Dracones commited on
Commit
8c99c80
1 Parent(s): 516885d

Upload folder using huggingface_hub

Browse files
README.md ADDED
@@ -0,0 +1,174 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: transformers
3
+ language:
4
+ - en
5
+ license: unknown
6
+ tags:
7
+ - exl2
8
+ ---
9
+
10
+ # miqu-1-70b-sf - EXL2 2.25bpw
11
+
12
+ This is a 2.25bpw EXL2 quant of [152334H/miqu-1-70b-sf](https://huggingface.co/152334H/miqu-1-70b-sf)
13
+
14
+ Details about the model can be found at the above model page.
15
+
16
+
17
+ ## EXL2 Version
18
+
19
+ These quants were made with exllamav2 version 0.0.18. Quants made on this version of EXL2 may not work on older versions of the exllamav2 library.
20
+
21
+ If you have problems loading these models, please update Text Generation WebUI to the latest version.
22
+
23
+ ## Perplexity Scoring
24
+
25
+ Below are the perplexity scores for the EXL2 models. A lower score is better.
26
+
27
+ | Quant Level | Perplexity Score |
28
+ |-------------|------------------|
29
+ | 5.0 | 4.2637 |
30
+ | 4.5 | 4.2876 |
31
+ | 4.0 | 4.3097 |
32
+ | 3.5 | 4.4459 |
33
+ | 3.0 | 4.6504 |
34
+ | 2.75 | 5.1638 |
35
+ | 2.5 | 5.1715 |
36
+ | 2.25 | 6.0848 |
37
+
38
+ ## EQ Bench
39
+
40
+ Here are the EQ Bench scores for the EXL2 quants using Alpaca, ChatML, Mistral, Vicuna-v1.1 and Vicuna-v0 prompt templates. A higher score is better.
41
+
42
+ | Quant Size | Instruct Template | Score |
43
+ |------------|-------------------|-------|
44
+ | 5.0 | ChatML | 79.91 |
45
+ | 5.0 | Alpaca | 81.45 |
46
+ | 5.0 | Mistral | 81.11 |
47
+ | 5.0 | Vicuna-v1.1 | 78.37 |
48
+ | 5.0 | Vicuna-v0 | 76.64 |
49
+ | 4.5 | ChatML | 80.64 |
50
+ | 4.5 | Alpaca | 80.9 |
51
+ | 4.5 | Mistral | 81.65 |
52
+ | 4.5 | Vicuna-v1.1 | 77.04 |
53
+ | 4.5 | Vicuna-v0 | 74.6 |
54
+ | 4.0 | ChatML | 80.78 |
55
+ | 4.0 | Alpaca | 79.53 |
56
+ | 4.0 | Mistral | 82.78 |
57
+ | 4.0 | Vicuna-v1.1 | 79.17 |
58
+ | 4.0 | Vicuna-v0 | 76.41 |
59
+ | 3.5 | ChatML | 81.11 |
60
+ | 3.5 | Alpaca | 82.42 |
61
+ | 3.5 | Mistral | 82.34 |
62
+ | 3.5 | Vicuna-v1.1 | 81.04 |
63
+ | 3.5 | Vicuna-v0 | 78.09 |
64
+ | 3.0 | ChatML | 79.13 |
65
+ | 3.0 | Alpaca | 77.74 |
66
+ | 3.0 | Mistral | 80.11 |
67
+ | 3.0 | Vicuna-v1.1 | 79.38 |
68
+ | 3.0 | Vicuna-v0 | 77.25 |
69
+ | 2.75 | ChatML | 79.6 |
70
+ | 2.75 | Alpaca | 77.85 |
71
+ | 2.75 | Mistral | 79.71 |
72
+ | 2.75 | Vicuna-v1.1 | 76.93 |
73
+ | 2.75 | Vicuna-v0 | 75.91 |
74
+ | 2.5 | ChatML | 77.45 |
75
+ | 2.5 | Alpaca | 77.0 |
76
+ | 2.5 | Mistral | 78.4 |
77
+ | 2.5 | Vicuna-v1.1 | 75.86 |
78
+ | 2.5 | Vicuna-v0 | 75.25 |
79
+ | 2.25 | ChatML | 77.18 |
80
+ | 2.25 | Alpaca | 74.06 |
81
+ | 2.25 | Mistral | 76.75 |
82
+ | 2.25 | Vicuna-v1.1 | 75.56 |
83
+ | 2.25 | Vicuna-v0 | 74.28 |
84
+
85
+
86
+
87
+ ### Perplexity Script
88
+
89
+ This was the script used for perplexity testing.
90
+
91
+ ```bash
92
+ #!/bin/bash
93
+
94
+ # Activate the conda environment
95
+ source ~/miniconda3/etc/profile.d/conda.sh
96
+ conda activate exllamav2
97
+
98
+ # Set the model name and bit size
99
+ MODEL_NAME="miqu-1-70b-sf"
100
+ BIT_PRECISIONS=(8.0 7.0 6.0 5.5 5.0 4.5 4.0 3.5 3.0 2.75 2.5 2.25)
101
+
102
+ # Print the markdown table header
103
+ echo "| Quant Level | Perplexity Score |"
104
+ echo "|-------------|------------------|"
105
+
106
+ for BIT_PRECISION in "${BIT_PRECISIONS[@]}"
107
+ do
108
+ MODEL_DIR="models/${MODEL_NAME}_exl2_${BIT_PRECISION}bpw"
109
+ if [ -d "$MODEL_DIR" ]; then
110
+ output=$(python test_inference.py -m "$MODEL_DIR" -gs 22,24 -ed data/wikitext/wikitext-2-v1.parquet)
111
+ score=$(echo "$output" | grep -oP 'Evaluation perplexity: \K[\d.]+')
112
+ echo "| $BIT_PRECISION | $score |"
113
+ fi
114
+ done
115
+ ```
116
+
117
+
118
+ ## Quant Details
119
+
120
+ This is the script used for quantization.
121
+
122
+ ```bash
123
+ #!/bin/bash
124
+
125
+ # Activate the conda environment
126
+ source ~/miniconda3/etc/profile.d/conda.sh
127
+ conda activate exllamav2
128
+
129
+ # Set the model name and bit size
130
+ MODEL_NAME="miqu-1-70b-sf"
131
+
132
+ # Define variables
133
+ MODEL_DIR="models/152334H_miqu-1-70b-sf"
134
+ OUTPUT_DIR="exl2_$MODEL_NAME"
135
+ MEASUREMENT_FILE="measurements/$MODEL_NAME.json"
136
+
137
+ # Create the measurement file if needed
138
+ if [ ! -f "$MEASUREMENT_FILE" ]; then
139
+ echo "Creating $MEASUREMENT_FILE"
140
+ # Create directories
141
+ if [ -d "$OUTPUT_DIR" ]; then
142
+ rm -r "$OUTPUT_DIR"
143
+ fi
144
+ mkdir "$OUTPUT_DIR"
145
+
146
+ python convert.py -i $MODEL_DIR -o $OUTPUT_DIR -nr -om $MEASUREMENT_FILE
147
+ fi
148
+
149
+ # Choose one of the below. Either create a single quant for testing or a batch of them.
