quants upload

CodeFuse-DeepSeek-33B 6.95bpw exllamav2 quants

README.md

@@ -0,0 +1,10 @@
+---
+license: other
+tasks: 
+- code-generation
+inference: false
+---
+
+### CodeFuse-DeepSeek-33B
+
+ExLlamav2 6.95 bpw h 8 quants of https://huggingface.co/codefuse-ai/CodeFuse-DeepSeek-33B

config.json

@@ -0,0 +1,31 @@
+{
+  "_name_or_path": "..\\workspace\\CodeFuse-DeepSeek-33B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "hidden_act": "silu",
+  "hidden_size": 7168,
+  "initializer_range": 0.02,
+  "intermediate_size": 19200,
+  "max_position_embeddings": 16384,
+  "model_type": "llama",
+  "num_attention_heads": 56,
+  "num_hidden_layers": 62,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": {
+    "factor": 4.0,
+    "type": "linear"
+  },
+  "rope_theta": 100000,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.36.2",
+  "use_cache": true,
+  "vocab_size": 32256
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 32013,
+  "eos_token_id": 32014,
+  "transformers_version": "4.36.2"
+}

model.safetensors.index.json

@@ -0,0 +1,568 @@
+{
+  "metadata": {
+    "total_size": 66685982720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00036-of-00036.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00036.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00036.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00008-of-00036.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00008-of-00036.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00007-of-00036.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00036.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00008-of-00036.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00036.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00036.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00036.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00012-of-00036.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00036.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00036.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00036.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00012-of-00036.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00036.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00013-of-00036.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00014-of-00036.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00016-of-00036.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00016-of-00036.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00015-of-00036.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00036.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00016-of-00036.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00018-of-00036.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00017-of-00036.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00036.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00018-of-00036.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00020-of-00036.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00020-of-00036.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00036.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00021-of-00036.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00020-of-00036.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00022-of-00036.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00021-of-00036.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00022-of-00036.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00024-of-00036.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00024-of-00036.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00023-of-00036.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00004-of-00036.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00004-of-00036.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00036.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00025-of-00036.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00024-of-00036.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00026-of-00036.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00025-of-00036.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00026-of-00036.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00028-of-00036.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00028-of-00036.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00027-of-00036.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00029-of-00036.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00028-of-00036.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00030-of-00036.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00029-of-00036.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00030-of-00036.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00032-of-00036.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00032-of-00036.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00031-of-00036.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00033-of-00036.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00032-of-00036.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00034-of-00036.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00033-of-00036.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00034-of-00036.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00005-of-00036.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00036.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00036-of-00036.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00036-of-00036.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00036-of-00036.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00035-of-00036.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00036-of-00036.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00036-of-00036.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00036-of-00036.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00036-of-00036.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00036-of-00036.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00036-of-00036.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00036-of-00036.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00036-of-00036.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00036-of-00036.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00006-of-00036.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00036.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00006-of-00036.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00006-of-00036.safetensors",
+    "model.norm.weight": "model-00036-of-00036.safetensors"
+  }
+}

output-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cb5ab86fdc48c12ea53295d24d141c42f4bb7b6bc235920ff67d7c4aac5e158f
+size 8569323624

output-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:99f014fd098e4b4c9afd3480567ad8bbedc9ad53ad2c97f77583e01e1347bfe5
+size 8460362288

output-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2b270d6239dc29cbcc2d9cb7595b5c68deb085be25b98f1bd7ed47fe130ea792
+size 8526210444

output-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9537d23bf989d2192f69bb6c217da9f64161b8c15b4c1a70c6589b6acbf0a3fe
+size 3700242360

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,193 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "32000": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32001": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32002": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32003": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32004": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32006": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32007": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32008": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32009": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32010": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32011": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32012": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32013": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32014": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32015": {
+      "content": "<｜fim▁hole｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32016": {
+      "content": "<｜fim▁begin｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32017": {
+      "content": "<｜fim▁end｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32018": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32019": {
+      "content": "<|User|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32020": {
+      "content": "<|Assistant|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "32021": {
+      "content": "<|EOT|>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% set system_message = false %}{% endif %}{% for message in loop_messages %}{% if (message['role'] == 'user' or message['role'] == 'human') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if loop.index0 == 0 and system_message != false %}{% set content = '<s>system\n' + system_message + '\n' %}{% else %}{% set content = '' %}{% endif %}{% if message['role'] == 'user' or message['role'] == 'human' %}{{ content + '<s>human\n' + message['content'] + '\n' }}{% elif message['role'] == 'assistant' or message['role'] == 'bot' %}{{ '<s>bot\n' + message['content'] + '\n' +  eos_token + '\n'}}{% else %}{{ raise_exception('Only user/human and assistant/bot roles are supported!') }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<s>bot\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 16384,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": false
+}