Upload folder using huggingface_hub

config.json

@@ -0,0 +1,32 @@
+{
+  "architectures": [
+    "Starcoder2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "bos_token_id": 0,
+  "dtype": "bfloat16",
+  "embedding_dropout": 0.1,
+  "eos_token_id": 0,
+  "hidden_act": "gelu_pytorch_tanh",
+  "hidden_size": 3072,
+  "initializer_range": 0.018042,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 16384,
+  "mlp_type": "default",
+  "model_type": "starcoder2",
+  "norm_epsilon": 1e-05,
+  "norm_type": "layer_norm",
+  "num_attention_heads": 24,
+  "num_hidden_layers": 30,
+  "num_key_value_heads": 2,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "residual_dropout": 0.1,
+  "rope_scaling": null,
+  "rope_theta": 999999.4420358813,
+  "sliding_window": 4096,
+  "transformers_version": "4.57.1",
+  "use_bias": true,
+  "use_cache": true,
+  "vocab_size": 49152
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:321dfab2fc552ca8cdd68ba92dd9cc3ba2e2856817b1452e63b82c7e7245a8d1
+size 4949934200

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa8c20cf809a8338533a70330fc6ac18db9d3b01cc14a59f95e1fa904bbcff8a
+size 1110874944

model.safetensors.index.json

@@ -0,0 +1,492 @@
+{
+  "metadata": {
+    "total_parameters": 3030377472,
+    "total_size": 6060754944
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.c_fc.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.c_fc.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.c_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.c_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.c_fc.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.c_fc.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.c_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.c_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.bias": "model-00002-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "score.weight": "model-00002-of-00002.safetensors"
+  }
+}

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb8c085208851f659b581c4e12d4e92bf6dba6a609f7f638f7f9353b9818757
+size 12121931191

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:635280b947b0e77134523506de917453973d12ae936b14db993c4df92fd1ddbe
+size 14645

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ccbcc5e53c9022df1dfec64e771e1cacaf2516aa1eb2a70e2c4324d155c2124e
+size 1465

special_tokens_map.json

@@ -0,0 +1,45 @@
+{
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|endoftext|>",
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,189 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<fim_prefix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<fim_middle>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<fim_suffix>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<fim_pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "5": {
+      "content": "<filename>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "6": {
+      "content": "<gh_stars>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "7": {
+      "content": "<issue_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "8": {
+      "content": "<issue_comment>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "9": {
+      "content": "<issue_closed>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "10": {
+      "content": "<jupyter_start>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "11": {
+      "content": "<jupyter_text>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "12": {
+      "content": "<jupyter_code>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "13": {
+      "content": "<jupyter_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "14": {
+      "content": "<empty_output>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "15": {
+      "content": "<commit_before>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "16": {
+      "content": "<commit_msg>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "17": {
+      "content": "<commit_after>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "18": {
+      "content": "<reponame>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|endoftext|>",
+    "<fim_prefix>",
+    "<fim_middle>",
+    "<fim_suffix>",
+    "<fim_pad>",
+    "<filename>",
+    "<gh_stars>",
+    "<issue_start>",
+    "<issue_comment>",
+    "<issue_closed>",
+    "<jupyter_start>",
+    "<jupyter_text>",
+    "<jupyter_code>",
+    "<jupyter_output>",
+    "<empty_output>",
+    "<commit_before>",
+    "<commit_msg>",
+    "<commit_after>",
+    "<reponame>"
+  ],
+  "bos_token": "<|endoftext|>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "extra_special_tokens": {},
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "tokenizer_class": "GPT2Tokenizer",
+  "truncation_side": "right",
+  "unk_token": "<|endoftext|>",
+  "vocab_size": 49152
+}