150
+ # BIT_PRECISIONS=(5.0)
151
+ BIT_PRECISIONS=(8.0 7.0 6.0 5.5 5.0 4.5 4.0 3.5 3.0 2.75 2.5 2.25)
152
+
153
+ for BIT_PRECISION in "${BIT_PRECISIONS[@]}"
154
+ do
155
+ CONVERTED_FOLDER="models/${MODEL_NAME}_exl2_${BIT_PRECISION}bpw"
156
+
157
+ # If it doesn't already exist, make the quant
158
+ if [ ! -d "$CONVERTED_FOLDER" ]; then
159
+
160
+ echo "Creating $CONVERTED_FOLDER"
161
+
162
+ # Create directories
163
+ if [ -d "$OUTPUT_DIR" ]; then
164
+ rm -r "$OUTPUT_DIR"
165
+ fi
166
+ mkdir "$OUTPUT_DIR"
167
+ mkdir "$CONVERTED_FOLDER"
168
+
169
+ # Run conversion commands
170
+ python convert.py -i $MODEL_DIR -o $OUTPUT_DIR -nr -m $MEASUREMENT_FILE -b $BIT_PRECISION -cf $CONVERTED_FOLDER
171
+
172
+ fi
173
+ done
174
+ ```
config.json ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "LlamaForCausalLM"
4
+ ],
5
+ "attention_bias": false,
6
+ "attention_dropout": 0.0,
7
+ "bos_token_id": 1,
8
+ "eos_token_id": 2,
9
+ "hidden_act": "silu",
10
+ "hidden_size": 8192,
11
+ "initializer_range": 0.02,
12
+ "intermediate_size": 28672,
13
+ "max_position_embeddings": 32764,
14
+ "model_type": "llama",
15
+ "num_attention_heads": 64,
16
+ "num_hidden_layers": 80,
17
+ "num_key_value_heads": 8,
18
+ "pad_token_id": 0,
19
+ "pretraining_tp": 1,
20
+ "rms_norm_eps": 1e-05,
21
+ "rope_scaling": null,
22
+ "rope_theta": 1000000,
23
+ "tie_word_embeddings": false,
24
+ "torch_dtype": "float16",
25
+ "transformers_version": "4.36.0",
26
+ "use_cache": true,
27
+ "vocab_size": 32000,
28
+ "quantization_config": {
29
+ "quant_method": "exl2",
30
+ "version": "0.0.18",
31
+ "bits": 2.25,
32
+ "head_bits": 6,
33
+ "calibration": {
34
+ "rows": 100,
35
+ "length": 2048,
36
+ "dataset": "(default)"
37
+ }
38
+ }
39
+ }
generation_config.json ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ {
2
+ "_from_model_config": true,
3
+ "bos_token_id": 1,
4
+ "eos_token_id": 2,
5
+ "pad_token_id": 0,
6
+ "transformers_version": "4.36.0"
7
+ }
huggingface-metadata.txt ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ url: https://huggingface.co/152334H/miqu-1-70b-sf
2
+ branch: main
3
+ download date: 2024-02-02 21:23:11
4
+ sha256sum:
5
+ e4521dba2f4fd701e024430314926b1fed04733a648c1053c2cec18a87dd6c46 model-00001-of-00029.safetensors
6
+ bfb0c432003d8d446450f72610922be06f416ae6f7c06a7ad89f2e85c275d0ca model-00002-of-00029.safetensors
7
+ 92d77749c41a5377a114508208f1709c319a06fe92a5c49e61d363e3afcc3d30 model-00003-of-00029.safetensors
8
+ 6dd121c5e17630b58bb5b7a44f08b645d0dbc3b98e4c0db4fb4ba85e952b1b9c model-00004-of-00029.safetensors
9
+ 16dfdd5a91c8a678e8bfd2f1db5ff649bc685b0c20dc73546dff0cfc2168734d model-00005-of-00029.safetensors
10
+ 160a2801c7e331bc3ec2f824ad7eb6a9817a81e504a6da018aea33b5a44c3ec1 model-00006-of-00029.safetensors
11
+ fa6b89f709c6fc87ad3931dae8b66c6d7912f79d5f9a5fa48532e19418735b82 model-00007-of-00029.safetensors
12
+ 91db94ed795f94a48a473e76887d4af311a6f562a0d36150f7a327bd346be7cf model-00008-of-00029.safetensors
13
+ 5747d98bbde1cd2abde773da35981cd764cccfae5e11b9a29272caa196a0b6a0 model-00009-of-00029.safetensors
14
+ 914f5f29be7f866e503a22d977b4c5cd0e8f9585139b820e137a365c34816197 model-00010-of-00029.safetensors
15
+ 6793971064bea26ce74ff41b22d7035317e994699b6d89dfbf57d2936455c0f3 model-00011-of-00029.safetensors
16
+ 64d56b5a824e1ae9b3012f6d0082a76c465357f2251e9d041486e32114887d73 model-00012-of-00029.safetensors
17
+ 874ed27bc2a6a752951edb22f4d49588a1e9d9e1ae2ecfc5180cfbd8360bdebb model-00013-of-00029.safetensors
18
+ 157efff30be2135bbd692e5380d0ef88e775b2f1d7067199462dfd5c93e87ea0 model-00014-of-00029.safetensors
19
+ 9686648c11044955b6c00bf08243eb01c29304d5995b83aa8a87045bbef28cb0 model-00015-of-00029.safetensors
20
+ 31edde02fe845f115ad13646fbc160e2d965804176cdc50332cbcc847ee643b2 model-00016-of-00029.safetensors
21
+ b83b699790a6a507067cb56c64dc6aebc8210f56deab30dc5d47daa11fc92e12 model-00017-of-00029.safetensors
22
+ 8118012bd63f7a7710b98ecc4fb1345283ade6c941d78f4d06b01a35272b0f2e model-00018-of-00029.safetensors
23
+ daace6f5d2941018315ea9dddfec3b83ac7545d8d7bcf19c35430724472537c8 model-00019-of-00029.safetensors
24
+ 8c074463cb2495c654d1a837d166632c4256db80084b01a04dd78e69d7b5acab model-00020-of-00029.safetensors
25
+ 02088161532e05c1312b06863e30ab9d5fec582f6fda5269d0b61fad67dcc9b1 model-00021-of-00029.safetensors
26
+ c389e3523c9d39c52c78b305aea14c1aa127e129f63a1e12d342d62d0b47fa74 model-00022-of-00029.safetensors
27
+ b250d54ed699f605c475e92611feed0dd63d25d7d130dabda7500cc4d84d2958 model-00023-of-00029.safetensors
28
+ 094e0d8ed7809117ccab4c8bfb17b34e3aebaf5a1afa54a8399511d69106b12a model-00024-of-00029.safetensors
29
+ 79909eb582b19001c79098e1432cff3b2c78a7db244c2dbfbdc22e4c3b1bd71e model-00025-of-00029.safetensors
30
+ 077f127c73176214b1212c5bcc0e06d72451bb32cbbc658c03f0e37d0da17147 model-00026-of-00029.safetensors
31
+ 0dc6626da04c767844b5d948dcd1d9ca6d0cf57f75ae502fb94447d318944dba model-00027-of-00029.safetensors
32
+ a7673df9dde803c39d3b8b9af0d448215fa8ae6635e9a14c4e560c6ebb08ba9a model-00028-of-00029.safetensors
33
+ 6cc8c4e1a699bdd4e211a0e1cf7014ae5bb945ddb860b6286b0596d505c8df1b model-00029-of-00029.safetensors
34
+ 9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347 tokenizer.model
model.safetensors.index.json ADDED
@@ -0,0 +1,730 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_size": 137953296384
4
+ },
5
+ "weight_map": {
6
+ "lm_head.weight": "model-00029-of-00029.safetensors",
7
+ "model.embed_tokens.weight": "model-00001-of-00029.safetensors",
8
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00029.safetensors",
9
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00029.safetensors",
10
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
11
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
12
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00029.safetensors",
13
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
14
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
15
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
16
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
17
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00029.safetensors",
18
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00029.safetensors",
19
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
20
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00029.safetensors",
21
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00029.safetensors",
22
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
23
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
24
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
25
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
26
+ "model.layers.10.input_layernorm.weight": "model-00004-of-00029.safetensors",
27
+ "model.layers.10.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
28
+ "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
29
+ "model.layers.10.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
30
+ "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
31
+ "model.layers.10.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
32
+ "model.layers.10.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
33
+ "model.layers.10.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
34
+ "model.layers.10.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
35
+ "model.layers.11.input_layernorm.weight": "model-00005-of-00029.safetensors",
36
+ "model.layers.11.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
37
+ "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
38
+ "model.layers.11.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
39
+ "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
40
+ "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
41
+ "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
42
+ "model.layers.11.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
43
+ "model.layers.11.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
44
+ "model.layers.12.input_layernorm.weight": "model-00005-of-00029.safetensors",
45
+ "model.layers.12.mlp.down_proj.weight": "model-00005-of-00029.safetensors",
46
+ "model.layers.12.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
47
+ "model.layers.12.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
48
+ "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00029.safetensors",
49
+ "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
50
+ "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
51
+ "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
52
+ "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
53
+ "model.layers.13.input_layernorm.weight": "model-00006-of-00029.safetensors",
54
+ "model.layers.13.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
55
+ "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00029.safetensors",
56
+ "model.layers.13.mlp.up_proj.weight": "model-00005-of-00029.safetensors",
57
+ "model.layers.13.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
