Hugging Face's logo

PrunaAI
/
dolphin-2.8-mistral-7b-v02-bnb-8bit

Safetensors
pruna-engine
mistral
8-bit precision
bitsandbytes
Model card Files Community
3

[WIP] Upload folder using huggingface_hub (multi-commit d31de71b43aa94a6943b591a59e800f65b489284fd09ff929c5aa7ce168a69fa)

#1
by sharpenb - opened
base: refs/heads/main
←
from: refs/pr/1
Discussion Files changed
+0
-628
Files changed (7) hide show
  1. README.md +0 -47
  2. config.json +0 -43
  3. generation_config.json +0 -7
  4. model-00001-of-00002.safetensors +0 -3
  5. model-00002-of-00002.safetensors +0 -3
  6. model.safetensors +0 -3
  7. model.safetensors.index.json +0 -522
README.md DELETED
@@ -1,47 +0,0 @@
1
- ---
2
- library_name: pruna-engine
3
- thumbnail: "https://assets-global.website-files.com/646b351987a8d8ce158d1940/64ec9e96b4334c0e1ac41504_Logo%20with%20white%20text.svg"
4
- metrics:
5
- - memory_disk
6
- - memory_inference
7
- - inference_latency
8
- - inference_throughput
9
- - inference_CO2_emissions
10
- - inference_energy_consumption
11
- ---
12
- <!-- header start -->
13
- <!-- 200823 -->
14
- <div style="width: auto; margin-left: auto; margin-right: auto">
15
- <a href="https://www.pruna.ai/" target="_blank" rel="noopener noreferrer">
16
- <img src="https://i.imgur.com/eDAlcgk.png" alt="PrunaAI" style="width: 100%; min-width: 400px; display: block; margin: auto;">
17
- </a>
18
- </div>
19
- <!-- header end -->
20
-
21
- [![Twitter](https://img.shields.io/twitter/follow/PrunaAI?style=social)](https://twitter.com/PrunaAI)
22
- [![GitHub](https://img.shields.io/github/followers/PrunaAI?label=Follow%20%40PrunaAI&style=social)](https://github.com/PrunaAI)
23
- [![LinkedIn](https://img.shields.io/badge/LinkedIn-Connect-blue)](https://www.linkedin.com/company/93832878/admin/feed/posts/?feedType=following)
24
- [![Discord](https://img.shields.io/badge/Discord-Join%20Us-blue?style=social&logo=discord)](https://discord.com/invite/vb6SmA3hxu)
25
-
26
- # Simply make AI models cheaper, smaller, faster, and greener!
27
-
28
- - Give a thumbs up if you like this model!
29
- - Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
30
- - Request access to easily compress your *own* AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
31
- - Read the documentations to know more [here](https://pruna-ai-pruna.readthedocs-hosted.com/en/latest/)
32
- - Join Pruna AI community on Discord [here](https://discord.gg/rskEr4BZJx) to share feedback/suggestions or get help.
33
-
34
- **Frequently Asked Questions**
35
- - ***How does the compression work?*** The model is compressed by using bitsandbytes.
36
