Upload folder using huggingface_hub

row016/chat_template.jinja

@@ -0,0 +1,15 @@
+{% for message in messages %}
+{% if message['role'] == 'user' %}
+{{ '<|user|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'system' %}
+{{ '<|system|>
+' + message['content'] + eos_token }}
+{% elif message['role'] == 'assistant' %}
+{{ '<|assistant|>
+'  + message['content'] + eos_token }}
+{% endif %}
+{% if loop.last and add_generation_prompt %}
+{{ '<|assistant|>' }}
+{% endif %}
+{% endfor %}

row016/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 64,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.53.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

row016/generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 2048,
+  "pad_token_id": 0,
+  "transformers_version": "4.53.0"
+}

row016/model-00001-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dbc4e4b2f8d2b914e06d161cc276297ca28573a61ec5f521a52de2a06416a6e
+size 262144136

row016/model-00002-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48a7ddbc8ba95c545eaf38417bab121b3dd256104007f66b15feca7a3d1fd9ed
+size 197150040

row016/model-00003-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ef1fb4085e5701852c1faea724c879b2824e724bd0f1ee107672cf8dd8334433
+size 192955512

row016/model-00004-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:263d02127e947a3635ad67d0254ce75c9d74a9b6f1c43947790e195a71dea940
+size 176178184

row016/model-00005-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:093dcb206de2281c8acccd15ab73c3f34f51a168d71d4a1b0af8f828f959a46c
+size 176178184

row016/model-00006-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6d4aaa549e32bfef449dde0f89f7b3205c96d8d802ba7ba908dd459830eb23f9
+size 176178184

row016/model-00007-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d54be58da5d2da68c888ccc156b2c9f220ca8000479af6d67ed718cb3137614
+size 176178184

row016/model-00008-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f057b2a45c73018a423eb887de5eecae851b8d1434789eba4a7622ebcfd29dd8
+size 176178184

row016/model-00009-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdb096a2b154a7d198ccacf6ef19b521392886ff0639e6dce4e9b20cd648c71e
+size 176178184

row016/model-00010-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:995ceb36f8b6301c00375e32041b337f82e40b9f134ede1bd22879b058c1edf0
+size 176178184

row016/model-00011-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f6f1d2e5cee4ccff0f821c787951377862d75185d31f1c16916f05dda8e80a
+size 176178184

row016/model-00012-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7f827ddde5d9a792aa86b3eb8dc333dffbc92d729d05384e50f16bee0abc4d6
+size 176178192

row016/model-00013-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bea1ae026f62578202554b33706ca34ad71358e5a9325d836a49bb6dfed2da0d
+size 176178192

row016/model-00014-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bab7ad20dee974d3b37ff422e4fb8ef93c96de3be429b9edb570e524dca355f
+size 176178192

row016/model-00015-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5443cb067a6d88c987cf3d34b0838d3a339e86983899e4abcfd398754fcc1ee
+size 176178192

row016/model-00016-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1eea7de5555787b221ef2680d36155a4e4a1d2dc87dee7929ead799d9b9baef7
+size 176178192

row016/model-00017-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56c99137f34f36de6696810952bbc0f17798d3519d93a8fac6cfa3c4db769dc7
+size 176178192

row016/model-00018-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e5bb8354832d029d36becc4294d1966e83581456d0be984c06a7868f5b1a7da
+size 176178192

row016/model-00019-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:276d1adce51f8aae44f166141b4ae85fb9f09462f6091695199f8100a44ea996
+size 176178192

row016/model-00020-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6740c8047506059d4811006701e913fe55cb816662189b264f10fc9cff51a99e
+size 176178192

row016/model-00021-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a91deed27ab64a1c15e2b4557bbacdd9cda1a71f60feee078c55b3a6d97d8ad
+size 176178192

row016/model-00022-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52789b5fbeffb0ce1b529e4c638a4ac191a905c17abe4838505f748dd8f26e38
+size 176178192

row016/model-00023-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:44af17b7fc8321d35774ef5fa043114a0b25d0c7fe72683feb633a128f62e278
+size 262144128

row016/model-00024-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14a40cc042906472ebf521ef8329301140f4509c7dbc762879d4e89796881256
+size 138437280