58
+ "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00029.safetensors",
59
+ "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00029.safetensors",
60
+ "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00029.safetensors",
61
+ "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00029.safetensors",
62
+ "model.layers.14.input_layernorm.weight": "model-00006-of-00029.safetensors",
63
+ "model.layers.14.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
64
+ "model.layers.14.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
65
+ "model.layers.14.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
66
+ "model.layers.14.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
67
+ "model.layers.14.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
68
+ "model.layers.14.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
69
+ "model.layers.14.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
70
+ "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
71
+ "model.layers.15.input_layernorm.weight": "model-00006-of-00029.safetensors",
72
+ "model.layers.15.mlp.down_proj.weight": "model-00006-of-00029.safetensors",
73
+ "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
74
+ "model.layers.15.mlp.up_proj.weight": "model-00006-of-00029.safetensors",
75
+ "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00029.safetensors",
76
+ "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
77
+ "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
78
+ "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
79
+ "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
80
+ "model.layers.16.input_layernorm.weight": "model-00007-of-00029.safetensors",
81
+ "model.layers.16.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
82
+ "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00029.safetensors",
83
+ "model.layers.16.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
84
+ "model.layers.16.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
85
+ "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00029.safetensors",
86
+ "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00029.safetensors",
87
+ "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00029.safetensors",
88
+ "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00029.safetensors",
89
+ "model.layers.17.input_layernorm.weight": "model-00007-of-00029.safetensors",
90
+ "model.layers.17.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
91
+ "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
92
+ "model.layers.17.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
93
+ "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
94
+ "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
95
+ "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
96
+ "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
97
+ "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
98
+ "model.layers.18.input_layernorm.weight": "model-00007-of-00029.safetensors",
99
+ "model.layers.18.mlp.down_proj.weight": "model-00007-of-00029.safetensors",
100
+ "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00029.safetensors",
101
+ "model.layers.18.mlp.up_proj.weight": "model-00007-of-00029.safetensors",
102
+ "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00029.safetensors",
103
+ "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
104
+ "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
105
+ "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
106
+ "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
107
+ "model.layers.19.input_layernorm.weight": "model-00008-of-00029.safetensors",
108
+ "model.layers.19.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
109
+ "model.layers.19.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
110
+ "model.layers.19.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
111
+ "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
112
+ "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00029.safetensors",
113
+ "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00029.safetensors",
114
+ "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00029.safetensors",
115
+ "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00029.safetensors",
116
+ "model.layers.2.input_layernorm.weight": "model-00002-of-00029.safetensors",
117
+ "model.layers.2.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
118
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00029.safetensors",
119
+ "model.layers.2.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
120
+ "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
121
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00029.safetensors",
122
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00029.safetensors",
123
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00029.safetensors",
124
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00029.safetensors",
125
+ "model.layers.20.input_layernorm.weight": "model-00008-of-00029.safetensors",
126
+ "model.layers.20.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
127
+ "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
128
+ "model.layers.20.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
129
+ "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
130
+ "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
131
+ "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
132
+ "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
133
+ "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
134
+ "model.layers.21.input_layernorm.weight": "model-00008-of-00029.safetensors",
135
+ "model.layers.21.mlp.down_proj.weight": "model-00008-of-00029.safetensors",
136
+ "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00029.safetensors",
137
+ "model.layers.21.mlp.up_proj.weight": "model-00008-of-00029.safetensors",
138
+ "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00029.safetensors",
139
+ "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
140
+ "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00029.safetensors",
141
+ "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
142
+ "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
143
+ "model.layers.22.input_layernorm.weight": "model-00009-of-00029.safetensors",
144
+ "model.layers.22.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
145
+ "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
146
+ "model.layers.22.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
147
+ "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
148
+ "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00029.safetensors",
149
+ "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
150
+ "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00029.safetensors",
151
+ "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00029.safetensors",
152
+ "model.layers.23.input_layernorm.weight": "model-00009-of-00029.safetensors",
153
+ "model.layers.23.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
154
+ "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
155
+ "model.layers.23.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
156
+ "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
157
+ "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
158
+ "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
159
+ "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
160
+ "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
161
+ "model.layers.24.input_layernorm.weight": "model-00009-of-00029.safetensors",
162
+ "model.layers.24.mlp.down_proj.weight": "model-00009-of-00029.safetensors",
163
+ "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00029.safetensors",
164
+ "model.layers.24.mlp.up_proj.weight": "model-00009-of-00029.safetensors",
165
+ "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00029.safetensors",
166
+ "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00029.safetensors",
167
+ "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00029.safetensors",
168
+ "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00029.safetensors",
169
+ "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00029.safetensors",
170
+ "model.layers.25.input_layernorm.weight": "model-00010-of-00029.safetensors",
171
+ "model.layers.25.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
172
+ "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
173
+ "model.layers.25.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
174
+ "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
175
+ "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
176
+ "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
177
+ "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
178
+ "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
179
+ "model.layers.26.input_layernorm.weight": "model-00010-of-00029.safetensors",
180
