Upload folder using huggingface_hub

row004/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 %}

row004/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
+}

row004/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"
+}

row004/model-00001-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e41dedd6781b47b9f1254940777ac0c03e0efb090b3f36f8c71585cc10338670
+size 262144136

row004/model-00002-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cc0cec67c94f4ba66d656067122854487fd1d1588f399b3d9ea1477e5249c578
+size 197150040

row004/model-00003-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c94ce5d0c667c95e90c73fd0bf7a652096037fc3674e563b35074a1ccd9a3011
+size 192955512

row004/model-00004-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bff577bf6395db854bd4362ee0cbac37fd6ca3f09ee738d58afdf244260a7104
+size 176178184

row004/model-00005-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f8d7481437aec9e0909aafea635e8fd11bb73173d0ef757f69877b0eb4c9bca4
+size 176178184

row004/model-00006-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bf12758b7f9b58c9345d0934cbb3aa720b3125dbb9fc0d68874a6853b1915377
+size 176178184

row004/model-00007-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa664ef87aecdb35b95dc306799e026da20cc6f765f74717e1cd9f45fa942661
+size 176178184

row004/model-00008-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cd5cadb428ecc977d2ce5fbbdf228431ec3d5ba6f7c374aa8649442b54fcebc
+size 176178184

row004/model-00009-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3fb3485db3e608ec9767f22081c2492efeff3624e2bd372572925d89f8791457
+size 176178184

row004/model-00010-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d35460f36461a2d29054859819d4136b5eb5919231ad1facdbaeca97b8acfc31
+size 176178184

row004/model-00011-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e0a7c045477b769910e0c5d26c4f0cc717d672a6ddf041dfeaead26b1770db5
+size 176178184

row004/model-00012-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:655bd6938e9ed63bac04b258c6ef2bea5394a03339131922799f12a8bee36d25
+size 176178192

row004/model-00013-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e84cb7d7d338895fec3d230a832926063385e230ac8ef0e0a8e13fae5561672c
+size 176178192

row004/model-00014-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a578454661e2342423a425cb7983e66b7319aca86f9c2105855f9f6130ffe888
+size 176178192

row004/model-00015-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1689e00163acf687032526e5f9d3052916dbd96e10b49a171e8efbbcd1756c68
+size 176178192

row004/model-00016-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92a1fe5cc97165c85304dfdfd559232775fe1bc20c1ff817e2a8affe91d8871d
+size 176178192

row004/model-00017-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8ea1726be7866dcc38dddd6f76de3633221864cf2e42c082119ad6a2ab941d75
+size 176178192

row004/model-00018-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee2de8a3922a1daf939a8716a948d0b4ab299d7d76d95e6ce09a7b015947587a
+size 176178192

row004/model-00019-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7421d584915b957758a370bf1c5031dd6ec337ea9872b25331ee8b8fe69c1c78
+size 176178192

row004/model-00020-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c975b9e4115dcc3e597371c5c5aa9225710b75437d7a84080c7059b6515b8b3
+size 176178192

row004/model-00021-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2166884eb550ce4f639cc271b64e2f4b02cfcf3df37ca5c3fd93d6cccb916bda
+size 176178192

row004/model-00022-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:97a89a57a6f4e53d69c9ff444428d3374f994f35f035f4e2807332c605734c0e
+size 176178192

row004/model-00023-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:899ede24fe29653c5aa9c2fbd99a6ede7c066eb4e5f9bf2de98c54e5d82835a4
+size 262144128

row004/model-00024-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bedad306a0e32a7f0f3f03dc68f0e68d6dcd5e7ec87a17b19e64376e84a9735f
+size 138437280

row004/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"
+  }
+}

row004/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
+  }
+}

row004/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
+}