Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+.ipynb_checkpoints/benchmarks-checkpoint.png filter=lfs diff=lfs merge=lfs -text
+benchmarks.png filter=lfs diff=lfs merge=lfs -text
+training_curves_finetune.png filter=lfs diff=lfs merge=lfs -text

fine-tune/chat_template.jinja

@@ -0,0 +1,4 @@
+{{ '<|bos|>' }}{% for message in messages %}{% if message['role'] == 'assistant' %}{{ 'assistant:
+' }}{% generation %}{{ message['content'] + '<|eos|>' }}{% endgeneration %}{% else %}{{ message['role'] + ':
+' + message['content'] + '<|eos|>' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ 'assistant:
+' }}{% endif %}

fine-tune/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 2,
+  "dtype": "bfloat16",
+  "eos_token_id": 0,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 12,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 500000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.13.1",
+  "use_cache": false,
+  "vocab_size": 50432
+}

fine-tune/generation_config.json

@@ -0,0 +1,11 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 2,
+  "eos_token_id": [
+    0,
+    2
+  ],
+  "pad_token_id": 1,
+  "transformers_version": "5.13.1",
+  "use_cache": true
+}

fine-tune/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0092a032fd02d1a09fa5058a4b873d2f4c0333142931105f0cd4122ad8389a6
+size 1668984400

fine-tune/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a93dd2d598793fc8ead576bf8cb661200b0d8716c9ab771e06dc55f89b9a0f1
+size 3338106571

fine-tune/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87b07b911601d04abcbcc91c12340e18730f0dbec6517e92e9000c51517972c9
+size 14645

fine-tune/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7de8280ebbe0d58ed80bc8da8eb199176e46a97927b9f5c9a890cf4f91db7cd
+size 1465

fine-tune/tokenizer_config.json

@@ -0,0 +1,11 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|bos|>",
+  "eos_token": "<|eos|>",
+  "is_local": true,
+  "local_files_only": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|unk|>"
+}

fine-tune/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0f9d0081bb4043be7456aa3a14a783a2a7c582459f60fe9df8e4c3b1b5cbe614
+size 5713

pre-train/.ipynb_checkpoints/config-checkpoint.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 12,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 500000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.13.1",
+  "use_cache": true,
+  "vocab_size": 50432
+}

pre-train/.ipynb_checkpoints/tokenizer_config-checkpoint.json

@@ -0,0 +1,9 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|bos|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|unk|>"
+}

pre-train/config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "max_position_embeddings": 4096,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 12,
+  "pad_token_id": null,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 500000.0,
+    "rope_type": "default"
+  },
+  "tie_word_embeddings": false,
+  "transformers_version": "5.13.1",
+  "use_cache": true,
+  "vocab_size": 50432
+}

pre-train/model-00001-of-00001.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22c5ba6dbff419c1e49a9c15d726c971f3eb77ac7b40b17ae3d42d1b475d76b4
+size 3337945418

pre-train/model.safetensors.index.json

@@ -0,0 +1,226 @@
+{
+  "metadata": {
+    "total_size": 1668959232
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00001.safetensors",
+    "model.norm.weight": "model-00001-of-00001.safetensors",
+    "lm_head.weight": "model-00001-of-00001.safetensors"
+  }
+}

pre-train/tokenizer_config.json

@@ -0,0 +1,9 @@
+{
+  "backend": "tokenizers",
+  "bos_token": "<|bos|>",
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|pad|>",
+  "tokenizer_class": "TokenizersBackend",
+  "unk_token": "<|unk|>"
+}