1db4c1b68af2a358d08d1368c034ed019e72ad4a133d01975e6f
-size 1979781416
+oid sha256:4e0a81d53bb865d86a0cd509ef6f35dbf563fe48a273e3d94b03a00f70716cbf
+size 1979781464

model-00005-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:511ebb89d16b35378e6cd43a38eba3e0ef309b62765b13741ef3d863530e97da
-size 1862349080
+oid sha256:5db52c0902ceff7f44eea3ee586cc40ce12bdcedb68d3ccddb6ad90d49ded156
+size 1946243984

model-00006-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd19125263a64ccdb6ac21d609de2a8b727e9bd8c133f76b22cbbb30326e084a
-size 1916866512
+oid sha256:5e2370162d4d8f727712b910da01bd66deb32251d9cdd5a3224c8ea70c81245a
+size 1923166040

model-00007-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7c34e16fe5e35121ca96928290cf090ee8a0d477ef313d570b4a11b2360d406a
-size 1979781456
+oid sha256:74cb94b2d4cfebc0c9a3303951c45f4cbab89f087610941f2b8b3aa91ec95a58
+size 1946243984

model-00008-of-00008.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4612421cc4f1ccf86e4cb2d8bef6679fd4d6537a3f993e1195c50d0d330e8c5d
-size 906012472
+oid sha256:620105f68aa3fad836d84cc37448867d2acd59d38c4005475ad592878bb8533e
+size 788563544

model.safetensors.index.json

@@ -1 +1 @@
-{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.layers.22.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00005-of-00008.safetensors", "lm_head.weight": "model-00006-of-00008.safetensors", "model.norm.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.embed_tokens.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00008.safetensors"}}
+{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00008.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00008.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00008.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00008.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00008.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00008.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00008.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00008.safetensors", "model.embed_tokens.weight": "model-00003-of-00008.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00008.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00008.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00008.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00008.safetensors", "lm_head.weight": "model-00006-of-00008.safetensors", "model.norm.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors", "model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00006-of-00008.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.10.input_layernorm.weight": "model-00006-of-00008.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.28.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.27.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00008.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00008.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00008-of-00008.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00008.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00008.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00008.safetensors"}}

special_tokens_map.json

@@ -7,7 +7,7 @@
     "single_word": false
   },
   "eos_token": {
-    "content": "<|im_end|>",
+    "content": "</s>",
     "lstrip": false,
     "normalized": false,
     "rstrip": false,

tokenizer.json

@@ -29,24 +29,6 @@
       "rstrip": false,
       "normalized": false,
       "special": true
-    },
-    {
-      "id": 32000,
-      "content": "<|im_end|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
-    },
-    {
-      "id": 32001,
-      "content": "<|im_start|>",
-      "single_word": false,
-      "lstrip": false,
-      "rstrip": false,
-      "normalized": false,
-      "special": true
     }
   ],
   "normalizer": {

tokenizer_config.json

@@ -23,37 +23,19 @@
       "rstrip": false,
       "single_word": false,
       "special": true
-    },
-    "32000": {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32001": {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
     }
   },
   "additional_special_tokens": [],
   "bos_token": "<s>",
-  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
   "clean_up_tokenization_spaces": false,
-  "eos_token": "<|im_end|>",
+  "eos_token": "</s>",
   "legacy": true,
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": null,
   "sp_model_kwargs": {},
   "spaces_between_special_tokens": false,
   "tokenizer_class": "LlamaTokenizer",
-  "trust_remote_code": false,
   "unk_token": "<unk>",
-  "use_default_system_prompt": true,
-  "use_fast": true
+  "use_default_system_prompt": false
 }