+ "model.layers.26.mlp.down_proj.weight": "model-00010-of-00029.safetensors",
181
+ "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
182
+ "model.layers.26.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
183
+ "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00029.safetensors",
184
+ "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
185
+ "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
186
+ "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
187
+ "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
188
+ "model.layers.27.input_layernorm.weight": "model-00011-of-00029.safetensors",
189
+ "model.layers.27.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
190
+ "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00029.safetensors",
191
+ "model.layers.27.mlp.up_proj.weight": "model-00010-of-00029.safetensors",
192
+ "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
193
+ "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00029.safetensors",
194
+ "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00029.safetensors",
195
+ "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00029.safetensors",
196
+ "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00029.safetensors",
197
+ "model.layers.28.input_layernorm.weight": "model-00011-of-00029.safetensors",
198
+ "model.layers.28.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
199
+ "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
200
+ "model.layers.28.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
201
+ "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
202
+ "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
203
+ "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
204
+ "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
205
+ "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
206
+ "model.layers.29.input_layernorm.weight": "model-00011-of-00029.safetensors",
207
+ "model.layers.29.mlp.down_proj.weight": "model-00011-of-00029.safetensors",
208
+ "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
209
+ "model.layers.29.mlp.up_proj.weight": "model-00011-of-00029.safetensors",
210
+ "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00029.safetensors",
211
+ "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
212
+ "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
213
+ "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
214
+ "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
215
+ "model.layers.3.input_layernorm.weight": "model-00002-of-00029.safetensors",
216
+ "model.layers.3.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
217
+ "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
218
+ "model.layers.3.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
219
+ "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
220
+ "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
221
+ "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
222
+ "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
223
+ "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
224
+ "model.layers.30.input_layernorm.weight": "model-00012-of-00029.safetensors",
225
+ "model.layers.30.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
226
+ "model.layers.30.mlp.gate_proj.weight": "model-00011-of-00029.safetensors",
227
+ "model.layers.30.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
228
+ "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
229
+ "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00029.safetensors",
230
+ "model.layers.30.self_attn.o_proj.weight": "model-00011-of-00029.safetensors",
231
+ "model.layers.30.self_attn.q_proj.weight": "model-00011-of-00029.safetensors",
232
+ "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00029.safetensors",
233
+ "model.layers.31.input_layernorm.weight": "model-00012-of-00029.safetensors",
234
+ "model.layers.31.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
235
+ "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
236
+ "model.layers.31.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
237
+ "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
238
+ "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
239
+ "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
240
+ "model.layers.31.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
241
+ "model.layers.31.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
242
+ "model.layers.32.input_layernorm.weight": "model-00012-of-00029.safetensors",
243
+ "model.layers.32.mlp.down_proj.weight": "model-00012-of-00029.safetensors",
244
+ "model.layers.32.mlp.gate_proj.weight": "model-00012-of-00029.safetensors",
245
+ "model.layers.32.mlp.up_proj.weight": "model-00012-of-00029.safetensors",
246
+ "model.layers.32.post_attention_layernorm.weight": "model-00012-of-00029.safetensors",
247
+ "model.layers.32.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
248
+ "model.layers.32.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
249
+ "model.layers.32.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
250
+ "model.layers.32.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
251
+ "model.layers.33.input_layernorm.weight": "model-00013-of-00029.safetensors",
252
+ "model.layers.33.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
253
+ "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
254
+ "model.layers.33.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
255
+ "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
256
+ "model.layers.33.self_attn.k_proj.weight": "model-00012-of-00029.safetensors",
257
+ "model.layers.33.self_attn.o_proj.weight": "model-00012-of-00029.safetensors",
258
+ "model.layers.33.self_attn.q_proj.weight": "model-00012-of-00029.safetensors",
259
+ "model.layers.33.self_attn.v_proj.weight": "model-00012-of-00029.safetensors",
260
+ "model.layers.34.input_layernorm.weight": "model-00013-of-00029.safetensors",
261
+ "model.layers.34.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
262
+ "model.layers.34.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
263
+ "model.layers.34.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
264
+ "model.layers.34.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
265
+ "model.layers.34.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
266
+ "model.layers.34.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
267
+ "model.layers.34.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
268
+ "model.layers.34.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
269
+ "model.layers.35.input_layernorm.weight": "model-00013-of-00029.safetensors",
270
+ "model.layers.35.mlp.down_proj.weight": "model-00013-of-00029.safetensors",
271
+ "model.layers.35.mlp.gate_proj.weight": "model-00013-of-00029.safetensors",
272
+ "model.layers.35.mlp.up_proj.weight": "model-00013-of-00029.safetensors",
273
+ "model.layers.35.post_attention_layernorm.weight": "model-00013-of-00029.safetensors",
274
+ "model.layers.35.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
275
+ "model.layers.35.self_attn.o_proj.weight": "model-00013-of-00029.safetensors",
276
+ "model.layers.35.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
277
+ "model.layers.35.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
278
+ "model.layers.36.input_layernorm.weight": "model-00014-of-00029.safetensors",
279
+ "model.layers.36.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
280
+ "model.layers.36.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
281
+ "model.layers.36.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
282
+ "model.layers.36.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
283
+ "model.layers.36.self_attn.k_proj.weight": "model-00013-of-00029.safetensors",
284
+ "model.layers.36.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
285
+ "model.layers.36.self_attn.q_proj.weight": "model-00013-of-00029.safetensors",
286
+ "model.layers.36.self_attn.v_proj.weight": "model-00013-of-00029.safetensors",
287
+ "model.layers.37.input_layernorm.weight": "model-00014-of-00029.safetensors",
288
+ "model.layers.37.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
289
+ "model.layers.37.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
290
+ "model.layers.37.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
291
+ "model.layers.37.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
292
+ "model.layers.37.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
293
+ "model.layers.37.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
294
+ "model.layers.37.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
295
+ "model.layers.37.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
296
+ "model.layers.38.input_layernorm.weight": "model-00014-of-00029.safetensors",
297
+ "model.layers.38.mlp.down_proj.weight": "model-00014-of-00029.safetensors",
298
+ "model.layers.38.mlp.gate_proj.weight": "model-00014-of-00029.safetensors",