- - ***How does the model quality change?*** The quality of the model output will slightly degrade.
37
- - ***What is the model format?*** We the standard safetensors format.
38
- - ***How to compress my own models?*** You can request premium access to more compression methods and tech support for your specific use-cases [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
39
-
40
- ## Credits & License
41
-
42
- The license of the smashed model follows the license of the original model. Please check the license of the original model cognitivecomputations/dolphin-2.8-mistral-7b-v02 before using this model which provided the base model. The license of the `pruna-engine` is [here](https://pypi.org/project/pruna-engine/) on Pypi.
43
-
44
- ## Want to compress other models?
45
-
46
- - Contact us and tell us which model to compress next [here](https://www.pruna.ai/contact).
47
- - Request access to easily compress your own AI models [here](https://z0halsaff74.typeform.com/pruna-access?typeform-source=www.pruna.ai).
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
config.json DELETED
@@ -1,43 +0,0 @@
1
- {
2
- "_name_or_path": "cognitivecomputations/dolphin-2.8-mistral-7b-v02",
3
- "architectures": [
4
- "MistralForCausalLM"
5
- ],
6
- "attention_dropout": 0.0,
7
- "bos_token_id": 1,
8
- "eos_token_id": 32000,
9
- "hidden_act": "silu",
10
- "hidden_size": 4096,
11
- "initializer_range": 0.02,
12
- "intermediate_size": 14336,
13
- "max_position_embeddings": 32768,
14
- "model_type": "mistral",
15
- "num_attention_heads": 32,
16
- "num_hidden_layers": 32,
17
- "num_key_value_heads": 8,
18
- "quantization_config": {
19
- "_load_in_4bit": false,
20
- "_load_in_8bit": true,
21
- "bnb_4bit_compute_dtype": "bfloat16",
22
- "bnb_4bit_quant_storage": "uint8",
23
- "bnb_4bit_quant_type": "fp4",
24
- "bnb_4bit_use_double_quant": true,
25
- "llm_int8_enable_fp32_cpu_offload": false,
26
- "llm_int8_has_fp16_weight": false,
27
- "llm_int8_skip_modules": [
28
- "lm_head"
29
- ],
30
- "llm_int8_threshold": 6.0,
31
- "load_in_4bit": false,
32
- "load_in_8bit": true,
33
- "quant_method": "bitsandbytes"
34
- },
35
- "rms_norm_eps": 1e-05,
36
- "rope_theta": 1000000.0,
37
- "sliding_window": null,
38
- "tie_word_embeddings": false,
39
- "torch_dtype": "bfloat16",
40
- "transformers_version": "4.39.2",
41
- "use_cache": false,
42
- "vocab_size": 32002
43
- }
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
generation_config.json DELETED
@@ -1,7 +0,0 @@
1
- {
2
- "_from_model_config": true,
3
- "bos_token_id": 1,
4
- "do_sample": true,
5
- "eos_token_id": 2,
6
- "transformers_version": "4.39.2"
7
- }
 
