divinetaco commited on
Commit
7fbf780
1 Parent(s): 45730bf

a67c4d53d6d37559b62257b7283268c99400beea8ed3ab1423be019c18da015a

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ aranea-ancilla.png filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model:
3
+ - 152334H/miqu-1-70b-sf
4
+ - NeverSleep/MiquMaid-v1-70B
5
+ - Sao10K/WinterGoddess-1.4x-70B-L2
6
+ library_name: transformers
7
+ tags:
8
+ - mergekit
9
+ - merge
10
+ ---
11
+ # aranea-ancilla-116b-v1.0-4.4bpw-exl2
12
+ **aka MiquMaid-v1-70B + interleaved WinterGoddess-1.4x-70B-L2**
13
+
14
+ ![image/png](https://huggingface.co/divinetaco/aranea-ancilla-116b-v1.0-4.4bpw-exl2/resolve/main/aranea-ancilla.png)
15
+
16
+ A [mergekit](https://github.com/arcee-ai/mergekit) frankenmerge based on [NeverSleep/MiquMaid-v1-70B](https://huggingface.co/NeverSleep/MiquMaid-v1-70B) with interleaved layers of [Sao10K/WinterGoddess-1.4x-70B-L2](https://huggingface.co/Sao10K/WinterGoddess-1.4x-70B-L2).
17
+ This was the top performing model from a series of merge experiments to create a highly coherant creative writing model.
18
+
19
+ Tests consisted of a series of private benchmarks and manual comparisons. A number of different base models, interleave models and layer offsets were compared.
20
+
21
+ - Usable context ~32768
22
+ - Recommended context ~16384
23
+
24
+ Non frankenstein miqu-1 finetunes generally outperform their frankenstein counterparts at very long contexts due to coherency loss.
25
+ As a rough suggestion I might suggest swapping out to either [NeverSleep/MiquMaid-v1-70B](https://huggingface.co/NeverSleep/MiquMaid-v1-70B) or [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf) after 16k context.
26
+
27
+ Layers: 136
28
+
29
+ ### License
30
+
31
+ No license. Component models based on the [Mistral AI Miqu-1](https://huggingface.co/miqudev/miqu-1-70b/tree/main) llama2 finetune that was released without license.
32
+
33
+ ### Interesting observations from benchmarking
34
+
35
+ - 10 layer interleave stride with a 20 layer interleave width consistently outperformed alternatives combinations.
36
+ - Offsetting the interleaved model's first set of layers generally improved coherency. [14-30] reliably beat the [10-30] mergekit slice configuration for various combinations of models.
37
+ - Quality of resulting merges can vary wildly. Whilst a merge of two strong models tends to produce a strong frankenstein model, this rule does not always hold true.
38
+
39
+ ### Quantizations
40
+
41
+ Exllamav2 quants will be available when bandwidth permits.
aranea-ancilla.png ADDED

Git LFS Details

  • SHA256: e5134400ec8efe9313c010654f4385f42474d2ce77d0bd235849f95d683c2e35
  • Pointer size: 132 Bytes
  • Size of remote file: 1.6 MB
config.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "aranea-ancilla-116b-v1.0-4.4bpw-exl2",
3
+ "architectures": [
4
+ "LlamaForCausalLM"
5
+ ],
6
+ "attention_bias": false,
7
+ "attention_dropout": 0.0,
8
+ "bos_token_id": 1,
9
+ "eos_token_id": 2,
10
+ "hidden_act": "silu",
11
+ "hidden_size": 8192,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 28672,
14
+ "max_position_embeddings": 32764,
15
+ "model_type": "llama",
16
+ "num_attention_heads": 64,
17
+ "num_hidden_layers": 136,
18
+ "num_key_value_heads": 8,
19
+ "pad_token_id": 0,
20
+ "pretraining_tp": 1,
21
+ "rms_norm_eps": 1e-05,
22
+ "rope_scaling": null,
23
+ "rope_theta": 1000000,
24
+ "tie_word_embeddings": false,
25
+ "torch_dtype": "float16",
26
+ "transformers_version": "4.37.2",
27
+ "use_cache": false,
28
+ "vocab_size": 32000
29
+ }
mergekit_config.yml ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ merge_method: linear
2
+ parameters:
3
+ weight: 1.0
4
+ slices:
5
+ - sources:
6
+ - model: MiquMaid-v1-70B
7
+ layer_range: [0, 20]
8
+ - sources:
9
+ - model: WinterGoddess-1.4x-70B-L2
10
+ layer_range: [14, 30]
11
+ - sources:
12
+ - model: MiquMaid-v1-70B
13
+ layer_range: [20, 40]
14
+ - sources:
15
+ - model: WinterGoddess-1.4x-70B-L2
16
+ layer_range: [30, 50]
17
+ - sources:
18
+ - model: MiquMaid-v1-70B
19
+ layer_range: [40, 60]
20
+ - sources:
21
+ - model: WinterGoddess-1.4x-70B-L2
22
+ layer_range: [50, 70]
23
+ - sources:
24
+ - model: MiquMaid-v1-70B
25
+ layer_range: [60, 80]
26
+ dtype: float16
27
+ tokenizer_source: model:MiquMaid-v1-70B
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00024.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00024.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00024.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00024.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00024.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00024.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00024.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00024.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00024.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00024.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00024.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00024.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00024.safetensors", "model.embed_tokens.weight": "model-00001-of-00024.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00024.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00024.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00024.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00024.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00024.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00024.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00024.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00024.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00024.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00024.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00024.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00024.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00024.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00024.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00024.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00024.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00024.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00024.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00024.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00024.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00024.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00024.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00024.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00024.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00024.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00024.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00024.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00024.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00024.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00024.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00024.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00024.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00024.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00024.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00024.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00024.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00024.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00024.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00024.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00024.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00024.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00024.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00024.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00024.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00024.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00024.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00024.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00002-of-00024.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00024.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00002-of-00024.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00024.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00024.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00024.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00024.safetensors", "model.layers.7.input_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00024.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00024.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00024.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00024.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00024.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00024.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00024.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00024.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00024.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00024.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00003-of-00024.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.5.input_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00024.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00024.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00024.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00024.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00024.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00024.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00024.