299
+ "model.layers.38.mlp.up_proj.weight": "model-00014-of-00029.safetensors",
300
+ "model.layers.38.post_attention_layernorm.weight": "model-00014-of-00029.safetensors",
301
+ "model.layers.38.self_attn.k_proj.weight": "model-00014-of-00029.safetensors",
302
+ "model.layers.38.self_attn.o_proj.weight": "model-00014-of-00029.safetensors",
303
+ "model.layers.38.self_attn.q_proj.weight": "model-00014-of-00029.safetensors",
304
+ "model.layers.38.self_attn.v_proj.weight": "model-00014-of-00029.safetensors",
305
+ "model.layers.39.input_layernorm.weight": "model-00015-of-00029.safetensors",
306
+ "model.layers.39.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
307
+ "model.layers.39.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
308
+ "model.layers.39.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
309
+ "model.layers.39.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
310
+ "model.layers.39.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
311
+ "model.layers.39.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
312
+ "model.layers.39.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
313
+ "model.layers.39.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
314
+ "model.layers.4.input_layernorm.weight": "model-00002-of-00029.safetensors",
315
+ "model.layers.4.mlp.down_proj.weight": "model-00002-of-00029.safetensors",
316
+ "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00029.safetensors",
317
+ "model.layers.4.mlp.up_proj.weight": "model-00002-of-00029.safetensors",
318
+ "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00029.safetensors",
319
+ "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
320
+ "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
321
+ "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
322
+ "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
323
+ "model.layers.40.input_layernorm.weight": "model-00015-of-00029.safetensors",
324
+ "model.layers.40.mlp.down_proj.weight": "model-00015-of-00029.safetensors",
325
+ "model.layers.40.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
326
+ "model.layers.40.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
327
+ "model.layers.40.post_attention_layernorm.weight": "model-00015-of-00029.safetensors",
328
+ "model.layers.40.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
329
+ "model.layers.40.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
330
+ "model.layers.40.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
331
+ "model.layers.40.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
332
+ "model.layers.41.input_layernorm.weight": "model-00016-of-00029.safetensors",
333
+ "model.layers.41.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
334
+ "model.layers.41.mlp.gate_proj.weight": "model-00015-of-00029.safetensors",
335
+ "model.layers.41.mlp.up_proj.weight": "model-00015-of-00029.safetensors",
336
+ "model.layers.41.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
337
+ "model.layers.41.self_attn.k_proj.weight": "model-00015-of-00029.safetensors",
338
+ "model.layers.41.self_attn.o_proj.weight": "model-00015-of-00029.safetensors",
339
+ "model.layers.41.self_attn.q_proj.weight": "model-00015-of-00029.safetensors",
340
+ "model.layers.41.self_attn.v_proj.weight": "model-00015-of-00029.safetensors",
341
+ "model.layers.42.input_layernorm.weight": "model-00016-of-00029.safetensors",
342
+ "model.layers.42.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
343
+ "model.layers.42.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
344
+ "model.layers.42.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
345
+ "model.layers.42.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
346
+ "model.layers.42.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
347
+ "model.layers.42.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
348
+ "model.layers.42.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
349
+ "model.layers.42.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
350
+ "model.layers.43.input_layernorm.weight": "model-00016-of-00029.safetensors",
351
+ "model.layers.43.mlp.down_proj.weight": "model-00016-of-00029.safetensors",
352
+ "model.layers.43.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
353
+ "model.layers.43.mlp.up_proj.weight": "model-00016-of-00029.safetensors",
354
+ "model.layers.43.post_attention_layernorm.weight": "model-00016-of-00029.safetensors",
355
+ "model.layers.43.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
356
+ "model.layers.43.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
357
+ "model.layers.43.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
358
+ "model.layers.43.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
359
+ "model.layers.44.input_layernorm.weight": "model-00017-of-00029.safetensors",
360
+ "model.layers.44.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
361
+ "model.layers.44.mlp.gate_proj.weight": "model-00016-of-00029.safetensors",
362
+ "model.layers.44.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
363
+ "model.layers.44.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
364
+ "model.layers.44.self_attn.k_proj.weight": "model-00016-of-00029.safetensors",
365
+ "model.layers.44.self_attn.o_proj.weight": "model-00016-of-00029.safetensors",
366
+ "model.layers.44.self_attn.q_proj.weight": "model-00016-of-00029.safetensors",
367
+ "model.layers.44.self_attn.v_proj.weight": "model-00016-of-00029.safetensors",
368
+ "model.layers.45.input_layernorm.weight": "model-00017-of-00029.safetensors",
369
+ "model.layers.45.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
370
+ "model.layers.45.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
371
+ "model.layers.45.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
372
+ "model.layers.45.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
373
+ "model.layers.45.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
374
+ "model.layers.45.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
375
+ "model.layers.45.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
376
+ "model.layers.45.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
377
+ "model.layers.46.input_layernorm.weight": "model-00017-of-00029.safetensors",
378
+ "model.layers.46.mlp.down_proj.weight": "model-00017-of-00029.safetensors",
379
+ "model.layers.46.mlp.gate_proj.weight": "model-00017-of-00029.safetensors",
380
+ "model.layers.46.mlp.up_proj.weight": "model-00017-of-00029.safetensors",
381
+ "model.layers.46.post_attention_layernorm.weight": "model-00017-of-00029.safetensors",
382
+ "model.layers.46.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
383
+ "model.layers.46.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
384
+ "model.layers.46.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
385
+ "model.layers.46.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
386
+ "model.layers.47.input_layernorm.weight": "model-00018-of-00029.safetensors",
387
+ "model.layers.47.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
388
+ "model.layers.47.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
389
+ "model.layers.47.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
390
+ "model.layers.47.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
391
+ "model.layers.47.self_attn.k_proj.weight": "model-00017-of-00029.safetensors",
392
+ "model.layers.47.self_attn.o_proj.weight": "model-00017-of-00029.safetensors",
393
+ "model.layers.47.self_attn.q_proj.weight": "model-00017-of-00029.safetensors",
394
+ "model.layers.47.self_attn.v_proj.weight": "model-00017-of-00029.safetensors",
395
+ "model.layers.48.input_layernorm.weight": "model-00018-of-00029.safetensors",
396
+ "model.layers.48.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
397
+ "model.layers.48.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
398
+ "model.layers.48.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
399
+ "model.layers.48.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
400
+ "model.layers.48.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
401
+ "model.layers.48.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
402
+ "model.layers.48.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
403
+ "model.layers.48.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
404
+ "model.layers.49.input_layernorm.weight": "model-00018-of-00029.safetensors",
405
+ "model.layers.49.mlp.down_proj.weight": "model-00018-of-00029.safetensors",
406
+ "model.layers.49.mlp.gate_proj.weight": "model-00018-of-00029.safetensors",
407
+ "model.layers.49.mlp.up_proj.weight": "model-00018-of-00029.safetensors",
408
+ "model.layers.49.post_attention_layernorm.weight": "model-00018-of-00029.safetensors",
409
+ "model.layers.49.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
410
+ "model.layers.49.self_attn.o_proj.weight": "model-00018-of-00029.safetensors",