 
 
 
 
 
 
 
model-00001-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:d4777bbdc80e90e79496555245877d7aad5c7e1d2f60afe49268c2dc8427661d
3
- size 4947096272
 
 
 
 
model-00002-of-00002.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:1edd62ffddf917977f09edc74ecaa57ad5e21ed7bc44b45f46074a303210e8e7
3
- size 2562639640
 
 
 
 
model.safetensors DELETED
@@ -1,3 +0,0 @@
1
- version https://git-lfs.github.com/spec/v1
2
- oid sha256:5d4b5ea7f8cca5bbf0e6d7fb400fa91d545f6200af6b6eb139382edf6a9c2c44
3
- size 4125720686
 
 
 
 
model.safetensors.index.json DELETED
@@ -1,522 +0,0 @@
1
- {
2
- "metadata": {
3
- "total_size": 7509680128
4
- },
5
- "weight_map": {
6
- "lm_head.weight": "model-00002-of-00002.safetensors",
7
- "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
- "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
- "model.layers.0.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
10
- "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
11
- "model.layers.0.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
12
- "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
13
- "model.layers.0.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
14
- "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
15
- "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
16
- "model.layers.0.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
17
- "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
18
- "model.layers.0.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
19
- "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
20
- "model.layers.0.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
21
- "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
22
- "model.layers.0.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
23
- "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
24
- "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
25
- "model.layers.1.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
26
- "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
27
- "model.layers.1.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
28
- "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
29
- "model.layers.1.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
30
- "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
31
- "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
32
- "model.layers.1.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
33
- "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
34
- "model.layers.1.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
35
- "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
36
- "model.layers.1.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
37
- "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
38
- "model.layers.1.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
39
- "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
40
- "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
41
- "model.layers.10.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
42
- "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
43
- "model.layers.10.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
44
- "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
45
- "model.layers.10.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
46
- "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
47
- "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
48
- "model.layers.10.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
49
- "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
50
- "model.layers.10.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
51
- "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
52
- "model.layers.10.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
53
- "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
54
- "model.layers.10.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
55
- "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
56
- "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
57
- "model.layers.11.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
58
- "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
59
- "model.layers.11.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
60
- "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
61
- "model.layers.11.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
62
- "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
63
- "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
64
- "model.layers.11.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
65
- "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
66
- "model.layers.11.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
67
- "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
68
- "model.layers.11.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
69
- "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
70
- "model.layers.11.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
71
- "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
72
- "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
73
- "model.layers.12.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
74
- "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
75
- "model.layers.12.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
76
- "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
77
- "model.layers.12.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
78
- "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
79
- "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
80
- "model.layers.12.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
81
- "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
82
- "model.layers.12.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
83
- "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
84
- "model.layers.12.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
85
- "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
86
- "model.layers.12.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
87
- "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
88
- "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
89
- "model.layers.13.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
90
- "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
91
- "model.layers.13.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
92
- "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
93
- "model.layers.13.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
94
- "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
95
- "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
96
- "model.layers.13.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
97
- "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
98
- "model.layers.13.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
99
- "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
100
- "model.layers.13.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
101
- "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
102
- "model.layers.13.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
103
- "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
104
- "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
105
- "model.layers.14.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
106
- "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
107
- "model.layers.14.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
108
- "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
109
- "model.layers.14.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
110
- "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
111
- "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
112
- "model.layers.14.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
113
- "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
114
- "model.layers.14.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
115
- "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
116
- "model.layers.14.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
117
- "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
118
- "model.layers.14.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
119
- "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
120
- "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
121
- "model.layers.15.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
122
- "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
123
- "model.layers.15.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
124
- "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
125
- "model.layers.15.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
126
- "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
127
- "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
128
- "model.layers.15.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
129
- "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
130
- "model.layers.15.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
131
- "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
132
- "model.layers.15.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
133
- "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
134
- "model.layers.15.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
135
- "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
136
- "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
137
- "model.layers.16.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
138
- "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
139
- "model.layers.16.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
140
- "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
141
- "model.layers.16.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
142
- "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
143
- "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
144
- "model.layers.16.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
145
- "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
146
- "model.layers.16.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
147
- "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
- "model.layers.16.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
149
- "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
- "model.layers.16.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
151
- "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
152
- "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
153
- "model.layers.17.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
154
- "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
155
- "model.layers.17.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
156
- "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
157
- "model.layers.17.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
158
- "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
159
- "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
160
- "model.layers.17.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
161
- "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
162
- "model.layers.17.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
163
- "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
164
- "model.layers.17.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
165
- "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
166
- "model.layers.17.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
167
- "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
168
- "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
169
- "model.layers.18.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
170
- "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
171
- "model.layers.18.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
172