trainer_state.json

@@ -0,0 +1,341 @@
+{
+  "best_global_step": 4098,
+  "best_metric": 0.6050512445095169,
+  "best_model_checkpoint": "./saved_models/starcoder2-1b/checkpoint-4098",
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 4098,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07321314175894574,
+      "grad_norm": 6272.0,
+      "learning_rate": 2.4146341463414637e-06,
+      "loss": 20.953,
+      "step": 100
+    },
+    {
+      "epoch": 0.14642628351789147,
+      "grad_norm": 1464.0,
+      "learning_rate": 4.853658536585366e-06,
+      "loss": 15.9012,
+      "step": 200
+    },
+    {
+      "epoch": 0.2196394252768372,
+      "grad_norm": 1408.0,
+      "learning_rate": 7.292682926829269e-06,
+      "loss": 11.7032,
+      "step": 300
+    },
+    {
+      "epoch": 0.29285256703578294,
+      "grad_norm": 820.0,
+      "learning_rate": 9.731707317073171e-06,
+      "loss": 8.3928,
+      "step": 400
+    },
+    {
+      "epoch": 0.36606570879472866,
+      "grad_norm": 776.0,
+      "learning_rate": 9.758676789587853e-06,
+      "loss": 7.3384,
+      "step": 500
+    },
+    {
+      "epoch": 0.4392788505536744,
+      "grad_norm": 328.0,
+      "learning_rate": 9.487527114967463e-06,
+      "loss": 6.3891,
+      "step": 600
+    },
+    {
+      "epoch": 0.5124919923126201,
+      "grad_norm": 264.0,
+      "learning_rate": 9.216377440347072e-06,
+      "loss": 6.458,
+      "step": 700
+    },
+    {
+      "epoch": 0.5857051340715659,
+      "grad_norm": 207.0,
+      "learning_rate": 8.945227765726682e-06,
+      "loss": 6.1615,
+      "step": 800
+    },
+    {
+      "epoch": 0.6589182758305115,
+      "grad_norm": 147.0,
+      "learning_rate": 8.674078091106292e-06,
+      "loss": 6.2411,
+      "step": 900
+    },
+    {
+      "epoch": 0.7321314175894573,
+      "grad_norm": 166.0,
+      "learning_rate": 8.4029284164859e-06,
+      "loss": 5.9795,
+      "step": 1000
+    },
+    {
+      "epoch": 0.805344559348403,
+      "grad_norm": 217.0,
+      "learning_rate": 8.13177874186551e-06,
+      "loss": 6.283,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8785577011073488,
+      "grad_norm": 442.0,
+      "learning_rate": 7.86062906724512e-06,
+      "loss": 5.8614,
+      "step": 1200
+    },
+    {
+      "epoch": 0.9517708428662945,
+      "grad_norm": 328.0,
+      "learning_rate": 7.589479392624729e-06,
+      "loss": 5.8366,
+      "step": 1300
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5768667642752562,
+      "eval_loss": 0.6696338653564453,
+      "eval_runtime": 29.2163,
+      "eval_samples_per_second": 93.509,
+      "eval_steps_per_second": 11.706,
+      "step": 1366
+    },
+    {
+      "epoch": 1.0248924681980416,
+      "grad_norm": 286.0,
+      "learning_rate": 7.318329718004339e-06,
+      "loss": 5.8651,
+      "step": 1400
+    },
+    {
+      "epoch": 1.0981056099569872,
+      "grad_norm": 172.0,
+      "learning_rate": 7.047180043383949e-06,
+      "loss": 5.7271,
+      "step": 1500
+    },
+    {
+      "epoch": 1.171318751715933,
+      "grad_norm": 302.0,
+      "learning_rate": 6.776030368763558e-06,
+      "loss": 5.7241,
+      "step": 1600
+    },
+    {
+      "epoch": 1.2445318934748788,
+      "grad_norm": 236.0,
+      "learning_rate": 6.504880694143168e-06,
+      "loss": 5.8987,
+      "step": 1700
+    },
+    {
+      "epoch": 1.3177450352338245,
+      "grad_norm": 152.0,
+      "learning_rate": 6.233731019522777e-06,
+      "loss": 5.6734,
+      "step": 1800
+    },
+    {
+      "epoch": 1.3909581769927701,
+      "grad_norm": 144.0,
+      "learning_rate": 5.962581344902386e-06,
+      "loss": 5.6935,
+      "step": 1900
+    },
+    {
+      "epoch": 1.464171318751716,
+      "grad_norm": 180.0,
+      "learning_rate": 5.691431670281996e-06,
+      "loss": 5.6752,
+      "step": 2000
+    },
+    {
+      "epoch": 1.5373844605106617,
+      "grad_norm": 398.0,
+      "learning_rate": 5.420281995661606e-06,
