Zoyd commited on
Commit
901eb58
1 Parent(s): ab4d095

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,71 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: apache-2.0
3
+ language:
4
+ - en
5
+ tags:
6
+ - 32 bit upscale
7
+ - full 32 bit precision
8
+ - master files
9
+ ---
10
+ <h3> Master Files for Ultra High Quality Remasters of "Psyonic-Cetacean" 20B </h3>
11
+
12
+ <img src="science-mad.jpg" width=300px height=300px style="float:right; padding:5px;">
13
+
14
+ May "Space Whale" swim in the oceans of the universe forever!
15
+
16
+ This repo contains the full precision (32 bit) master files for 32 bit upscales created by "DavidAU" of:
17
+
18
+ https://huggingface.co/DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF-imatrix
19
+
20
+ And
21
+
22
+ https://huggingface.co/DavidAU/Psyonic-Cetacean-Ultra-Quality-20b-GGUF
23
+
24
+ Please view either repo for details on the remaster's results, and other important infomation.
25
+
26
+ <font color="red"><B>IMPORTANT NOTES For Maximum Results: </b></font>
27
+
28
+ These are "final" result files of the full precision rebuild (including end result merge(s)) minus
29
+ GGUF and Imatrix level upscaling / adjustments which occuring during "GGUFing" processes.
30
+
31
+ If you use these to create your own GGUFs, please use "outfile" at F32 for best results. If
32
+ you use F16 this will reduce the quality by a factor of 2 or higher.
33
+
34
+ Imatrix processes should use a stable dataset(s) of at least 500 "chunks" or more.
35
+ If smaller dataset(s) are used this may corrupt or reduce the quality of the Imatrix builds.
36
+
37
+ Due to the precision remaster there will be "greater" distance between each quant - both
38
+ non imatrix and imatrix.
39
+
40
+ IE: The jump in quality, instruction following, "ai brainpower", nuance and output
41
+ between Q4 and Q5 and likewise Q5 and Q6 will be larger than normal.
42
+
43
+ Same applies to "Imatrix" quants.
44
+
45
+ In addition there will also be differences between exact Imatrix and non-imatrix quants
46
+ especially in terms of "creative uses" and/or uses where there is no "right answer".
47
+
48
+ Finally, in terms of prompts:
49
+
50
+ You may find longer prompts are no longer required and/or you may need to reduce the size
51
+ of prompts in usage. This is a factor due to the precision upscale.
52
+
53
+ Doing this will ensure the quality of the upscale is maximized in the GGUFs.
54
+
55
+ /* GPTQers:
56
+
57
+ Suggest 4bit-Act32 TRUE for best results.
58
+
59
+ /* EXL2ers:
60
+
61
+ Suggest Min 4.5 BPW or higher ; 6 BPW and up is especially potent.
62
+ Strongly suggest you do not reduce layer bit count, as this will affect depth and nuance.
63
+ The more BPW the better.
64
+
65
+ Happy GGUFing, EXL2ing, GPTQing, AWQing, HQQing and of course "Merging".
66
+
67
+ <b>LONG LIVE OPEN SOURCE!</B>
68
+
69
+ <I>DavidAU</I>
70
+
71
+ /* Drop me a note when up, and I will link the masters to your repos.
added_tokens.json ADDED
@@ -0,0 +1,5 @@
 
 
 
 
 
 
1
+ {
2
+ "</s>": 2,
3
+ "<s>": 1,
4
+ "<unk>": 0
5
+ }
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "_name_or_path": "F:/13B/Orca-2-13b_flat",
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": 5120,
12
+ "initializer_range": 0.02,
13
+ "intermediate_size": 13824,
14
+ "max_position_embeddings": 4096,
15
+ "mlp_bias": false,
16
+ "model_type": "llama",
17
+ "num_attention_heads": 40,
18
+ "num_hidden_layers": 62,
19
+ "num_key_value_heads": 40,
20
+ "pad_token_id": 0,
21
+ "pretraining_tp": 1,
22
+ "rms_norm_eps": 1e-05,
23
+ "rope_scaling": null,
24
+ "rope_theta": 10000.0,
25
+ "tie_word_embeddings": false,
26
+ "torch_dtype": "float32",
27
+ "transformers_version": "4.42.0.dev0",
28
+ "use_cache": true,
29
+ "vocab_size": 32000,
30
+ "quantization_config": {
31
+ "quant_method": "exl2",
32
+ "version": "0.1.3",
33
+ "bits": 3.5,
34
+ "head_bits": 6,
35
+ "calibration": {
36
+ "rows": 100,
37
+ "length": 2048,
38
+ "dataset": "(default)"
39
+ }
40
+ }
41
+ }
model.safetensors.index.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"metadata": {"mergekit_version": "0.0.4.2", "total_size": 79977451520}, "weight_map": {"lm_head.weight": "model-00001-of-00011.safetensors", "model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.48.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.49.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.50.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.51.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.52.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.53.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.54.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.55.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.56.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.57.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.58.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.59.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.60.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.61.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}
output-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14766d848fa4ff032660563954ca3dcb2737fb5eb80b7aba9578d91492e372a9
3
+ size 8559099168
output-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fb5d24f6731bd281e85ae191da454059dfce814d23a8372a772ccba0869e7e60
3
+ size 500968312
science-mad.jpg ADDED
special_tokens_map.json ADDED
@@ -0,0 +1,10 @@
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<unk>",
4
+ "<s>",
5
+ "</s>"
6
+ ],
7
+ "bos_token": "<s>",
8
+ "eos_token": "</s>",
9
+ "unk_token": "<unk>"
10
+ }
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 +1,42 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<unk>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<s>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ }
27
+ },
28
+ "additional_special_tokens": [
29
+ "<unk>",
30
+ "<s>",
31
+ "</s>"
32
+ ],
33
+ "bos_token": "<s>",
34
+ "clean_up_tokenization_spaces": false,
35
+ "eos_token": "</s>",
36
+ "model_max_length": 1000000000000000019884624838656,
37
+ "pad_token": null,
38
+ "sp_model_kwargs": {},
39
+ "tokenizer_class": "LlamaTokenizer",
40
+ "unk_token": "<unk>",
41
+ "use_default_system_prompt": true
42
+ }