411
+ "model.layers.49.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
412
+ "model.layers.49.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
413
+ "model.layers.5.input_layernorm.weight": "model-00003-of-00029.safetensors",
414
+ "model.layers.5.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
415
+ "model.layers.5.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
416
+ "model.layers.5.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
417
+ "model.layers.5.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
418
+ "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00029.safetensors",
419
+ "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00029.safetensors",
420
+ "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00029.safetensors",
421
+ "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00029.safetensors",
422
+ "model.layers.50.input_layernorm.weight": "model-00019-of-00029.safetensors",
423
+ "model.layers.50.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
424
+ "model.layers.50.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
425
+ "model.layers.50.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
426
+ "model.layers.50.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
427
+ "model.layers.50.self_attn.k_proj.weight": "model-00018-of-00029.safetensors",
428
+ "model.layers.50.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
429
+ "model.layers.50.self_attn.q_proj.weight": "model-00018-of-00029.safetensors",
430
+ "model.layers.50.self_attn.v_proj.weight": "model-00018-of-00029.safetensors",
431
+ "model.layers.51.input_layernorm.weight": "model-00019-of-00029.safetensors",
432
+ "model.layers.51.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
433
+ "model.layers.51.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
434
+ "model.layers.51.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
435
+ "model.layers.51.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
436
+ "model.layers.51.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
437
+ "model.layers.51.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
438
+ "model.layers.51.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
439
+ "model.layers.51.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
440
+ "model.layers.52.input_layernorm.weight": "model-00019-of-00029.safetensors",
441
+ "model.layers.52.mlp.down_proj.weight": "model-00019-of-00029.safetensors",
442
+ "model.layers.52.mlp.gate_proj.weight": "model-00019-of-00029.safetensors",
443
+ "model.layers.52.mlp.up_proj.weight": "model-00019-of-00029.safetensors",
444
+ "model.layers.52.post_attention_layernorm.weight": "model-00019-of-00029.safetensors",
445
+ "model.layers.52.self_attn.k_proj.weight": "model-00019-of-00029.safetensors",
446
+ "model.layers.52.self_attn.o_proj.weight": "model-00019-of-00029.safetensors",
447
+ "model.layers.52.self_attn.q_proj.weight": "model-00019-of-00029.safetensors",
448
+ "model.layers.52.self_attn.v_proj.weight": "model-00019-of-00029.safetensors",
449
+ "model.layers.53.input_layernorm.weight": "model-00020-of-00029.safetensors",
450
+ "model.layers.53.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
451
+ "model.layers.53.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
452
+ "model.layers.53.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
453
+ "model.layers.53.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
454
+ "model.layers.53.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
455
+ "model.layers.53.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
456
+ "model.layers.53.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
457
+ "model.layers.53.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
458
+ "model.layers.54.input_layernorm.weight": "model-00020-of-00029.safetensors",
459
+ "model.layers.54.mlp.down_proj.weight": "model-00020-of-00029.safetensors",
460
+ "model.layers.54.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
461
+ "model.layers.54.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
462
+ "model.layers.54.post_attention_layernorm.weight": "model-00020-of-00029.safetensors",
463
+ "model.layers.54.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
464
+ "model.layers.54.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
465
+ "model.layers.54.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
466
+ "model.layers.54.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
467
+ "model.layers.55.input_layernorm.weight": "model-00021-of-00029.safetensors",
468
+ "model.layers.55.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
469
+ "model.layers.55.mlp.gate_proj.weight": "model-00020-of-00029.safetensors",
470
+ "model.layers.55.mlp.up_proj.weight": "model-00020-of-00029.safetensors",
471
+ "model.layers.55.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
472
+ "model.layers.55.self_attn.k_proj.weight": "model-00020-of-00029.safetensors",
473
+ "model.layers.55.self_attn.o_proj.weight": "model-00020-of-00029.safetensors",
474
+ "model.layers.55.self_attn.q_proj.weight": "model-00020-of-00029.safetensors",
475
+ "model.layers.55.self_attn.v_proj.weight": "model-00020-of-00029.safetensors",
476
+ "model.layers.56.input_layernorm.weight": "model-00021-of-00029.safetensors",
477
+ "model.layers.56.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
478
+ "model.layers.56.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
479
+ "model.layers.56.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
480
+ "model.layers.56.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
481
+ "model.layers.56.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
482
+ "model.layers.56.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
483
+ "model.layers.56.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
484
+ "model.layers.56.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
485
+ "model.layers.57.input_layernorm.weight": "model-00021-of-00029.safetensors",
486
+ "model.layers.57.mlp.down_proj.weight": "model-00021-of-00029.safetensors",
487
+ "model.layers.57.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
488
+ "model.layers.57.mlp.up_proj.weight": "model-00021-of-00029.safetensors",
489
+ "model.layers.57.post_attention_layernorm.weight": "model-00021-of-00029.safetensors",
490
+ "model.layers.57.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
491
+ "model.layers.57.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
492
+ "model.layers.57.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
493
+ "model.layers.57.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
494
+ "model.layers.58.input_layernorm.weight": "model-00022-of-00029.safetensors",
495
+ "model.layers.58.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
496
+ "model.layers.58.mlp.gate_proj.weight": "model-00021-of-00029.safetensors",
497
+ "model.layers.58.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
498
+ "model.layers.58.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
499
+ "model.layers.58.self_attn.k_proj.weight": "model-00021-of-00029.safetensors",
500
+ "model.layers.58.self_attn.o_proj.weight": "model-00021-of-00029.safetensors",
501
+ "model.layers.58.self_attn.q_proj.weight": "model-00021-of-00029.safetensors",
502
+ "model.layers.58.self_attn.v_proj.weight": "model-00021-of-00029.safetensors",
503
+ "model.layers.59.input_layernorm.weight": "model-00022-of-00029.safetensors",
504
+ "model.layers.59.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
505
+ "model.layers.59.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
506
+ "model.layers.59.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
507
+ "model.layers.59.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
508
+ "model.layers.59.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
509
+ "model.layers.59.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
510
+ "model.layers.59.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
511
+ "model.layers.59.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
512
+ "model.layers.6.input_layernorm.weight": "model-00003-of-00029.safetensors",
513
+ "model.layers.6.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
514
+ "model.layers.6.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
515
+ "model.layers.6.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
516
+ "model.layers.6.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
517
+ "model.layers.6.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
518
+ "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
519
+ "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
520
+ "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
521
+ "model.layers.60.input_layernorm.weight": "model-00022-of-00029.safetensors",
522
+ "model.layers.60.mlp.down_proj.weight": "model-00022-of-00029.safetensors",
523