+      "loss": 5.5941,
+      "step": 2100
+    },
+    {
+      "epoch": 1.6105976022696074,
+      "grad_norm": 172.0,
+      "learning_rate": 5.149132321041215e-06,
+      "loss": 5.7496,
+      "step": 2200
+    },
+    {
+      "epoch": 1.6838107440285532,
+      "grad_norm": 225.0,
+      "learning_rate": 4.877982646420824e-06,
+      "loss": 5.6826,
+      "step": 2300
+    },
+    {
+      "epoch": 1.757023885787499,
+      "grad_norm": 402.0,
+      "learning_rate": 4.606832971800434e-06,
+      "loss": 5.6096,
+      "step": 2400
+    },
+    {
+      "epoch": 1.8302370275464446,
+      "grad_norm": 396.0,
+      "learning_rate": 4.335683297180044e-06,
+      "loss": 5.7266,
+      "step": 2500
+    },
+    {
+      "epoch": 1.9034501693053905,
+      "grad_norm": 160.0,
+      "learning_rate": 4.064533622559653e-06,
+      "loss": 5.6795,
+      "step": 2600
+    },
+    {
+      "epoch": 1.976663311064336,
+      "grad_norm": 188.0,
+      "learning_rate": 3.7933839479392624e-06,
+      "loss": 5.5912,
+      "step": 2700
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5955344070278185,
+      "eval_loss": 0.671582818031311,
+      "eval_runtime": 29.3299,
+      "eval_samples_per_second": 93.147,
+      "eval_steps_per_second": 11.66,
+      "step": 2732
+    },
+    {
+      "epoch": 2.049784936396083,
+      "grad_norm": 177.0,
+      "learning_rate": 3.5222342733188724e-06,
+      "loss": 5.5596,
+      "step": 2800
+    },
+    {
+      "epoch": 2.122998078155029,
+      "grad_norm": 398.0,
+      "learning_rate": 3.251084598698482e-06,
+      "loss": 5.6186,
+      "step": 2900
+    },
+    {
+      "epoch": 2.1962112199139745,
+      "grad_norm": 227.0,
+      "learning_rate": 2.979934924078091e-06,
+      "loss": 5.5111,
+      "step": 3000
+    },
+    {
+      "epoch": 2.2694243616729204,
+      "grad_norm": 236.0,
+      "learning_rate": 2.708785249457701e-06,
+      "loss": 5.5668,
+      "step": 3100
+    },
+    {
+      "epoch": 2.342637503431866,
+      "grad_norm": 105.0,
+      "learning_rate": 2.4376355748373105e-06,
+      "loss": 5.4987,
+      "step": 3200
+    },
+    {
+      "epoch": 2.4158506451908117,
+      "grad_norm": 195.0,
+      "learning_rate": 2.16648590021692e-06,
+      "loss": 5.5228,
+      "step": 3300
+    },
+    {
+      "epoch": 2.4890637869497576,
+      "grad_norm": 194.0,
+      "learning_rate": 1.8953362255965294e-06,
+      "loss": 5.5394,
+      "step": 3400
+    },
+    {
+      "epoch": 2.562276928708703,
+      "grad_norm": 185.0,
+      "learning_rate": 1.624186550976139e-06,
+      "loss": 5.5566,
+      "step": 3500
+    },
+    {
+      "epoch": 2.635490070467649,
+      "grad_norm": 260.0,
+      "learning_rate": 1.3530368763557487e-06,
+      "loss": 5.6079,
+      "step": 3600
+    },
+    {
+      "epoch": 2.708703212226595,
+      "grad_norm": 168.0,
+      "learning_rate": 1.081887201735358e-06,
+      "loss": 5.63,
+      "step": 3700
+    },
+    {
+      "epoch": 2.7819163539855403,
+      "grad_norm": 171.0,
+      "learning_rate": 8.107375271149676e-07,
+      "loss": 5.5637,
+      "step": 3800
+    },
+    {
+      "epoch": 2.855129495744486,
+      "grad_norm": 151.0,
+      "learning_rate": 5.39587852494577e-07,
+      "loss": 5.4782,
+      "step": 3900
+    },
+    {
+      "epoch": 2.928342637503432,
+      "grad_norm": 184.0,
+      "learning_rate": 2.6843817787418654e-07,
+      "loss": 5.5504,
+      "step": 4000
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6050512445095169,
+      "eval_loss": 0.6602969765663147,
+      "eval_runtime": 29.1681,
+      "eval_samples_per_second": 93.664,
+      "eval_steps_per_second": 11.725,
+      "step": 4098
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 4098,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.899631267339305e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58c1fa3c9190494903fbfcbb87cda9eea56beb624e2692c06d3aca9dde1272b8
+size 5777