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00024.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00024.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00024.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00024.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00024.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00024.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00024.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00024.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00024.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00024.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00024.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00024.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00024.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00024.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00024.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00024.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00024.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00024.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00024.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00024.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00024.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00024.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00024.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00024.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00024.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00024.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00024.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00024.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00024.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00024.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00024.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00024.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00024.safetensors", "model.layers.23.input_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00024.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00004-of-00024.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00024.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00024.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00024.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00024.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00004-of-00024.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00004-of-00024.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00024.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00024.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00024.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00024.safetensors", "model.layers.9.input_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00004-of-00024.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00004-of-00024.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00024.safetensors", "model.layers.8.input_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00024.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00024.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00024.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00024.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00024.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00024.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00024.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00024.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00024.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00024.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00024.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00024.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00024.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00024.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00024.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00024.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00024.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00024.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00024.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00024.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00024.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00024.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00024.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00024.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00024.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00024.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00024.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00024.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00024.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00024.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00024.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00024.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00024.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00024.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00005-of-00024.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00024.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00024.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00024.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00024.safetensors", "model.layers.12.input_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00024.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00024.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00024.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00024.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00024.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00024.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00024.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00024.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00006-of-00024.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00006-of-00024.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00006-of-00024.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00006-of-00024.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00006-of-00024.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00006-of-00024.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.59.input_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00006-of-00024.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00006-of-00024.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00006-of-00024.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00006-of-00024.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.58.input_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00006-of-00024.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00006-of-00024.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00006-of-00024.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00006-of-00024.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.57.input_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00006-of-00024.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00006-of-00024.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00006-of-00024.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00006-of-00024.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.56.input_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00006-of-00024.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00024.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00006-of-00024.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00024.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.35.input_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00006-of-00024.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00024.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00024.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00024.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00024.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00024.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00007-of-00024.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00007-of-00024.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00007-of-00024.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00007-of-00024.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00007-of-00024.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00007-of-00024.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00007-of-00024.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00007-of-00024.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00007-of-00024.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00007-of-00024.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00007-of-00024.safetensors", "model.layers.15.input_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00024.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00007-of-00024.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00024.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00024.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00024.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00024.safetensors", "model.layers.14.input_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.13.input_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.66.input_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00007-of-00024.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00007-of-00024.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00007-of-00024.