+ "model.layers.60.mlp.gate_proj.weight": "model-00022-of-00029.safetensors",
524
+ "model.layers.60.mlp.up_proj.weight": "model-00022-of-00029.safetensors",
525
+ "model.layers.60.post_attention_layernorm.weight": "model-00022-of-00029.safetensors",
526
+ "model.layers.60.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
527
+ "model.layers.60.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
528
+ "model.layers.60.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
529
+ "model.layers.60.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
530
+ "model.layers.61.input_layernorm.weight": "model-00023-of-00029.safetensors",
531
+ "model.layers.61.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
532
+ "model.layers.61.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
533
+ "model.layers.61.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
534
+ "model.layers.61.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
535
+ "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00029.safetensors",
536
+ "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00029.safetensors",
537
+ "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00029.safetensors",
538
+ "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00029.safetensors",
539
+ "model.layers.62.input_layernorm.weight": "model-00023-of-00029.safetensors",
540
+ "model.layers.62.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
541
+ "model.layers.62.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
542
+ "model.layers.62.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
543
+ "model.layers.62.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
544
+ "model.layers.62.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
545
+ "model.layers.62.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
546
+ "model.layers.62.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
547
+ "model.layers.62.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
548
+ "model.layers.63.input_layernorm.weight": "model-00023-of-00029.safetensors",
549
+ "model.layers.63.mlp.down_proj.weight": "model-00023-of-00029.safetensors",
550
+ "model.layers.63.mlp.gate_proj.weight": "model-00023-of-00029.safetensors",
551
+ "model.layers.63.mlp.up_proj.weight": "model-00023-of-00029.safetensors",
552
+ "model.layers.63.post_attention_layernorm.weight": "model-00023-of-00029.safetensors",
553
+ "model.layers.63.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
554
+ "model.layers.63.self_attn.o_proj.weight": "model-00023-of-00029.safetensors",
555
+ "model.layers.63.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
556
+ "model.layers.63.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
557
+ "model.layers.64.input_layernorm.weight": "model-00024-of-00029.safetensors",
558
+ "model.layers.64.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
559
+ "model.layers.64.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
560
+ "model.layers.64.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
561
+ "model.layers.64.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
562
+ "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00029.safetensors",
563
+ "model.layers.64.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
564
+ "model.layers.64.self_attn.q_proj.weight": "model-00023-of-00029.safetensors",
565
+ "model.layers.64.self_attn.v_proj.weight": "model-00023-of-00029.safetensors",
566
+ "model.layers.65.input_layernorm.weight": "model-00024-of-00029.safetensors",
567
+ "model.layers.65.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
568
+ "model.layers.65.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
569
+ "model.layers.65.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
570
+ "model.layers.65.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
571
+ "model.layers.65.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
572
+ "model.layers.65.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
573
+ "model.layers.65.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
574
+ "model.layers.65.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
575
+ "model.layers.66.input_layernorm.weight": "model-00024-of-00029.safetensors",
576
+ "model.layers.66.mlp.down_proj.weight": "model-00024-of-00029.safetensors",
577
+ "model.layers.66.mlp.gate_proj.weight": "model-00024-of-00029.safetensors",
578
+ "model.layers.66.mlp.up_proj.weight": "model-00024-of-00029.safetensors",
579
+ "model.layers.66.post_attention_layernorm.weight": "model-00024-of-00029.safetensors",
580
+ "model.layers.66.self_attn.k_proj.weight": "model-00024-of-00029.safetensors",
581
+ "model.layers.66.self_attn.o_proj.weight": "model-00024-of-00029.safetensors",
582
+ "model.layers.66.self_attn.q_proj.weight": "model-00024-of-00029.safetensors",
583
+ "model.layers.66.self_attn.v_proj.weight": "model-00024-of-00029.safetensors",
584
+ "model.layers.67.input_layernorm.weight": "model-00025-of-00029.safetensors",
585
+ "model.layers.67.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
586
+ "model.layers.67.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
587
+ "model.layers.67.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
588
+ "model.layers.67.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
589
+ "model.layers.67.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
590
+ "model.layers.67.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
591
+ "model.layers.67.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
592
+ "model.layers.67.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
593
+ "model.layers.68.input_layernorm.weight": "model-00025-of-00029.safetensors",
594
+ "model.layers.68.mlp.down_proj.weight": "model-00025-of-00029.safetensors",
595
+ "model.layers.68.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
596
+ "model.layers.68.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
597
+ "model.layers.68.post_attention_layernorm.weight": "model-00025-of-00029.safetensors",
598
+ "model.layers.68.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
599
+ "model.layers.68.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
600
+ "model.layers.68.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
601
+ "model.layers.68.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
602
+ "model.layers.69.input_layernorm.weight": "model-00026-of-00029.safetensors",
603
+ "model.layers.69.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
604
+ "model.layers.69.mlp.gate_proj.weight": "model-00025-of-00029.safetensors",
605
+ "model.layers.69.mlp.up_proj.weight": "model-00025-of-00029.safetensors",
606
+ "model.layers.69.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
607
+ "model.layers.69.self_attn.k_proj.weight": "model-00025-of-00029.safetensors",
608
+ "model.layers.69.self_attn.o_proj.weight": "model-00025-of-00029.safetensors",
609
+ "model.layers.69.self_attn.q_proj.weight": "model-00025-of-00029.safetensors",
610
+ "model.layers.69.self_attn.v_proj.weight": "model-00025-of-00029.safetensors",
611
+ "model.layers.7.input_layernorm.weight": "model-00003-of-00029.safetensors",
612
+ "model.layers.7.mlp.down_proj.weight": "model-00003-of-00029.safetensors",
613
+ "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00029.safetensors",
614
+ "model.layers.7.mlp.up_proj.weight": "model-00003-of-00029.safetensors",
615
+ "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00029.safetensors",
616
+ "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
617
+ "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00029.safetensors",
618
+ "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
619
+ "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
620
+ "model.layers.70.input_layernorm.weight": "model-00026-of-00029.safetensors",
621
+ "model.layers.70.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
622
+ "model.layers.70.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
623
+ "model.layers.70.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
624
+ "model.layers.70.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
625
+ "model.layers.70.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
626
+ "model.layers.70.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
627
+ "model.layers.70.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
628
+ "model.layers.70.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
629
+ "model.layers.71.input_layernorm.weight": "model-00026-of-00029.safetensors",
630
+ "model.layers.71.mlp.down_proj.weight": "model-00026-of-00029.safetensors",
631
+ "model.layers.71.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
632
+ "model.layers.71.mlp.up_proj.weight": "model-00026-of-00029.safetensors",
633
+ "model.layers.71.post_attention_layernorm.weight": "model-00026-of-00029.safetensors",
634
+ "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
635
+ "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
636
