Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+base_model/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,9 @@
+---
+license: other
+language:
+- en
+tags:
+- autoquant
+- exl2
+---
+chatml, 3k rp entries in this step.

base_model/config.json

@@ -0,0 +1,29 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 65536,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 50,
+  "num_key_value_heads": 8,
+  "pad_token_id": 10,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_version": "2025.4.7",
+  "use_cache": true,
+  "vocab_size": 131072
+}

base_model/generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "max_length": 65536,
+  "pad_token_id": 10,
+  "transformers_version": "4.51.3"
+}

base_model/model.safetensors.index.json

@@ -0,0 +1,460 @@
+{
+  "metadata": {
+    "total_size": 29948364800
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00007-of-00007.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.norm.weight": "model-00006-of-00007.safetensors"
+  }
+}

base_model/special_tokens_map.json

@@ -0,0 +1,6 @@
+{
+  "bos_token": "<s>",
+  "eos_token": "<|im_end|>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

base_model/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d7cdf4abdcf2582c9f4d0b852fcbacd98f42dc86c58f8f46b4bb75e03274496
+size 17078322

cal_data.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5492fa7d8132db3a9c5445ab2493fbd4197748d8ed94fd1f4a0eb3f9462e7d38
+size 1638488

hidden_states.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ce75b5f36f08f14aa3f7df48de97210eebc548630a50a09cc046bdbd25ac85b
+size 2097160800

out_tensor/lm_head.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:49e4c13231b939b486704a6b5c9606b942fdd8e480c18ae131effd0004063e07
+size 531124904

out_tensor/model.layers.0.mlp.down_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1f64e99e602fd46f8c6085f9a980d3fb3c92c18c8fa022d931d7040256d7c14a
+size 49417368

out_tensor/model.layers.0.mlp.gate_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43457fa45d0b6206ad317521c30c4c780e8af8a6cd1279ecc157e680a77fc7cb
+size 47961560

out_tensor/model.layers.0.mlp.up_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10bb76333f28c62d5a2595db26e7bd2c6f83dd64c6961f8a399b8ceaea700457
+size 49337808

out_tensor/model.layers.0.self_attn.k_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a20bfbec93bf2b17fac4cdc8aafeae084a7c41259cf8544543f582f8a13afec
+size 3446240

out_tensor/model.layers.0.self_attn.o_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58277b67c374f177ee8353b8b4eb5e49dc526b345e9347b62b1adcfd5b185afa
+size 13718824

out_tensor/model.layers.0.self_attn.q_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9563eb6496031d5bc3298b1ebe9995f5852de28e823d9b947829da68a191b54b
+size 13719016

out_tensor/model.layers.0.self_attn.v_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a9953e93458fdc6854860c6a65b46b71a07b1c8f1d2e8d258823a56a4f87a709
+size 4036064

out_tensor/model.layers.1.mlp.down_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15e64427e858d484aaecaca8dfcac07388787ee928797be5c7983d10467edfb8
+size 39958820

out_tensor/model.layers.1.mlp.gate_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd1a51458ddd225688b746614774ba2a668b6c23022d7f41a3277af0ed8df0c
+size 37925640

out_tensor/model.layers.1.mlp.up_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ca2f048472901d306b2243bc2c7ca8ec9d14e83251244b639b9ea6a425fc8c84
+size 39301880

out_tensor/model.layers.1.self_attn.k_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9d767e08efbd29ac20b8d3fe12722c90c91db359eda664db898a52c49d5e4089
+size 4036064

out_tensor/model.layers.1.self_attn.o_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1715e77c8efb909963872fba7fc8eacb206fa1c0de5aff2e4ada99f9685a7fdd
+size 16074024

out_tensor/model.layers.1.self_attn.q_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:523f379990335136b1458aa5badb83cdd9cb01be884efcfd0bd302b881a366f4
+size 16078312

out_tensor/model.layers.1.self_attn.v_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:612e6c6ae3e4c7d06641d6efe3990fc6a18171f3af0f5b9b2f507dfa564a2325
+size 5346784