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00007-of-00024.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00007-of-00024.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00007-of-00024.safetensors", "model.layers.65.input_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00007-of-00024.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00007-of-00024.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00007-of-00024.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00007-of-00024.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00007-of-00024.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00007-of-00024.safetensors", "model.layers.64.input_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00007-of-00024.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00007-of-00024.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00007-of-00024.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00007-of-00024.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00007-of-00024.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00007-of-00024.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00007-of-00024.safetensors", "model.layers.63.input_layernorm.weight": "model-00007-of-00024.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00008-of-00024.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00008-of-00024.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00008-of-00024.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00008-of-00024.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00008-of-00024.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00008-of-00024.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00008-of-00024.safetensors", "model.layers.62.input_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00008-of-00024.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00008-of-00024.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00008-of-00024.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00008-of-00024.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00008-of-00024.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00008-of-00024.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00008-of-00024.safetensors", "model.layers.61.input_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00008-of-00024.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00008-of-00024.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00008-of-00024.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00008-of-00024.safetensors", "model.layers.60.input_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00024.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00024.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00024.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00024.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00008-of-00024.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00008-of-00024.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00008-of-00024.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00008-of-00024.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00008-of-00024.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00008-of-00024.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00008-of-00024.safetensors", "model.layers.18.input_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00008-of-00024.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00008-of-00024.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00008-of-00024.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00008-of-00024.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00008-of-00024.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00008-of-00024.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00008-of-00024.safetensors", "model.layers.17.input_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00008-of-00024.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00008-of-00024.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.16.input_layernorm.weight": "model-00008-of-00024.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00008-of-00024.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00009-of-00024.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00009-of-00024.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00009-of-00024.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00009-of-00024.safetensors", "model.layers.71.input_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00009-of-00024.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00009-of-00024.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00009-of-00024.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00009-of-00024.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00009-of-00024.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00009-of-00024.safetensors", "model.layers.70.input_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00009-of-00024.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00009-of-00024.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00009-of-00024.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00009-of-00024.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00009-of-00024.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00009-of-00024.safetensors", "model.layers.69.input_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00009-of-00024.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00009-of-00024.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00009-of-00024.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00009-of-00024.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00009-of-00024.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00009-of-00024.safetensors", "model.layers.68.input_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00009-of-00024.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00009-of-00024.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00009-of-00024.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00009-of-00024.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00009-of-00024.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00009-of-00024.safetensors", "model.layers.67.input_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00009-of-00024.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00009-of-00024.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00009-of-00024.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00009-of-00024.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00009-of-00024.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00009-of-00024.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00009-of-00024.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00009-of-00024.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00024.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00024.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00024.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00009-of-00024.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00010-of-00024.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00010-of-00024.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00010-of-00024.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00010-of-00024.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00010-of-00024.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00010-of-00024.safetensors", "model.layers.37.input_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00010-of-00024.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00010-of-00024.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00010-of-00024.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00010-of-00024.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00010-of-00024.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00010-of-00024.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00010-of-00024.safetensors", "model.layers.36.input_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00010-of-00024.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00024.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00010-of-00024.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.19.input_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.97.mlp.gate_proj.weight": "model-00010-of-00024.safetensors", "model.layers.97.mlp.up_proj.weight": "model-00010-of-00024.safetensors", "model.layers.97.self_attn.k_proj.weight": "model-00010-of-00024.safetensors", "model.layers.96.mlp.down_proj.weight": "model-00010-of-00024.safetensors", "model.layers.96.mlp.gate_proj.weight": "model-00010-of-00024.safetensors", "model.layers.96.mlp.up_proj.weight": "model-00010-of-00024.safetensors", "model.layers.96.post_attention_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.96.self_attn.o_proj.weight": "model-00010-of-00024.safetensors", "model.layers.96.self_attn.v_proj.weight": "model-00010-of-00024.safetensors", "model.layers.96.self_attn.k_proj.weight": "model-00010-of-00024.safetensors", "model.layers.96.self_attn.q_proj.weight": "model-00010-of-00024.safetensors", "model.layers.96.input_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00010-of-00024.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00010-of-00024.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00010-of-00024.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00010-of-00024.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00010-of-00024.