Trained with Unsloth

Upload model trained with Unsloth 2x faster

config.json

@@ -1,23 +1,22 @@
 {
-  "_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
+  "_name_or_path": "unsloth/qwen2-7b-bnb-4bit",
   "architectures": [
-    "LlamaForCausalLM"
+    "Qwen2ForCausalLM"
   ],
-  "attention_bias": false,
   "attention_dropout": 0.0,
-  "bos_token_id": 128000,
-  "eos_token_id": 128001,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 3584,
   "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,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "pad_token_id": 151646,
   "quantization_config": {
     "bnb_4bit_compute_dtype": "float16",
     "bnb_4bit_quant_type": "nf4",
@@ -30,13 +29,15 @@
     "load_in_8bit": false,
     "quant_method": "bitsandbytes"
   },
-  "rms_norm_eps": 1e-05,
+  "rms_norm_eps": 1e-06,
   "rope_scaling": null,
-  "rope_theta": 500000.0,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
   "tie_word_embeddings": false,
   "torch_dtype": "float16",
-  "transformers_version": "4.41.2",
-  "unsloth_version": "2024.6",
+  "transformers_version": "4.42.3",
+  "unsloth_version": "2024.7",
   "use_cache": true,
-  "vocab_size": 128256
+  "use_sliding_window": false,
+  "vocab_size": 152064
 }

generation_config.json

@@ -1,9 +1,6 @@
 {
-  "bos_token_id": 128000,
-  "do_sample": true,
-  "eos_token_id": 128001,
-  "max_length": 4096,
-  "temperature": 0.6,
-  "top_p": 0.9,
-  "transformers_version": "4.41.2"
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.42.3"
 }

model-00001-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f34bf30f73bf3e1da0d0986786b1c1c360b8bafd84e08847947f7abbb13657f3
-size 4652072861
+oid sha256:5883841ab0093b81c8255c984b2b10b04d4f665110027622675bb78f97eaaa7e
+size 4457259441

model-00002-of-00002.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e4f15e64381b74dcb7857c03cbfb62806534f7582ab885c738980a12e5b78989
-size 1050673280
+oid sha256:a17b24a36727400faebe507c4efd3192abb501c59965c969027a6676c70902e5
+size 1089994880

model.safetensors.index.json

@@ -1,6 +1,6 @@
 {
   "metadata": {
-    "total_size": 5702577741
+    "total_size": 5547097905
   },
   "weight_map": {
     "lm_head.weight": "model-00002-of-00002.safetensors",
@@ -25,6 +25,7 @@
     "model.layers.0.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.0.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -37,12 +38,14 @@
     "model.layers.0.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.0.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -69,6 +72,7 @@
     "model.layers.1.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.1.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -81,12 +85,14 @@
     "model.layers.1.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.1.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -113,6 +119,7 @@
     "model.layers.10.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.10.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -125,12 +132,14 @@
     "model.layers.10.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.10.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -157,6 +166,7 @@
     "model.layers.11.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.11.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -169,12 +179,14 @@
     "model.layers.11.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.11.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -201,6 +213,7 @@
     "model.layers.12.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.12.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -213,12 +226,14 @@
     "model.layers.12.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.12.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -245,6 +260,7 @@
     "model.layers.13.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.13.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -257,12 +273,14 @@
     "model.layers.13.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.13.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -289,6 +307,7 @@
     "model.layers.14.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.14.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -301,12 +320,14 @@
     "model.layers.14.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.14.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -333,6 +354,7 @@
     "model.layers.15.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.15.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -345,12 +367,14 @@
     "model.layers.15.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.15.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -377,6 +401,7 @@
     "model.layers.16.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.16.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -389,12 +414,14 @@
     "model.layers.16.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.16.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -421,6 +448,7 @@
     "model.layers.17.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.17.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -433,12 +461,14 @@
     "model.layers.17.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.17.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -465,6 +495,7 @@
     "model.layers.18.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.18.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -477,12 +508,14 @@
     "model.layers.18.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.18.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -509,6 +542,7 @@
     "model.layers.19.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.19.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -521,12 +555,14 @@
     "model.layers.19.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.19.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -553,6 +589,7 @@
     "model.layers.2.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.2.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -565,12 +602,14 @@
     "model.layers.2.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.2.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -597,6 +636,7 @@
     "model.layers.20.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.20.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -609,12 +649,14 @@
     "model.layers.20.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.20.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -641,6 +683,7 @@
     "model.layers.21.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.21.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -653,12 +696,14 @@
     "model.layers.21.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.21.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -685,6 +730,7 @@
     "model.layers.22.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.22.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -697,12 +743,14 @@
     "model.layers.22.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.22.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -729,6 +777,7 @@
     "model.layers.23.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.23.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -741,12 +790,14 @@
     "model.layers.23.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.23.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -773,6 +824,7 @@
     "model.layers.24.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.24.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -785,12 +837,14 @@
     "model.layers.24.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.24.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -817,6 +871,7 @@
     "model.layers.25.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.25.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -829,12 +884,14 @@
     "model.layers.25.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.25.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -861,6 +918,7 @@
     "model.layers.26.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.26.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -873,12 +931,14 @@
     "model.layers.26.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.26.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -905,6 +965,7 @@
     "model.layers.27.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.27.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -917,106 +978,20 @@
     "model.layers.27.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.27.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.28.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.29.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -1037,6 +1012,7 @@
     "model.layers.3.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.3.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -1049,106 +1025,20 @@
     "model.layers.3.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.3.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.30.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.down_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.down_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.down_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.down_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.gate_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.gate_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.gate_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.gate_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.gate_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.up_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.up_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.up_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.k_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.k_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.k_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.o_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.o_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.v_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.v_proj.weight.quant_map": "model-00001-of-00002.safetensors",
-    "model.layers.31.self_attn.v_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.down_proj.weight.absmax": "model-00001-of-00002.safetensors",
@@ -1169,6 +1059,7 @@
     "model.layers.4.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.4.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -1181,12 +1072,14 @@
     "model.layers.4.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.4.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -1213,6 +1106,7 @@
     "model.layers.5.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.5.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -1225,12 +1119,14 @@
     "model.layers.5.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.5.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -1257,6 +1153,7 @@
     "model.layers.6.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.6.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -1269,12 +1166,14 @@
     "model.layers.6.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.6.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -1301,6 +1200,7 @@
     "model.layers.7.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.7.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -1313,12 +1213,14 @@
     "model.layers.7.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.7.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -1345,6 +1247,7 @@
     "model.layers.8.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.8.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -1357,12 +1260,14 @@
     "model.layers.8.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.8.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -1389,6 +1294,7 @@
     "model.layers.9.mlp.up_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.9.mlp.up_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
     "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.k_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
@@ -1401,12 +1307,14 @@
     "model.layers.9.self_attn.o_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.o_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.weight.nested_quant_map": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.weight.quant_map": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.q_proj.weight.quant_state.bitsandbytes__nf4": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.weight.absmax": "model-00001-of-00002.safetensors",
     "model.layers.9.self_attn.v_proj.weight.nested_absmax": "model-00001-of-00002.safetensors",