Upload folder using huggingface_hub

row042/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 %}

row042/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
+}

row042/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"
+}

row042/model-00001-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:522a45d9c2a8a5aac9a4f3d6b366433c5c65f400b8c0eff21b941aee082a915f
+size 262144136

row042/model-00002-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e25d444236a6fdc049072829779336e8d4e55398b8c8b96d90b2cefa6b3ad76
+size 197150040

row042/model-00003-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:250ee4ec72b3574042a70289c29f13ca0cb63cc2fd4dcaab31b2fd3eb693b81f
+size 192955512

row042/model-00004-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4c2bf5d21a816344bb90726dfbbcc418f987118c171a944da6d183a8f52742f
+size 176178184

row042/model-00005-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31412c79d10976ce216cd5520ef8202882aa45236736e89a5c6c0e3b241f5afa
+size 176178184

row042/model-00006-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f23651de40c4cd5ad5cfa92fc19b655fbc1fdfd19a0d2130c723e27fef03df3
+size 176178184

row042/model-00007-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd433ac82b1950f7bdf951654b1e4306df7c4b6ddd35261d3837b5a57ee6384
+size 176178184

row042/model-00008-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e3d324ca59dc8345e927ad09ddd2668e36895c36eb5c067a96665fdefd7bdc0
+size 176178184

row042/model-00009-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9dcdbd375661375f68d37fc66966d8ce1dc9b5621f2feef040b9f168ebe5cf17
+size 176178184

row042/model-00010-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d1d4b92fdd58a7a00af0fdae33b24c79d60d111492d8bc5561327191f792d10
+size 176178184

row042/model-00011-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:606bd4291d1ad06abf4aa706aa6dabae4b93655648bf4ead080a62d9093bec65
+size 176178184

row042/model-00012-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cde80d2eee2bfe67b2c1d734458a076d74bcb56acbae02cc6b9270fd1b293901
+size 176178192

row042/model-00013-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c88296a0402db6175dec85469cfebb82712ba9807079ed7ef4136b0f5459cd96
+size 176178192

row042/model-00014-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8fc1b7171aa131c8e59884d3fbc58625848acca43b2850e9375b1d2d80d01c69
+size 176178192

row042/model-00015-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c7513212b6d9def5394fc987c904df1eaacc7e16e3b030fd341f98c7108f3e2
+size 176178192

row042/model-00016-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e386255114ed9596702e6be0e75a00b86059458c885c55ccff5bc012d26066d
+size 176178192

row042/model-00017-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e03f6f21453247cf8ee840a83a9895ea86ba998f20e29594ebfb54bdf60f25d
+size 176178192

row042/model-00018-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7202d92bd5498fbd0227329050596e9555524121a3423e4d02341f3fd6e47ede
+size 176178192

row042/model-00019-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dc097accef09358fac2e1da1f3ad8018a30e1d017f436fc4bc2d98579656453
+size 176178192

row042/model-00020-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96fc8fd6d3d63c3a9c4d04f5368eb31c27a5f8b0394797710fc48ab519b95e23
+size 176178192

row042/model-00021-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbca1c1d361e5323f4a4884f35748f3a5f51ee5e48cfd96bdae5a6150ea62052
+size 176178192

row042/model-00022-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:73053effa53b72449cc36e242df959470c088df8afdfd420a355a3e2a1b72e60
+size 176178192

row042/model-00023-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea1aa44992f897847a6c693fe2628006e86131d09636f908ad826c58fb7d5e95
+size 262144128

row042/model-00024-of-00024.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da9b7695097ffaa9f5583fb744b9ea787fc34f56a7b68efdd683c7f8491cf8f4
+size 138437280

row042/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"
+  }
+}

row042/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
+  }
+}

row042/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
+}