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00010-of-00024.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00010-of-00024.safetensors", "model.layers.75.input_layernorm.weight": "model-00010-of-00024.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00010-of-00024.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00010-of-00024.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00011-of-00024.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00011-of-00024.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00011-of-00024.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.74.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00011-of-00024.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00011-of-00024.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00011-of-00024.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00011-of-00024.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00011-of-00024.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.73.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00011-of-00024.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00011-of-00024.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00011-of-00024.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00011-of-00024.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00011-of-00024.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.72.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00011-of-00024.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00011-of-00024.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00011-of-00024.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00011-of-00024.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00011-of-00024.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00011-of-00024.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.40.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00011-of-00024.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00011-of-00024.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00011-of-00024.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00011-of-00024.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00011-of-00024.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.39.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00011-of-00024.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00011-of-00024.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00011-of-00024.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00011-of-00024.safetensors", "model.layers.38.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.103.self_attn.o_proj.weight": "model-00011-of-00024.safetensors", "model.layers.103.self_attn.v_proj.weight": "model-00011-of-00024.safetensors", "model.layers.103.self_attn.k_proj.weight": "model-00011-of-00024.safetensors", "model.layers.103.self_attn.q_proj.weight": "model-00011-of-00024.safetensors", "model.layers.103.input_layernorm.weight": "model-00011-of-00024.safetensors", "model.layers.102.mlp.down_proj.weight": "model-00012-of-00024.safetensors", "model.layers.102.mlp.gate_proj.weight": "model-00012-of-00024.safetensors", "model.layers.102.mlp.up_proj.weight": "model-00012-of-00024.safetensors", "model.layers.102.post_attention_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.102.self_attn.o_proj.weight": "model-00012-of-00024.safetensors", "model.layers.102.self_attn.v_proj.weight": "model-00012-of-00024.safetensors", "model.layers.102.self_attn.k_proj.weight": "model-00012-of-00024.safetensors", "model.layers.102.self_attn.q_proj.weight": "model-00012-of-00024.safetensors", "model.layers.102.input_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.101.mlp.down_proj.weight": "model-00012-of-00024.safetensors", "model.layers.101.mlp.gate_proj.weight": "model-00012-of-00024.safetensors", "model.layers.101.mlp.up_proj.weight": "model-00012-of-00024.safetensors", "model.layers.101.post_attention_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.101.self_attn.o_proj.weight": "model-00012-of-00024.safetensors", "model.layers.101.self_attn.v_proj.weight": "model-00012-of-00024.safetensors", "model.layers.101.self_attn.k_proj.weight": "model-00012-of-00024.safetensors", "model.layers.101.self_attn.q_proj.weight": "model-00012-of-00024.safetensors", "model.layers.101.input_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.100.mlp.down_proj.weight": "model-00012-of-00024.safetensors", "model.layers.100.mlp.gate_proj.weight": "model-00012-of-00024.safetensors", "model.layers.100.mlp.up_proj.weight": "model-00012-of-00024.safetensors", "model.layers.100.post_attention_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.100.self_attn.o_proj.weight": "model-00012-of-00024.safetensors", "model.layers.100.self_attn.v_proj.weight": "model-00012-of-00024.safetensors", "model.layers.100.self_attn.k_proj.weight": "model-00012-of-00024.safetensors", "model.layers.100.self_attn.q_proj.weight": "model-00012-of-00024.safetensors", "model.layers.100.input_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.99.mlp.down_proj.weight": "model-00012-of-00024.safetensors", "model.layers.99.mlp.gate_proj.weight": "model-00012-of-00024.safetensors", "model.layers.99.mlp.up_proj.weight": "model-00012-of-00024.safetensors", "model.layers.99.post_attention_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.99.self_attn.o_proj.weight": "model-00012-of-00024.safetensors", "model.layers.99.self_attn.v_proj.weight": "model-00012-of-00024.safetensors", "model.layers.99.self_attn.k_proj.weight": "model-00012-of-00024.safetensors", "model.layers.99.self_attn.q_proj.weight": "model-00012-of-00024.safetensors", "model.layers.99.input_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.98.mlp.down_proj.weight": "model-00012-of-00024.safetensors", "model.layers.98.mlp.gate_proj.weight": "model-00012-of-00024.safetensors", "model.layers.98.mlp.up_proj.weight": "model-00012-of-00024.safetensors", "model.layers.98.post_attention_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.98.self_attn.o_proj.weight": "model-00012-of-00024.safetensors", "model.layers.98.self_attn.v_proj.weight": "model-00012-of-00024.safetensors", "model.layers.98.self_attn.k_proj.weight": "model-00012-of-00024.safetensors", "model.layers.98.self_attn.q_proj.weight": "model-00012-of-00024.safetensors", "model.layers.98.input_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.97.mlp.down_proj.weight": "model-00012-of-00024.safetensors", "model.layers.97.post_attention_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.97.self_attn.o_proj.weight": "model-00012-of-00024.safetensors", "model.layers.97.self_attn.v_proj.weight": "model-00012-of-00024.safetensors", "model.layers.97.self_attn.q_proj.weight": "model-00012-of-00024.safetensors", "model.layers.97.input_layernorm.weight": "model-00012-of-00024.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00012-of-00024.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00013-of-00024.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00013-of-00024.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00013-of-00024.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00013-of-00024.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00013-of-00024.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00013-of-00024.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00013-of-00024.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00013-of-00024.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00013-of-00024.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00013-of-00024.safetensors", "model.layers.42.input_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00013-of-00024.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00013-of-00024.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00013-of-00024.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00013-of-00024.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00013-of-00024.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00013-of-00024.safetensors", "model.layers.41.input_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.108.mlp.down_proj.weight": "model-00013-of-00024.safetensors", "model.layers.108.mlp.gate_proj.weight": "model-00013-of-00024.safetensors", "model.layers.108.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.108.post_attention_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.108.self_attn.o_proj.weight": "model-00013-of-00024.safetensors", "model.layers.108.self_attn.v_proj.weight": "model-00013-of-00024.safetensors", "model.layers.108.self_attn.k_proj.weight": "model-00013-of-00024.safetensors", "model.layers.108.self_attn.q_proj.weight": "model-00013-of-00024.safetensors", "model.layers.108.input_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.107.mlp.down_proj.weight": "model-00013-of-00024.safetensors", "model.layers.107.mlp.gate_proj.weight": "model-00013-of-00024.safetensors", "model.layers.107.