out_tensor/model.layers.10.mlp.down_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1970461725f2f6ea2b393f33271d30fc819146e8ace0101547d8b4766b958893
+size 39791776

out_tensor/model.layers.10.mlp.gate_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1089becc2a69d4e16c7a95ae8d0e7acbc2d1e33552c80d5853e99bb33575d857
+size 37869024

out_tensor/model.layers.10.mlp.up_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2489c7becc6448c5226c1aecb93f93f57fa1245d6553d42bbe84bdadb1188e9b
+size 37869016

out_tensor/model.layers.10.self_attn.k_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7440033b1fd13bedc568d4e59d339ff9a16c293343b26f59c41bc1a6c1fb2d5a
+size 2663184

out_tensor/model.layers.10.self_attn.o_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a57e72bb0a1603b9c8656a8ce55a2092317050314c7d07513f0877d8e1a91bb
+size 10584808

out_tensor/model.layers.10.self_attn.q_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:780f47a8a3878c84aa9b8bc91aba719fbdffff72f5d2246d02e8f20f223c8830
+size 10588952

out_tensor/model.layers.10.self_attn.v_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:72ee589a0ce5385e3abdce21cec32a7560dba570413ce4ce375ed7b087f58771
+size 2683904

out_tensor/model.layers.11.mlp.down_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c56d7637e60352e0cffe2c5f00019bfd88be3f09a53e49b338df9d4e7feb3b5a
+size 39791776

out_tensor/model.layers.11.mlp.gate_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2a8e97bc800bb2f1fcff1444659f0fc01a151a7db95dce0469ff9e269e355be
+size 37869024

out_tensor/model.layers.11.mlp.up_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15309484840bdd81590e96d77dbaed039c6347be858bd37c7f5db759820514f5
+size 37869016

out_tensor/model.layers.11.self_attn.k_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:12ed68413d4e1651239398e6343cc6e0483d8bd7a5c7049d460d1ab804599c16
+size 3446248

out_tensor/model.layers.11.self_attn.o_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8941d5be370161365a963b8c26af16be5a5797ae42c6f118a263f9bd17066eba
+size 13718824

out_tensor/model.layers.11.self_attn.q_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ab65a5413878e8a5c3bec26c064bf8080117a1175ec33a9cffa2925ec2003a74
+size 13719016

out_tensor/model.layers.11.self_attn.v_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ced98c5104e43a679d8afccb01ec6088e12a60ec121fc17277fc6541f8bc6255
+size 4036072

out_tensor/model.layers.12.mlp.down_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25267d59879223ffeede3d7c19525d7a7bd21939db6c488ffb8db893edb17d19
+size 39791776

out_tensor/model.layers.12.mlp.gate_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3649b9238c53848fa466c160ab3b64d5dfa32d073ce1ad00263e0363b1242bbe
+size 37869024

out_tensor/model.layers.12.mlp.up_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:526c5eacf2d9edd94aaa4a0884689c0d64e550be8e7733c9b1d73cf19f43d985
+size 37869016

out_tensor/model.layers.12.self_attn.k_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3628ee69bc87e837b6e49f3edb9803caf1bb94dbc7dcf0e06eb0841690132e0
+size 3446248

out_tensor/model.layers.12.self_attn.o_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41130d84415a469117f4ae2a8a96b5aa267f4eaf6a2e25e6f6c770c130587b8c
+size 13718824

out_tensor/model.layers.12.self_attn.q_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91eb12b9ac5a0bb9d59e09ae4dda082d5a0d695c959d4a66538f80e56e6347a0
+size 13719016

out_tensor/model.layers.12.self_attn.v_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:666652e92c13b5bc53bf693b209b18e54bee7cd768bd813b8660ffa40492be78
+size 4036072

out_tensor/model.layers.13.mlp.down_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:390ac936d71829053e37a856fec5a4486cb57f2a74f9cd46c98f74676a7d1afd
+size 38975788

out_tensor/model.layers.13.mlp.gate_proj.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6a67c489f040d4ddab42ed8c9f5445bb026bf0f0c4ffa07302ac252aa47ed56
+size 37008136