- "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
173
- "model.layers.18.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
174
- "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
175
- "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
176
- "model.layers.18.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
177
- "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
178
- "model.layers.18.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
179
- "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
180
- "model.layers.18.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
181
- "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
182
- "model.layers.18.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
183
- "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
184
- "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
185
- "model.layers.19.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
186
- "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
187
- "model.layers.19.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
188
- "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
189
- "model.layers.19.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
190
- "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
191
- "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
192
- "model.layers.19.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
193
- "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
194
- "model.layers.19.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
195
- "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
196
- "model.layers.19.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
197
- "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
198
- "model.layers.19.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
199
- "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
200
- "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
201
- "model.layers.2.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
202
- "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
203
- "model.layers.2.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
204
- "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
205
- "model.layers.2.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
206
- "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
207
- "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
208
- "model.layers.2.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
209
- "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
210
- "model.layers.2.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
211
- "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
212
- "model.layers.2.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
213
- "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
214
- "model.layers.2.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
215
- "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
216
- "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
217
- "model.layers.20.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
218
- "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
219
- "model.layers.20.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
220
- "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
221
- "model.layers.20.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
222
- "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
223
- "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
224
- "model.layers.20.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
225
- "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
226
- "model.layers.20.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
227
- "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
228
- "model.layers.20.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
229
- "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
230
- "model.layers.20.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
231
- "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
232
- "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
233
- "model.layers.21.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
234
- "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
235
- "model.layers.21.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
236
- "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
237
- "model.layers.21.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
238
- "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
239
- "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
240
- "model.layers.21.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
241
- "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
242
- "model.layers.21.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
243
- "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
244
- "model.layers.21.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
245
- "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
246
- "model.layers.21.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
247
- "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
248
- "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
249
- "model.layers.22.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
250
- "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
251
- "model.layers.22.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
252
- "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
253
- "model.layers.22.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
254
- "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
255
- "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
256
- "model.layers.22.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
257
- "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
258
- "model.layers.22.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
259
- "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
260
- "model.layers.22.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
261
- "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
262
- "model.layers.22.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
263
- "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
264
- "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
265
- "model.layers.23.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
266
- "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
267
- "model.layers.23.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
268
- "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
269
- "model.layers.23.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
270
- "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
271
- "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
272
- "model.layers.23.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
273
- "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
274
- "model.layers.23.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
275
- "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
276
- "model.layers.23.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
277
- "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
278
- "model.layers.23.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
279
- "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
280
- "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
281
- "model.layers.24.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
282
- "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
283
- "model.layers.24.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
284
- "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
285
- "model.layers.24.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
286
- "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
287
- "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
288
- "model.layers.24.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
289
- "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
- "model.layers.24.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
291
- "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
292
- "model.layers.24.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
293
- "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
294
- "model.layers.24.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
295
- "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
296
- "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
297
- "model.layers.25.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
298
- "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
299
- "model.layers.25.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
300
- "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
301
- "model.layers.25.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
302
- "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
303
- "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
304
- "model.layers.25.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
305
- "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
306
- "model.layers.25.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
307
- "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
308
- "model.layers.25.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
309
- "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
310
- "model.layers.25.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
311
- "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
312
- "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
313
- "model.layers.26.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
314
- "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
315
- "model.layers.26.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
316
- "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
317
- "model.layers.26.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
318
- "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
319
- "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
320
- "model.layers.26.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
321
- "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
322
- "model.layers.26.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
323
- "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
324
- "model.layers.26.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
325
- "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
326
- "model.layers.26.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
327
- "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
328
- "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
329
- "model.layers.27.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
330
- "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
331
- "model.layers.27.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
332
- "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
333
- "model.layers.27.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
334
- "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
335
- "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
336
- "model.layers.27.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
337
- "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
338
- "model.layers.27.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
339
- "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
340
- "model.layers.27.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
341
- "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
342
- "model.layers.27.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
343
- "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
344
- "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
345
- "model.layers.28.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
346
- "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