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.107.post_attention_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.107.self_attn.o_proj.weight": "model-00013-of-00024.safetensors", "model.layers.107.self_attn.v_proj.weight": "model-00013-of-00024.safetensors", "model.layers.107.self_attn.k_proj.weight": "model-00013-of-00024.safetensors", "model.layers.107.self_attn.q_proj.weight": "model-00013-of-00024.safetensors", "model.layers.107.input_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.106.mlp.down_proj.weight": "model-00013-of-00024.safetensors", "model.layers.106.mlp.gate_proj.weight": "model-00013-of-00024.safetensors", "model.layers.106.mlp.up_proj.weight": "model-00013-of-00024.safetensors", "model.layers.106.post_attention_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.106.self_attn.o_proj.weight": "model-00013-of-00024.safetensors", "model.layers.106.self_attn.v_proj.weight": "model-00013-of-00024.safetensors", "model.layers.106.self_attn.k_proj.weight": "model-00013-of-00024.safetensors", "model.layers.106.self_attn.q_proj.weight": "model-00013-of-00024.safetensors", "model.layers.106.input_layernorm.weight": "model-00013-of-00024.safetensors", "model.layers.105.mlp.down_proj.weight": "model-00013-of-00024.safetensors", "model.layers.105.mlp.gate_proj.weight": "model-00014-of-00024.safetensors", "model.layers.105.mlp.up_proj.weight": "model-00014-of-00024.safetensors", "model.layers.105.post_attention_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.105.self_attn.o_proj.weight": "model-00014-of-00024.safetensors", "model.layers.105.self_attn.v_proj.weight": "model-00014-of-00024.safetensors", "model.layers.105.self_attn.k_proj.weight": "model-00014-of-00024.safetensors", "model.layers.105.self_attn.q_proj.weight": "model-00014-of-00024.safetensors", "model.layers.105.input_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.104.mlp.down_proj.weight": "model-00014-of-00024.safetensors", "model.layers.104.mlp.gate_proj.weight": "model-00014-of-00024.safetensors", "model.layers.104.mlp.up_proj.weight": "model-00014-of-00024.safetensors", "model.layers.104.post_attention_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.104.self_attn.o_proj.weight": "model-00014-of-00024.safetensors", "model.layers.104.self_attn.v_proj.weight": "model-00014-of-00024.safetensors", "model.layers.104.self_attn.k_proj.weight": "model-00014-of-00024.safetensors", "model.layers.104.self_attn.q_proj.weight": "model-00014-of-00024.safetensors", "model.layers.104.input_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.103.mlp.down_proj.weight": "model-00014-of-00024.safetensors", "model.layers.103.mlp.gate_proj.weight": "model-00014-of-00024.safetensors", "model.layers.103.mlp.up_proj.weight": "model-00014-of-00024.safetensors", "model.layers.103.post_attention_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00014-of-00024.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00014-of-00024.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00014-of-00024.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00014-of-00024.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00014-of-00024.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00014-of-00024.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00014-of-00024.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00014-of-00024.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00014-of-00024.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00014-of-00024.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00014-of-00024.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00014-of-00024.safetensors", "model.layers.45.input_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00014-of-00024.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00014-of-00024.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00014-of-00024.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00014-of-00024.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00014-of-00024.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00014-of-00024.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00014-of-00024.safetensors", "model.layers.44.input_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00014-of-00024.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.43.input_layernorm.weight": "model-00014-of-00024.safetensors", "model.layers.114.mlp.down_proj.weight": "model-00014-of-00024.safetensors", "model.layers.114.mlp.gate_proj.weight": "model-00014-of-00024.safetensors", "model.layers.114.mlp.up_proj.weight": "model-00015-of-00024.safetensors", "model.layers.114.post_attention_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.114.self_attn.k_proj.weight": "model-00015-of-00024.safetensors", "model.layers.114.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.113.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.113.mlp.gate_proj.weight": "model-00015-of-00024.safetensors", "model.layers.113.mlp.up_proj.weight": "model-00015-of-00024.safetensors", "model.layers.113.post_attention_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.113.self_attn.o_proj.weight": "model-00015-of-00024.safetensors", "model.layers.113.self_attn.v_proj.weight": "model-00015-of-00024.safetensors", "model.layers.113.self_attn.k_proj.weight": "model-00015-of-00024.safetensors", "model.layers.113.self_attn.q_proj.weight": "model-00015-of-00024.safetensors", "model.layers.113.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.112.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.112.mlp.gate_proj.weight": "model-00015-of-00024.safetensors", "model.layers.112.mlp.up_proj.weight": "model-00015-of-00024.safetensors", "model.layers.112.post_attention_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.112.self_attn.o_proj.weight": "model-00015-of-00024.safetensors", "model.layers.112.self_attn.v_proj.weight": "model-00015-of-00024.safetensors", "model.layers.112.self_attn.k_proj.weight": "model-00015-of-00024.safetensors", "model.layers.112.self_attn.q_proj.weight": "model-00015-of-00024.safetensors", "model.layers.112.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.111.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.111.mlp.gate_proj.weight": "model-00015-of-00024.safetensors", "model.layers.111.mlp.up_proj.weight": "model-00015-of-00024.safetensors", "model.layers.111.post_attention_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.111.self_attn.o_proj.weight": "model-00015-of-00024.safetensors", "model.layers.111.self_attn.v_proj.weight": "model-00015-of-00024.safetensors", "model.layers.111.self_attn.k_proj.weight": "model-00015-of-00024.safetensors", "model.layers.111.self_attn.q_proj.weight": "model-00015-of-00024.safetensors", "model.layers.111.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.110.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.110.mlp.gate_proj.weight": "model-00015-of-00024.safetensors", "model.layers.110.mlp.up_proj.weight": "model-00015-of-00024.safetensors", "model.layers.110.post_attention_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.110.self_attn.o_proj.weight": "model-00015-of-00024.safetensors", "model.layers.110.self_attn.v_proj.weight": "model-00015-of-00024.safetensors", "model.layers.110.self_attn.k_proj.weight": "model-00015-of-00024.safetensors", "model.layers.110.self_attn.q_proj.weight": "model-00015-of-00024.safetensors", "model.layers.110.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.109.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.109.mlp.gate_proj.weight": "model-00015-of-00024.safetensors", "model.layers.109.mlp.up_proj.weight": "model-00015-of-00024.safetensors", "model.layers.109.post_attention_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.109.self_attn.o_proj.weight": "model-00015-of-00024.safetensors", "model.layers.109.self_attn.v_proj.weight": "model-00015-of-00024.safetensors", "model.layers.109.self_attn.k_proj.weight": "model-00015-of-00024.safetensors", "model.layers.109.self_attn.q_proj.weight": "model-00015-of-00024.safetensors", "model.layers.109.input_layernorm.weight": "model-00015-of-00024.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00015-of-00024.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00015-of-00024.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00015-of-00024.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00015-of-00024.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00015-of-00024.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00016-of-00024.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00016-of-00024.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00016-of-00024.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00016-of-00024.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00016-of-00024.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00016-of-00024.safetensors", "model.layers.48.input_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00016-of-00024.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00016-of-00024.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00016-of-00024.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00016-of-00024.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00016-of-00024.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00016-of-00024.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00016-of-00024.safetensors", "model.layers.47.input_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00016-of-00024.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00016-of-00024.