Upload folder using huggingface_hub

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "meta-llama/Meta-Llama-3-8B",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.42.4"
+}

model-00001-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:842cc595413853c02b000cf645989d672102937c5a0d0e80a3db58119232459f
+size 4890830656

model-00002-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:663918bc379145b46c50ae1c724ee27c28bfb5817f6314691ccb50fa43bc16d5
+size 4839160208

model-00003-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fa395ed591b8b01555aa0df31c476ec3ce25af37616b9d74ce71b1770fc31fb
+size 4772216624

model-00004-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8eef95ad04200f59a028758845f3ec55c133c1bc60eb66684eb76b027610ca05
+size 4839160328

model-00005-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:157f4d4deb3cfeec024a8c296d0ab26536f29d20b6d7ca8c004b0f4a7a92d8ea
+size 4772216664

model-00006-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa8c0b44d8c9060f37f388b4d7af059ce02574ba83f7f53fdf8f4587bbbdd735
+size 4839160328

model-00007-of-00007.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614421300087204453bdf282274d86a4fa9861bd5e1b0431230d10615ab14b41
+size 3210333760

model.safetensors.index.json

@@ -0,0 +1,746 @@
+{
+  "metadata": {
+    "total_size": 32162988032
+  },
+  "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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.lora_B.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.mlp.up_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.k_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.o_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.q_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.0.self_attn.v_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.lora_B.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.mlp.up_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.k_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.o_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.q_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.1.self_attn.v_proj.lora_B.default.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-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.lora_A.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.lora_B.default.weight": "model-00004-of-00007.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.lora_B.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.lora_B.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.mlp.up_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.k_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.o_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.q_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.2.self_attn.v_proj.lora_B.default.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-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.lora_A.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.lora_B.default.weight": "model-00005-of-00007.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.k_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.o_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.q_proj.lora_B.default.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.lora_A.default.weight": "model-00001-of-00007.safetensors",
+    "model.layers.3.self_attn.v_proj.lora_B.default.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-00007-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.lora_A.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.lora_B.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.lora_A.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.lora_B.default.weight": "model-00006-of-00007.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.lora_A.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.lora_B.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.lora_A.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.lora_B.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.lora_A.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.lora_B.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.lora_A.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.lora_B.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.lora_A.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.lora_B.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.lora_A.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.lora_B.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.lora_A.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.lora_B.default.weight": "model-00007-of-00007.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.mlp.up_proj.lora_B.default.weight": "model-00002-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.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.mlp.up_proj.lora_B.default.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.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.k_proj.lora_B.default.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.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.o_proj.lora_B.default.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.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.q_proj.lora_B.default.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.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.7.self_attn.v_proj.lora_B.default.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-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.lora_B.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.mlp.up_proj.lora_B.default.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-00003-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.k_proj.lora_B.default.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.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.o_proj.lora_B.default.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.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.q_proj.lora_B.default.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.lora_A.default.weight": "model-00002-of-00007.safetensors",
+    "model.layers.8.self_attn.v_proj.lora_B.default.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-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.lora_A.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.lora_B.default.weight": "model-00003-of-00007.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
+    "model.norm.weight": "model-00007-of-00007.safetensors"
+  }
+}

special_tokens_map.json

@@ -1,21 +1,27 @@
 {
   "additional_special_tokens": [
-    {
-      "content": "<|im_start|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    },
-    {
-      "content": "<|im_end|>",
-      "lstrip": false,
-      "normalized": false,
-      "rstrip": false,
-      "single_word": false
-    }
+    "<|im_start|>",
+    "<|im_end|>"
   ],
-  "bos_token": "<|im_start|>",
-  "eos_token": "<|im_end|>",
-  "pad_token": "<|im_end|>"
+  "bos_token": {
+    "content": "<|im_start|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
 }

tokenizer_config.json

@@ -2073,11 +2073,15 @@
   "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
   "clean_up_tokenization_spaces": true,
   "eos_token": "<|im_end|>",
+  "max_length": 512,
   "model_input_names": [
     "input_ids",
     "attention_mask"
   ],
   "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<|im_end|>",
-  "tokenizer_class": "PreTrainedTokenizerFast"
+  "stride": 0,
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "truncation_side": "right",
+  "truncation_strategy": "longest_first"
 }