row016/model.safetensors.index.json

@@ -0,0 +1,209 @@
+{
+  "metadata": {
+    "total_parameters": 1100048384,
+    "total_size": 4400193536
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00023-of-00024.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00024.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00024.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00024.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00024.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00002-of-00024.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00024.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00024.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00024.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00024.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00024.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00003-of-00024.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00003-of-00024.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00024.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00003-of-00024.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00024.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00024.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00024.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00024.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00024.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00012-of-00024.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00012-of-00024.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00012-of-00024.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00012-of-00024.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00012-of-00024.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00011-of-00024.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00024.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00011-of-00024.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00024.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00013-of-00024.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00013-of-00024.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00013-of-00024.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00013-of-00024.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00013-of-00024.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00012-of-00024.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00012-of-00024.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00012-of-00024.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00012-of-00024.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00014-of-00024.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00014-of-00024.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00014-of-00024.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00014-of-00024.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00014-of-00024.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00013-of-00024.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00013-of-00024.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00013-of-00024.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00013-of-00024.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00015-of-00024.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00015-of-00024.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00015-of-00024.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00015-of-00024.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00015-of-00024.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00014-of-00024.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00014-of-00024.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00014-of-00024.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00014-of-00024.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00016-of-00024.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00016-of-00024.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00016-of-00024.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00016-of-00024.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00016-of-00024.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00015-of-00024.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00015-of-00024.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00015-of-00024.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00015-of-00024.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00017-of-00024.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00017-of-00024.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00017-of-00024.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00017-of-00024.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00017-of-00024.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00016-of-00024.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00016-of-00024.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00016-of-00024.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00016-of-00024.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00018-of-00024.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00018-of-00024.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00018-of-00024.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00018-of-00024.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00018-of-00024.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00017-of-00024.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00017-of-00024.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00017-of-00024.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00017-of-00024.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00019-of-00024.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00019-of-00024.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00019-of-00024.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00019-of-00024.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00019-of-00024.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00018-of-00024.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00018-of-00024.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00018-of-00024.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00018-of-00024.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00020-of-00024.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00020-of-00024.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00020-of-00024.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00020-of-00024.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00020-of-00024.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00019-of-00024.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00019-of-00024.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00019-of-00024.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00019-of-00024.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00021-of-00024.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00021-of-00024.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00021-of-00024.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00021-of-00024.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00021-of-00024.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00020-of-00024.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00020-of-00024.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00020-of-00024.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00020-of-00024.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00004-of-00024.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00004-of-00024.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00024.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00004-of-00024.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00024.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00024.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00024.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00024.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00024.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00022-of-00024.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00022-of-00024.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00022-of-00024.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00022-of-00024.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00022-of-00024.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00021-of-00024.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00021-of-00024.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00021-of-00024.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00021-of-00024.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00024-of-00024.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00024-of-00024.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00024-of-00024.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00024-of-00024.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00024-of-00024.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00022-of-00024.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00022-of-00024.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00022-of-00024.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00022-of-00024.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00005-of-00024.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00005-of-00024.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00005-of-00024.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00005-of-00024.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00024.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00024.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00024.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00024.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00024.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00006-of-00024.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00006-of-00024.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00024.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00006-of-00024.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00024.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00024.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00024.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00024.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00024.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00007-of-00024.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00007-of-00024.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00007-of-00024.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00007-of-00024.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00007-of-00024.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00006-of-00024.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00006-of-00024.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00006-of-00024.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00006-of-00024.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00008-of-00024.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00008-of-00024.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00008-of-00024.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00008-of-00024.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00008-of-00024.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00007-of-00024.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00007-of-00024.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00007-of-00024.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00007-of-00024.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00009-of-00024.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00009-of-00024.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00009-of-00024.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00009-of-00024.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00024.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00008-of-00024.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00008-of-00024.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00008-of-00024.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00008-of-00024.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00010-of-00024.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00010-of-00024.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00010-of-00024.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00010-of-00024.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00024.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00024.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00024.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00024.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00024.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00011-of-00024.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00011-of-00024.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00011-of-00024.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00011-of-00024.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00024.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00024.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00010-of-00024.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00024.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00024.safetensors",
+    "model.norm.weight": "model-00024-of-00024.safetensors"
+  }
+}

row016/special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "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": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

row016/tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": {},
+  "legacy": false,
+  "model_max_length": 2048,
+  "pad_token": "</s>",
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}