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.46.input_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.115.mlp.down_proj.weight": "model-00016-of-00024.safetensors", "model.layers.115.mlp.gate_proj.weight": "model-00016-of-00024.safetensors", "model.layers.115.mlp.up_proj.weight": "model-00016-of-00024.safetensors", "model.layers.115.post_attention_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.115.self_attn.o_proj.weight": "model-00016-of-00024.safetensors", "model.layers.115.self_attn.v_proj.weight": "model-00016-of-00024.safetensors", "model.layers.115.self_attn.k_proj.weight": "model-00016-of-00024.safetensors", "model.layers.115.self_attn.q_proj.weight": "model-00016-of-00024.safetensors", "model.layers.115.input_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.114.self_attn.o_proj.weight": "model-00016-of-00024.safetensors", "model.layers.114.self_attn.v_proj.weight": "model-00016-of-00024.safetensors", "model.layers.114.self_attn.q_proj.weight": "model-00016-of-00024.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00016-of-00024.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00016-of-00024.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00016-of-00024.safetensors", "model.layers.51.input_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00016-of-00024.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00016-of-00024.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00016-of-00024.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00016-of-00024.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00016-of-00024.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00016-of-00024.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00016-of-00024.safetensors", "model.layers.50.input_layernorm.weight": "model-00016-of-00024.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00016-of-00024.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00017-of-00024.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.49.input_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00017-of-00024.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00017-of-00024.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00017-of-00024.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00017-of-00024.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00017-of-00024.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00017-of-00024.safetensors", "model.layers.54.input_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00017-of-00024.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00017-of-00024.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00017-of-00024.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00017-of-00024.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00017-of-00024.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00017-of-00024.safetensors", "model.layers.53.input_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00017-of-00024.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00017-of-00024.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00017-of-00024.safetensors", "model.layers.52.input_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00017-of-00024.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00017-of-00024.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00017-of-00024.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00017-of-00024.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00017-of-00024.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00017-of-00024.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00017-of-00024.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00017-of-00024.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00017-of-00024.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00017-of-00024.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00017-of-00024.safetensors", "model.layers.76.input_layernorm.weight": "model-00017-of-00024.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00017-of-00024.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00017-of-00024.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00018-of-00024.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.55.input_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00018-of-00024.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00018-of-00024.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00018-of-00024.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00018-of-00024.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.79.input_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00018-of-00024.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00018-of-00024.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00018-of-00024.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.78.input_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00018-of-00024.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.77.input_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00018-of-00024.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00018-of-00024.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00018-of-00024.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.82.input_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00018-of-00024.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00018-of-00024.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00018-of-00024.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00018-of-00024.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00018-of-00024.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00018-of-00024.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00018-of-00024.safetensors", "model.layers.81.input_layernorm.weight": "model-00018-of-00024.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00018-of-00024.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00019-of-00024.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.80.input_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.86.self_attn.v_proj.weight": "model-00019-of-00024.safetensors", "model.layers.86.self_attn.k_proj.weight": "model-00019-of-00024.safetensors", "model.layers.86.self_attn.q_proj.weight": "model-00019-of-00024.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00019-of-00024.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00019-of-00024.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00019-of-00024.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00019-of-00024.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00019-of-00024.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00019-of-00024.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00019-of-00024.safetensors", "model.layers.85.input_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00019-of-00024.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00019-of-00024.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00019-of-00024.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00019-of-00024.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00019-of-00024.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00019-of-00024.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00019-of-00024.safetensors", "model.layers.84.input_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00019-of-00024.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00019-of-00024.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00019-of-00024.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.83.input_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.88.mlp.down_proj.weight": "model-00019-of-00024.safetensors", "model.layers.88.mlp.gate_proj.weight": "model-00019-of-00024.safetensors", "model.layers.88.mlp.up_proj.weight": "model-00019-of-00024.safetensors", "model.layers.88.post_attention_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.88.self_attn.o_proj.weight": "model-00019-of-00024.safetensors", "model.layers.88.self_attn.v_proj.weight": "model-00019-of-00024.safetensors", "model.layers.88.self_attn.k_proj.weight": "model-00019-of-00024.safetensors", "model.layers.88.self_attn.q_proj.weight": "model-00019-of-00024.safetensors", "model.layers.88.input_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.87.mlp.down_proj.weight": "model-00019-of-00024.safetensors", "model.layers.87.mlp.gate_proj.weight": "model-00019-of-00024.safetensors", "model.layers.87.mlp.up_proj.weight": "model-00019-of-00024.safetensors", "model.layers.87.post_attention_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.87.self_attn.o_proj.weight": "model-00019-of-00024.safetensors", "model.layers.87.self_attn.v_proj.weight": "model-00019-of-00024.safetensors", "model.layers.87.self_attn.k_proj.weight": "model-00019-of-00024.safetensors", "model.layers.87.self_attn.q_proj.weight": "model-00019-of-00024.safetensors", "model.layers.87.input_layernorm.weight": "model-00019-of-00024.safetensors", "model.layers.86.mlp.down_proj.weight": "model-00019-of-00024.safetensors", "model.layers.86.mlp.gate_proj.weight": "model-00019-of-00024.safetensors", "model.layers.86.mlp.up_proj.weight": "model-00020-of-00024.safetensors", "model.layers.86.post_attention_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.86.self_attn.o_proj.weight": "model-00020-of-00024.safetensors", "model.layers.86.input_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.91.mlp.gate_proj.weight": "model-00020-of-00024.safetensors", "model.layers.91.mlp.up_proj.weight": "model-00020-of-00024.safetensors", "model.layers.91.self_attn.o_proj.weight": "model-00020-of-00024.safetensors", "model.layers.91.self_attn.v_proj.weight": "model-00020-of-00024.safetensors", "model.layers.91.self_attn.k_proj.weight": "model-00020-of-00024.safetensors", "model.layers.91.self_attn.q_proj.weight": "model-00020-of-00024.safetensors", "model