+ "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
637
+ "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
638
+ "model.layers.72.input_layernorm.weight": "model-00027-of-00029.safetensors",
639
+ "model.layers.72.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
640
+ "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00029.safetensors",
641
+ "model.layers.72.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
642
+ "model.layers.72.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
643
+ "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00029.safetensors",
644
+ "model.layers.72.self_attn.o_proj.weight": "model-00026-of-00029.safetensors",
645
+ "model.layers.72.self_attn.q_proj.weight": "model-00026-of-00029.safetensors",
646
+ "model.layers.72.self_attn.v_proj.weight": "model-00026-of-00029.safetensors",
647
+ "model.layers.73.input_layernorm.weight": "model-00027-of-00029.safetensors",
648
+ "model.layers.73.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
649
+ "model.layers.73.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
650
+ "model.layers.73.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
651
+ "model.layers.73.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
652
+ "model.layers.73.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
653
+ "model.layers.73.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
654
+ "model.layers.73.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
655
+ "model.layers.73.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
656
+ "model.layers.74.input_layernorm.weight": "model-00027-of-00029.safetensors",
657
+ "model.layers.74.mlp.down_proj.weight": "model-00027-of-00029.safetensors",
658
+ "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00029.safetensors",
659
+ "model.layers.74.mlp.up_proj.weight": "model-00027-of-00029.safetensors",
660
+ "model.layers.74.post_attention_layernorm.weight": "model-00027-of-00029.safetensors",
661
+ "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
662
+ "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
663
+ "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
664
+ "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
665
+ "model.layers.75.input_layernorm.weight": "model-00028-of-00029.safetensors",
666
+ "model.layers.75.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
667
+ "model.layers.75.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
668
+ "model.layers.75.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
669
+ "model.layers.75.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
670
+ "model.layers.75.self_attn.k_proj.weight": "model-00027-of-00029.safetensors",
671
+ "model.layers.75.self_attn.o_proj.weight": "model-00027-of-00029.safetensors",
672
+ "model.layers.75.self_attn.q_proj.weight": "model-00027-of-00029.safetensors",
673
+ "model.layers.75.self_attn.v_proj.weight": "model-00027-of-00029.safetensors",
674
+ "model.layers.76.input_layernorm.weight": "model-00028-of-00029.safetensors",
675
+ "model.layers.76.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
676
+ "model.layers.76.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
677
+ "model.layers.76.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
678
+ "model.layers.76.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
679
+ "model.layers.76.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
680
+ "model.layers.76.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
681
+ "model.layers.76.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
682
+ "model.layers.76.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
683
+ "model.layers.77.input_layernorm.weight": "model-00028-of-00029.safetensors",
684
+ "model.layers.77.mlp.down_proj.weight": "model-00028-of-00029.safetensors",
685
+ "model.layers.77.mlp.gate_proj.weight": "model-00028-of-00029.safetensors",
686
+ "model.layers.77.mlp.up_proj.weight": "model-00028-of-00029.safetensors",
687
+ "model.layers.77.post_attention_layernorm.weight": "model-00028-of-00029.safetensors",
688
+ "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
689
+ "model.layers.77.self_attn.o_proj.weight": "model-00028-of-00029.safetensors",
690
+ "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
691
+ "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
692
+ "model.layers.78.input_layernorm.weight": "model-00029-of-00029.safetensors",
693
+ "model.layers.78.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
694
+ "model.layers.78.mlp.gate_proj.weight": "model-00029-of-00029.safetensors",
695
+ "model.layers.78.mlp.up_proj.weight": "model-00029-of-00029.safetensors",
696
+ "model.layers.78.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
697
+ "model.layers.78.self_attn.k_proj.weight": "model-00028-of-00029.safetensors",
698
+ "model.layers.78.self_attn.o_proj.weight": "model-00029-of-00029.safetensors",
699
+ "model.layers.78.self_attn.q_proj.weight": "model-00028-of-00029.safetensors",
700
+ "model.layers.78.self_attn.v_proj.weight": "model-00028-of-00029.safetensors",
701
+ "model.layers.79.input_layernorm.weight": "model-00029-of-00029.safetensors",
702
+ "model.layers.79.mlp.down_proj.weight": "model-00029-of-00029.safetensors",
703
+ "model.layers.79.mlp.gate_proj.weight": "model-00029-of-00029.safetensors",
704
+ "model.layers.79.mlp.up_proj.weight": "model-00029-of-00029.safetensors",
705
+ "model.layers.79.post_attention_layernorm.weight": "model-00029-of-00029.safetensors",
706
+ "model.layers.79.self_attn.k_proj.weight": "model-00029-of-00029.safetensors",
707
+ "model.layers.79.self_attn.o_proj.weight": "model-00029-of-00029.safetensors",
708
+ "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00029.safetensors",
709
+ "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00029.safetensors",
710
+ "model.layers.8.input_layernorm.weight": "model-00004-of-00029.safetensors",
711
+ "model.layers.8.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
712
+ "model.layers.8.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
713
+ "model.layers.8.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
714
+ "model.layers.8.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
715
+ "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00029.safetensors",
716
+ "model.layers.8.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
717
+ "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00029.safetensors",
718
+ "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00029.safetensors",
719
+ "model.layers.9.input_layernorm.weight": "model-00004-of-00029.safetensors",
720
+ "model.layers.9.mlp.down_proj.weight": "model-00004-of-00029.safetensors",
721
+ "model.layers.9.mlp.gate_proj.weight": "model-00004-of-00029.safetensors",
722
+ "model.layers.9.mlp.up_proj.weight": "model-00004-of-00029.safetensors",
723
+ "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00029.safetensors",
724
+ "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00029.safetensors",
725
+ "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00029.safetensors",
726
+ "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00029.safetensors",
727
+ "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00029.safetensors",
728
+ "model.norm.weight": "model-00029-of-00029.safetensors"
729
+ }
730
+ }
output-00001-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:631df9dad15178209526182410a5763dfbd487fc5f6007b4d33a465ac69c4556
3
+ size 8588640882
output-00002-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f52a86e0bf9ce465bf3c665f518ed5315190b13d01e40ca4cc09616016ea0e7d
3
+ size 8587378780
output-00003-of-00003.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dd58ed53f2db6672a1f4b824acba821840fdf2305331d52a7d2d165c72006dfc
3
+ size 2810537414
special_tokens_map.json ADDED
@@ -0,0 +1,30 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": {
3
+ "content": "<s>",
4
+ "lstrip": false,
5
+ "normalized": true,
6
+ "rstrip": false,
7
+ "single_word": false
8
+ },
9
+ "eos_token": {
10
+ "content": "</s>",
11
+ "lstrip": false,
12
+ "normalized": true,
13
+ "rstrip": false,
14
+ "single_word": false
15
+ },
16
+ "pad_token": {
17
+ "content": "<unk>",
18
+ "lstrip": false,
19
+ "normalized": true,
20
+ "rstrip": false,
21
+ "single_word": false
22
+ },
23
+ "unk_token": {
24
+ "content": "<unk>",
25
+ "lstrip": false,
26
+ "normalized": true,
27
+ "rstrip": false,
28
+ "single_word": false
29
+ }
30
+ }
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
+ "add_bos_token": true,
3
+ "add_eos_token": false,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": true,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": true,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": true,
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
+ "unk_token": "<unk>",
40
+ "use_default_system_prompt": false,
41
+ "chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}"
42
+ }