347
- "model.layers.28.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
348
- "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
349
- "model.layers.28.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
350
- "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
351
- "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
352
- "model.layers.28.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
353
- "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
354
- "model.layers.28.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
355
- "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
356
- "model.layers.28.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
357
- "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
358
- "model.layers.28.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
359
- "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
360
- "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
361
- "model.layers.29.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
362
- "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
363
- "model.layers.29.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
364
- "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
365
- "model.layers.29.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
366
- "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
367
- "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
368
- "model.layers.29.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
369
- "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
370
- "model.layers.29.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
371
- "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
372
- "model.layers.29.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
373
- "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
374
- "model.layers.29.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
375
- "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
376
- "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
377
- "model.layers.3.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
378
- "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
379
- "model.layers.3.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
380
- "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
381
- "model.layers.3.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
382
- "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
383
- "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
384
- "model.layers.3.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
385
- "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
386
- "model.layers.3.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
387
- "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
388
- "model.layers.3.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
389
- "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
390
- "model.layers.3.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
391
- "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
392
- "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
393
- "model.layers.30.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
394
- "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
395
- "model.layers.30.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
396
- "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
397
- "model.layers.30.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
398
- "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
399
- "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
400
- "model.layers.30.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
401
- "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
402
- "model.layers.30.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
403
- "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
404
- "model.layers.30.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
405
- "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
406
- "model.layers.30.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
407
- "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
408
- "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
409
- "model.layers.31.mlp.down_proj.SCB": "model-00002-of-00002.safetensors",
410
- "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
411
- "model.layers.31.mlp.gate_proj.SCB": "model-00002-of-00002.safetensors",
412
- "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
413
- "model.layers.31.mlp.up_proj.SCB": "model-00002-of-00002.safetensors",
414
- "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
415
- "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
416
- "model.layers.31.self_attn.k_proj.SCB": "model-00002-of-00002.safetensors",
417
- "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
418
- "model.layers.31.self_attn.o_proj.SCB": "model-00002-of-00002.safetensors",
419
- "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
420
- "model.layers.31.self_attn.q_proj.SCB": "model-00002-of-00002.safetensors",
421
- "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
422
- "model.layers.31.self_attn.v_proj.SCB": "model-00002-of-00002.safetensors",
423
- "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
424
- "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
425
- "model.layers.4.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
426
- "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
427
- "model.layers.4.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
428
- "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
429
- "model.layers.4.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
430
- "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
431
- "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
432
- "model.layers.4.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
433
- "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
434
- "model.layers.4.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
435
- "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
436
- "model.layers.4.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
437
- "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
438
- "model.layers.4.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
439
- "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
440
- "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
441
- "model.layers.5.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
442
- "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
443
- "model.layers.5.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
444
- "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
445
- "model.layers.5.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
446
- "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
447
- "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
448
- "model.layers.5.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
449
- "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
450
- "model.layers.5.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
451
- "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
452
- "model.layers.5.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
453
- "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
454
- "model.layers.5.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
455
- "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
456
- "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
457
- "model.layers.6.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
458
- "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
459
- "model.layers.6.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
460
- "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
461
- "model.layers.6.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
462
- "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
463
- "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
464
- "model.layers.6.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
465
- "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
466
- "model.layers.6.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
467
- "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
468
- "model.layers.6.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
469
- "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
470
- "model.layers.6.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
471
- "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
472
- "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
473
- "model.layers.7.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
474
- "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
475
- "model.layers.7.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
476
- "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
477
- "model.layers.7.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
478
- "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
479
- "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
480
- "model.layers.7.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
481
- "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
482
- "model.layers.7.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
483
- "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
484
- "model.layers.7.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
485
- "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
486
- "model.layers.7.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
487
- "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
488
- "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
489
- "model.layers.8.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
490
- "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
491
- "model.layers.8.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
492
- "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
493
- "model.layers.8.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
494
- "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
495
- "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
496
- "model.layers.8.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
497
- "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
498
- "model.layers.8.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
499
- "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
500
- "model.layers.8.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
501
- "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
502
- "model.layers.8.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
503
- "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
504
- "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
505
- "model.layers.9.mlp.down_proj.SCB": "model-00001-of-00002.safetensors",
506
- "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
507
- "model.layers.9.mlp.gate_proj.SCB": "model-00001-of-00002.safetensors",
508
- "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
509
- "model.layers.9.mlp.up_proj.SCB": "model-00001-of-00002.safetensors",
510
- "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
511
- "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
512
- "model.layers.9.self_attn.k_proj.SCB": "model-00001-of-00002.safetensors",
513
- "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
514
- "model.layers.9.self_attn.o_proj.SCB": "model-00001-of-00002.safetensors",
515
- "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
516
- "model.layers.9.self_attn.q_proj.SCB": "model-00001-of-00002.safetensors",
517
- "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
518
- "model.layers.9.self_attn.v_proj.SCB": "model-00001-of-00002.safetensors",
519
- "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
520
- "model.norm.weight": "model-00002-of-00002.safetensors"
521
- }
522
- }