.layers.90.mlp.down_proj.weight": "model-00020-of-00024.safetensors", "model.layers.90.mlp.gate_proj.weight": "model-00020-of-00024.safetensors", "model.layers.90.mlp.up_proj.weight": "model-00020-of-00024.safetensors", "model.layers.90.post_attention_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.90.self_attn.o_proj.weight": "model-00020-of-00024.safetensors", "model.layers.90.self_attn.v_proj.weight": "model-00020-of-00024.safetensors", "model.layers.90.self_attn.k_proj.weight": "model-00020-of-00024.safetensors", "model.layers.90.self_attn.q_proj.weight": "model-00020-of-00024.safetensors", "model.layers.90.input_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.89.mlp.down_proj.weight": "model-00020-of-00024.safetensors", "model.layers.89.mlp.gate_proj.weight": "model-00020-of-00024.safetensors", "model.layers.89.mlp.up_proj.weight": "model-00020-of-00024.safetensors", "model.layers.89.post_attention_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.89.self_attn.o_proj.weight": "model-00020-of-00024.safetensors", "model.layers.89.self_attn.v_proj.weight": "model-00020-of-00024.safetensors", "model.layers.89.self_attn.k_proj.weight": "model-00020-of-00024.safetensors", "model.layers.89.self_attn.q_proj.weight": "model-00020-of-00024.safetensors", "model.layers.89.input_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.94.mlp.gate_proj.weight": "model-00020-of-00024.safetensors", "model.layers.94.self_attn.o_proj.weight": "model-00020-of-00024.safetensors", "model.layers.94.self_attn.v_proj.weight": "model-00020-of-00024.safetensors", "model.layers.94.self_attn.k_proj.weight": "model-00020-of-00024.safetensors", "model.layers.94.self_attn.q_proj.weight": "model-00020-of-00024.safetensors", "model.layers.93.mlp.down_proj.weight": "model-00020-of-00024.safetensors", "model.layers.93.mlp.gate_proj.weight": "model-00020-of-00024.safetensors", "model.layers.93.mlp.up_proj.weight": "model-00020-of-00024.safetensors", "model.layers.93.post_attention_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.93.self_attn.o_proj.weight": "model-00020-of-00024.safetensors", "model.layers.93.self_attn.v_proj.weight": "model-00020-of-00024.safetensors", "model.layers.93.self_attn.k_proj.weight": "model-00020-of-00024.safetensors", "model.layers.93.self_attn.q_proj.weight": "model-00020-of-00024.safetensors", "model.layers.93.input_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.92.mlp.down_proj.weight": "model-00020-of-00024.safetensors", "model.layers.92.mlp.gate_proj.weight": "model-00020-of-00024.safetensors", "model.layers.92.mlp.up_proj.weight": "model-00020-of-00024.safetensors", "model.layers.92.post_attention_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.92.self_attn.o_proj.weight": "model-00020-of-00024.safetensors", "model.layers.92.self_attn.v_proj.weight": "model-00020-of-00024.safetensors", "model.layers.92.self_attn.k_proj.weight": "model-00020-of-00024.safetensors", "model.layers.92.self_attn.q_proj.weight": "model-00020-of-00024.safetensors", "model.layers.92.input_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.91.mlp.down_proj.weight": "model-00020-of-00024.safetensors", "model.layers.91.post_attention_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.91.input_layernorm.weight": "model-00020-of-00024.safetensors", "model.layers.117.self_attn.o_proj.weight": "model-00021-of-00024.safetensors", "model.layers.117.self_attn.v_proj.weight": "model-00021-of-00024.safetensors", "model.layers.117.self_attn.k_proj.weight": "model-00021-of-00024.safetensors", "model.layers.117.self_attn.q_proj.weight": "model-00021-of-00024.safetensors", "model.layers.116.mlp.down_proj.weight": "model-00021-of-00024.safetensors", "model.layers.116.mlp.gate_proj.weight": "model-00021-of-00024.safetensors", "model.layers.116.mlp.up_proj.weight": "model-00021-of-00024.safetensors", "model.layers.116.post_attention_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.116.self_attn.o_proj.weight": "model-00021-of-00024.safetensors", "model.layers.116.self_attn.v_proj.weight": "model-00021-of-00024.safetensors", "model.layers.116.self_attn.k_proj.weight": "model-00021-of-00024.safetensors", "model.layers.116.self_attn.q_proj.weight": "model-00021-of-00024.safetensors", "model.layers.116.input_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.95.mlp.down_proj.weight": "model-00021-of-00024.safetensors", "model.layers.95.mlp.gate_proj.weight": "model-00021-of-00024.safetensors", "model.layers.95.mlp.up_proj.weight": "model-00021-of-00024.safetensors", "model.layers.95.post_attention_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.95.self_attn.o_proj.weight": "model-00021-of-00024.safetensors", "model.layers.95.self_attn.v_proj.weight": "model-00021-of-00024.safetensors", "model.layers.95.self_attn.k_proj.weight": "model-00021-of-00024.safetensors", "model.layers.95.self_attn.q_proj.weight": "model-00021-of-00024.safetensors", "model.layers.95.input_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.94.mlp.down_proj.weight": "model-00021-of-00024.safetensors", "model.layers.94.mlp.up_proj.weight": "model-00021-of-00024.safetensors", "model.layers.94.post_attention_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.94.input_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.120.self_attn.v_proj.weight": "model-00021-of-00024.safetensors", "model.layers.120.self_attn.k_proj.weight": "model-00021-of-00024.safetensors", "model.layers.120.self_attn.q_proj.weight": "model-00021-of-00024.safetensors", "model.layers.119.mlp.down_proj.weight": "model-00021-of-00024.safetensors", "model.layers.119.mlp.gate_proj.weight": "model-00021-of-00024.safetensors", "model.layers.119.mlp.up_proj.weight": "model-00021-of-00024.safetensors", "model.layers.119.post_attention_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.119.self_attn.o_proj.weight": "model-00021-of-00024.safetensors", "model.layers.119.self_attn.v_proj.weight": "model-00021-of-00024.safetensors", "model.layers.119.self_attn.k_proj.weight": "model-00021-of-00024.safetensors", "model.layers.119.self_attn.q_proj.weight": "model-00021-of-00024.safetensors", "model.layers.119.input_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.118.mlp.down_proj.weight": "model-00021-of-00024.safetensors", "model.layers.118.mlp.gate_proj.weight": "model-00021-of-00024.safetensors", "model.layers.118.mlp.up_proj.weight": "model-00021-of-00024.safetensors", "model.layers.118.post_attention_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.118.self_attn.o_proj.weight": "model-00021-of-00024.safetensors", "model.layers.118.self_attn.v_proj.weight": "model-00021-of-00024.safetensors", "model.layers.118.self_attn.k_proj.weight": "model-00021-of-00024.safetensors", "model.layers.118.self_attn.q_proj.weight": "model-00021-of-00024.safetensors", "model.layers.118.input_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.117.mlp.down_proj.weight": "model-00021-of-00024.safetensors", "model.layers.117.mlp.gate_proj.weight": "model-00021-of-00024.safetensors", "model.layers.117.mlp.up_proj.weight": "model-00021-of-00024.safetensors", "model.layers.117.post_attention_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.117.input_layernorm.weight": "model-00021-of-00024.safetensors", "model.layers.122.mlp.down_proj.weight": "model-00022-of-00024.safetensors", "model.layers.122.mlp.gate_proj.weight": "model-00022-of-00024.safetensors", "model.layers.122.mlp.up_proj.weight": "model-00022-of-00024.safetensors", "model.layers.122.post_attention_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.122.self_attn.o_proj.weight": "model-00022-of-00024.safetensors", "model.layers.122.self_attn.v_proj.weight": "model-00022-of-00024.safetensors", "model.layers.122.self_attn.k_proj.weight": "model-00022-of-00024.safetensors", "model.layers.122.self_attn.q_proj.weight": "model-00022-of-00024.safetensors", "model.layers.122.input_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.121.mlp.down_proj.weight": "model-00022-of-00024.safetensors", "model.layers.121.mlp.gate_proj.weight": "model-00022-of-00024.safetensors", "model.layers.121.mlp.up_proj.weight": "model-00022-of-00024.safetensors", "model.layers.121.post_attention_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.121.self_attn.o_proj.weight": "model-00022-of-00024.safetensors", "model.layers.121.self_attn.v_proj.weight": "model-00022-of-00024.safetensors", "model.layers.121.self_attn.k_proj.weight": "model-00022-of-00024.safetensors", "model.layers.121.self_attn.q_proj.weight": "model-00022-of-00024.safetensors", "model.layers.121.input_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.120.mlp.down_proj.weight": "model-00022-of-00024.safetensors", "model.layers.120.mlp.gate_proj.weight": "model-00022-of-00024.safetensors", "model.layers.120.mlp.up_proj.weight": "model-00022-of-00024.safetensors", "model.layers.120.post_attention_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.120.self_attn.o_proj.weight": "model-00022-of-00024.safetensors", "model.layers.120.input_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.125.mlp.gate_proj.weight": "model-00022-of-00024.safetensors", "model.layers.125.mlp.up_proj.weight": "model-00022-of-00024.safetensors", "model.layers.125.self_attn.o_proj.weight": "model-00022-of-00024.safetensors", "model.layers.125.self_attn.v_proj.weight": "model-00022-of-00024.safetensors", "model.layers.125.self_attn.k_proj.weight": "model-00022-of-00024.