fireplace-13b 1.0

.ipynb_checkpoints/config-checkpoint.json

@@ -1,28 +0,0 @@
-{
-  "_name_or_path": "ValiantLabs/Fireplace-13b",
-  "architectures": [
-    "LlamaForCausalLM"
-  ],
-  "attention_bias": false,
-  "attention_dropout": 0.0,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "hidden_act": "silu",
-  "hidden_size": 5120,
-  "initializer_range": 0.02,
-  "intermediate_size": 13824,
-  "max_position_embeddings": 16384,
-  "model_type": "llama",
-  "num_attention_heads": 40,
-  "num_hidden_layers": 40,
-  "num_key_value_heads": 40,
-  "pretraining_tp": 1,
-  "rms_norm_eps": 1e-05,
-  "rope_scaling": null,
-  "rope_theta": 1000000,
-  "tie_word_embeddings": false,
-  "torch_dtype": "float32",
-  "transformers_version": "4.36.2",
-  "use_cache": true,
-  "vocab_size": 32016
-}

.ipynb_checkpoints/generation_config-checkpoint.json

@@ -1,6 +0,0 @@
-{
-  "_from_model_config": true,
-  "bos_token_id": 1,
-  "eos_token_id": 2,
-  "transformers_version": "4.36.2"
-}

.ipynb_checkpoints/model.safetensors.index-checkpoint.json

@@ -1,370 +0,0 @@
-{
-  "metadata": {
-    "total_size": 52064112640
-  },
-  "weight_map": {
-    "lm_head.weight": "model-00011-of-00011.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00011.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.36.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.36.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.36.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.input_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.mlp.down_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.mlp.up_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.38.input_layernorm.weight": "model-00011-of-00011.safetensors",
-    "model.layers.38.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
-    "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
-    "model.layers.38.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
-    "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
-    "model.layers.38.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
-    "model.layers.38.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
-    "model.layers.38.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
-    "model.layers.39.input_layernorm.weight": "model-00011-of-00011.safetensors",
-    "model.layers.39.mlp.down_proj.weight": "model-00011-of-00011.safetensors",
-    "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00011.safetensors",
-    "model.layers.39.mlp.up_proj.weight": "model-00011-of-00011.safetensors",
-    "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
-    "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
-    "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
-    "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
-    "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00011.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00011.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00011.safetensors",
-    "model.norm.weight": "model-00011-of-00011.safetensors"
-  }
-}

.ipynb_checkpoints/special_tokens_map-checkpoint.json

@@ -1,30 +0,0 @@
-{
-  "additional_special_tokens": [
-    "▁<PRE>",
-    "▁<MID>",
-    "▁<SUF>",
-    "▁<EOT>"
-  ],
-  "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
-  }
-}

.ipynb_checkpoints/tokenizer_config-checkpoint.json

@@ -1,83 +0,0 @@
-{
-  "add_bos_token": true,
-  "add_eos_token": false,
-  "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
-    },
-    "32007": {
-      "content": "▁<PRE>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32008": {
-      "content": "▁<SUF>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32009": {
-      "content": "▁<MID>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    },
-    "32010": {
-      "content": "▁<EOT>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false,
-      "special": true
-    }
-  },
-  "additional_special_tokens": [
-    "▁<PRE>",
-    "▁<MID>",
-    "▁<SUF>",
-    "▁<EOT>"
-  ],
-  "bos_token": "<s>",
-  "clean_up_tokenization_spaces": false,
-  "eos_token": "</s>",
-  "eot_token": "▁<EOT>",
-  "fill_token": "<FILL_ME>",
-  "legacy": null,
-  "middle_token": "▁<MID>",
-  "model_max_length": 1000000000000000019884624838656,
-  "pad_token": "</s>",
-  "prefix_token": "▁<PRE>",
-  "sp_model_kwargs": {},
-  "suffix_token": "▁<SUF>",
-  "tokenizer_class": "LlamaTokenizer",
-  "unk_token": "<unk>",
-  "use_default_system_prompt": false
-}