Upload folder using huggingface_hub

row012/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 %}

row012/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
+}

row012/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"
+}

row012/model-00001-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f873a956908f446fd0fd57712f916848fe940dcb8c8ff8ba537c19d74169018
+size 262144136

row012/model-00002-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea3842d40578d39655c1cfe17cbb0262e03ad44a7f5ccab656748881a73675dd
+size 197150040

row012/model-00003-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3068fb5615664bbcb9d191bd1f5a8d8a14d05377eb9efb076b308dc9812fd231
+size 192955512

row012/model-00004-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2acbaa25f187146bfee1cbeac57fd3ac6da0e4c1f0de7407755d655add0da2ee
+size 176178184

row012/model-00005-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fbd1429cb43b9ebaef7fe6d1195329641437a7630214dd2beddfe801f7a8519
+size 176178184

row012/model-00006-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed8a7c32ce5b41f076670c3f2104eb30748570d30d88a11d68fb4384324f184b
+size 176178184

row012/model-00007-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f59f7ef37f0650534ce4b83377066a55ad1870f3ea8a87b7b37ecd09f953ab63
+size 176178184

row012/model-00008-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:054aac149818b6191e63ab5fbb2113176d2dd5418a5b4629c7981b0d10415451
+size 176178184

row012/model-00009-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:018b91c81541bfced36fa573d0a67d2b0abf10b6cecb712a5e251bee3b4cc503
+size 176178184

row012/model-00010-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9697491b7e89cb6d52e36c7257549245608ef89bf37d469c6c89a5f86e9e0878
+size 176178184

row012/model-00011-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05e049897b8db761179f1150dfe78093c00bcea3b30f0a48fba5c3f3a2808020
+size 176178184

row012/model-00012-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f03c6f48cb61e6b07618796036633b9aabcf456845833ab4c78b1a4b4fb80a45
+size 176178192

row012/model-00013-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d3d73c58028a2d37515aca2cb6ed1cebd9e62d5ec9c0317fc2c3dbb798febbe
+size 176178192

row012/model-00014-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac9597e8162d87fbe5e136e1f08f69c864c4b16ed483bf98b1dbbb00f55388f4
+size 176178192

row012/model-00015-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfa3f551bb3543a50f8f105b3352582953adaf6c1e437b3cd404d919a07ce934
+size 176178192

row012/model-00016-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c3324c0f8c73aabce59a2552da27b1b9325c024f73995b4de7a80295bcda15df
+size 176178192

row012/model-00017-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d8117fa236830563f902067792a1cdc46f955e650e11e46ebb18f129bd38b441
+size 176178192

row012/model-00018-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f9f7cce4c15678cf3b373374ab9229b96840866d6abc6396ce2b2b3d546063
+size 176178192

row012/model-00019-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:714d06b56e603c2a204beb463ae6c47c191b6a3ee32f1dbaa05419839eca4770
+size 176178192

row012/model-00020-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:24b53ee901e6ddf4f9c6974c16d7919a5aee43cc8ecb674b50a436d550e1e650
+size 176178192

row012/model-00021-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd833aef29d3fc9b636fbdd593187bdbe58c1f27b63b7cd2cb9548b6bc48e735
+size 176178192

row012/model-00022-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c01bebeb5ba6342b5b8ad0b5bd5bce70e80c5a533ee45f91d7e1ed1872d594e5
+size 176178192

row012/model-00023-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:684b951c7fd0853f79003b423aea2b257ff14e1c42e8c7bbea627e960d197316
+size 262144128

row012/model-00024-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02416447832351e347c55122808f7cc76ffbe32b80544d695a4029780e591209
+size 138437280

row012/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"
+  }
+}

row012/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
+  }
+}

row012/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
+}