safetensors", "model.layers.125.self_attn.q_proj.weight": "model-00022-of-00024.safetensors", "model.layers.124.mlp.down_proj.weight": "model-00022-of-00024.safetensors", "model.layers.124.mlp.gate_proj.weight": "model-00022-of-00024.safetensors", "model.layers.124.mlp.up_proj.weight": "model-00022-of-00024.safetensors", "model.layers.124.post_attention_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.124.self_attn.o_proj.weight": "model-00022-of-00024.safetensors", "model.layers.124.self_attn.v_proj.weight": "model-00022-of-00024.safetensors", "model.layers.124.self_attn.k_proj.weight": "model-00022-of-00024.safetensors", "model.layers.124.self_attn.q_proj.weight": "model-00022-of-00024.safetensors", "model.layers.124.input_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.123.mlp.down_proj.weight": "model-00022-of-00024.safetensors", "model.layers.123.mlp.gate_proj.weight": "model-00022-of-00024.safetensors", "model.layers.123.mlp.up_proj.weight": "model-00022-of-00024.safetensors", "model.layers.123.post_attention_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.123.self_attn.o_proj.weight": "model-00022-of-00024.safetensors", "model.layers.123.self_attn.v_proj.weight": "model-00022-of-00024.safetensors", "model.layers.123.self_attn.k_proj.weight": "model-00022-of-00024.safetensors", "model.layers.123.self_attn.q_proj.weight": "model-00022-of-00024.safetensors", "model.layers.123.input_layernorm.weight": "model-00022-of-00024.safetensors", "model.layers.128.mlp.gate_proj.weight": "model-00023-of-00024.safetensors", "model.layers.128.self_attn.o_proj.weight": "model-00023-of-00024.safetensors", "model.layers.128.self_attn.v_proj.weight": "model-00023-of-00024.safetensors", "model.layers.128.self_attn.k_proj.weight": "model-00023-of-00024.safetensors", "model.layers.128.self_attn.q_proj.weight": "model-00023-of-00024.safetensors", "model.layers.127.mlp.down_proj.weight": "model-00023-of-00024.safetensors", "model.layers.127.mlp.gate_proj.weight": "model-00023-of-00024.safetensors", "model.layers.127.mlp.up_proj.weight": "model-00023-of-00024.safetensors", "model.layers.127.post_attention_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.127.self_attn.o_proj.weight": "model-00023-of-00024.safetensors", "model.layers.127.self_attn.v_proj.weight": "model-00023-of-00024.safetensors", "model.layers.127.self_attn.k_proj.weight": "model-00023-of-00024.safetensors", "model.layers.127.self_attn.q_proj.weight": "model-00023-of-00024.safetensors", "model.layers.127.input_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.126.mlp.down_proj.weight": "model-00023-of-00024.safetensors", "model.layers.126.mlp.gate_proj.weight": "model-00023-of-00024.safetensors", "model.layers.126.mlp.up_proj.weight": "model-00023-of-00024.safetensors", "model.layers.126.post_attention_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.126.self_attn.o_proj.weight": "model-00023-of-00024.safetensors", "model.layers.126.self_attn.v_proj.weight": "model-00023-of-00024.safetensors", "model.layers.126.self_attn.k_proj.weight": "model-00023-of-00024.safetensors", "model.layers.126.self_attn.q_proj.weight": "model-00023-of-00024.safetensors", "model.layers.126.input_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.125.mlp.down_proj.weight": "model-00023-of-00024.safetensors", "model.layers.125.post_attention_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.125.input_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.131.self_attn.o_proj.weight": "model-00023-of-00024.safetensors", "model.layers.131.self_attn.v_proj.weight": "model-00023-of-00024.safetensors", "model.layers.131.self_attn.k_proj.weight": "model-00023-of-00024.safetensors", "model.layers.131.self_attn.q_proj.weight": "model-00023-of-00024.safetensors", "model.layers.130.mlp.down_proj.weight": "model-00023-of-00024.safetensors", "model.layers.130.mlp.gate_proj.weight": "model-00023-of-00024.safetensors", "model.layers.130.mlp.up_proj.weight": "model-00023-of-00024.safetensors", "model.layers.130.post_attention_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.130.self_attn.o_proj.weight": "model-00023-of-00024.safetensors", "model.layers.130.self_attn.v_proj.weight": "model-00023-of-00024.safetensors", "model.layers.130.self_attn.k_proj.weight": "model-00023-of-00024.safetensors", "model.layers.130.self_attn.q_proj.weight": "model-00023-of-00024.safetensors", "model.layers.130.input_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.129.mlp.down_proj.weight": "model-00023-of-00024.safetensors", "model.layers.129.mlp.gate_proj.weight": "model-00023-of-00024.safetensors", "model.layers.129.mlp.up_proj.weight": "model-00023-of-00024.safetensors", "model.layers.129.post_attention_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.129.self_attn.o_proj.weight": "model-00023-of-00024.safetensors", "model.layers.129.self_attn.v_proj.weight": "model-00023-of-00024.safetensors", "model.layers.129.self_attn.k_proj.weight": "model-00023-of-00024.safetensors", "model.layers.129.self_attn.q_proj.weight": "model-00023-of-00024.safetensors", "model.layers.129.input_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.128.mlp.down_proj.weight": "model-00023-of-00024.safetensors", "model.layers.128.mlp.up_proj.weight": "model-00023-of-00024.safetensors", "model.layers.128.post_attention_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.128.input_layernorm.weight": "model-00023-of-00024.safetensors", "model.layers.134.self_attn.v_proj.weight": "model-00023-of-00024.safetensors", "model.layers.134.self_attn.k_proj.weight": "model-00023-of-00024.safetensors", "model.layers.134.self_attn.q_proj.weight": "model-00023-of-00024.safetensors", "model.layers.133.mlp.down_proj.weight": "model-00023-of-00024.safetensors", "model.layers.133.mlp.gate_proj.weight": "model-00024-of-00024.safetensors", "model.layers.133.mlp.up_proj.weight": "model-00024-of-00024.safetensors", "model.layers.133.post_attention_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.133.self_attn.o_proj.weight": "model-00024-of-00024.safetensors", "model.layers.133.self_attn.v_proj.weight": "model-00024-of-00024.safetensors", "model.layers.133.self_attn.k_proj.weight": "model-00024-of-00024.safetensors", "model.layers.133.self_attn.q_proj.weight": "model-00024-of-00024.safetensors", "model.layers.133.input_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.132.mlp.down_proj.weight": "model-00024-of-00024.safetensors", "model.layers.132.mlp.gate_proj.weight": "model-00024-of-00024.safetensors", "model.layers.132.mlp.up_proj.weight": "model-00024-of-00024.safetensors", "model.layers.132.post_attention_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.132.self_attn.o_proj.weight": "model-00024-of-00024.safetensors", "model.layers.132.self_attn.v_proj.weight": "model-00024-of-00024.safetensors", "model.layers.132.self_attn.k_proj.weight": "model-00024-of-00024.safetensors", "model.layers.132.self_attn.q_proj.weight": "model-00024-of-00024.safetensors", "model.layers.132.input_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.131.mlp.down_proj.weight": "model-00024-of-00024.safetensors", "model.layers.131.mlp.gate_proj.weight": "model-00024-of-00024.safetensors", "model.layers.131.mlp.up_proj.weight": "model-00024-of-00024.safetensors", "model.layers.131.post_attention_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.131.input_layernorm.weight": "model-00024-of-00024.safetensors", "lm_head.weight": "model-00024-of-00024.safetensors", "model.norm.weight": "model-00024-of-00024.safetensors", "model.layers.135.mlp.down_proj.weight": "model-00024-of-00024.safetensors", "model.layers.135.mlp.gate_proj.weight": "model-00024-of-00024.safetensors", "model.layers.135.mlp.up_proj.weight": "model-00024-of-00024.safetensors", "model.layers.135.post_attention_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.135.self_attn.o_proj.weight": "model-00024-of-00024.safetensors", "model.layers.135.self_attn.v_proj.weight": "model-00024-of-00024.safetensors", "model.layers.135.self_attn.k_proj.weight": "model-00024-of-00024.safetensors", "model.layers.135.self_attn.q_proj.weight": "model-00024-of-00024.safetensors", "model.layers.135.input_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.134.mlp.down_proj.weight": "model-00024-of-00024.safetensors", "model.layers.134.mlp.gate_proj.weight": "model-00024-of-00024.safetensors", "model.layers.134.mlp.up_proj.weight": "model-00024-of-00024.safetensors", "model.layers.134.post_attention_layernorm.weight": "model-00024-of-00024.safetensors", "model.layers.134.self_attn.o_proj.weight": "model-00024-of-00024.safetensors", "model.layers.134.input_layernorm.weight": "model-00024-of-00024.safetensors"}}
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": false,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": false,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": false,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": false,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ }
29
+ },
30
+ "bos_token": "<s>",
31
+ "clean_up_tokenization_spaces": false,
32
+ "eos_token": "</s>",
33
+ "legacy": false,
34
+ "model_max_length": 1000000000000000019884624838656,
35
+ "pad_token": "<unk>",
36
+ "sp_model_kwargs": {},
37
+ "spaces_between_special_tokens": false,
38
+ "tokenizer_class": "LlamaTokenizer",
39
+ "trust_remote_code": false,
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": false,
42
+ "use_fast": true
43
+ }