TheDrummer
commited on
Commit
•
448a9cf
1
Parent(s):
c66d63f
Upload folder using huggingface_hub
Browse files- README.md +41 -0
- config.json +30 -0
- mergekit_config.yml +10 -0
- model-00001-of-00029.safetensors +3 -0
- model-00002-of-00029.safetensors +3 -0
- model-00003-of-00029.safetensors +3 -0
- model-00004-of-00029.safetensors +3 -0
- model-00005-of-00029.safetensors +3 -0
- model-00006-of-00029.safetensors +3 -0
- model-00007-of-00029.safetensors +3 -0
- model-00008-of-00029.safetensors +3 -0
- model-00009-of-00029.safetensors +3 -0
- model-00010-of-00029.safetensors +3 -0
- model-00011-of-00029.safetensors +3 -0
- model-00012-of-00029.safetensors +3 -0
- model-00013-of-00029.safetensors +3 -0
- model-00014-of-00029.safetensors +3 -0
- model-00015-of-00029.safetensors +3 -0
- model-00016-of-00029.safetensors +3 -0
- model-00017-of-00029.safetensors +3 -0
- model-00018-of-00029.safetensors +3 -0
- model-00019-of-00029.safetensors +3 -0
- model-00020-of-00029.safetensors +3 -0
- model-00021-of-00029.safetensors +3 -0
- model-00022-of-00029.safetensors +3 -0
- model-00023-of-00029.safetensors +3 -0
- model-00024-of-00029.safetensors +3 -0
- model-00025-of-00029.safetensors +3 -0
- model-00026-of-00029.safetensors +3 -0
- model-00027-of-00029.safetensors +3 -0
- model-00028-of-00029.safetensors +3 -0
- model-00029-of-00029.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +42 -0
README.md
ADDED
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- BeaverAI/Moist-Miqu-70B-v1-RC1
|
4 |
+
- sophosympatheia/Midnight-Miqu-70B-v1.5
|
5 |
+
library_name: transformers
|
6 |
+
tags:
|
7 |
+
- mergekit
|
8 |
+
- merge
|
9 |
+
|
10 |
+
---
|
11 |
+
# merged
|
12 |
+
|
13 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
14 |
+
|
15 |
+
## Merge Details
|
16 |
+
### Merge Method
|
17 |
+
|
18 |
+
This model was merged using the [linear](https://arxiv.org/abs/2203.05482) merge method.
|
19 |
+
|
20 |
+
### Models Merged
|
21 |
+
|
22 |
+
The following models were included in the merge:
|
23 |
+
* [BeaverAI/Moist-Miqu-70B-v1-RC1](https://huggingface.co/BeaverAI/Moist-Miqu-70B-v1-RC1)
|
24 |
+
* [sophosympatheia/Midnight-Miqu-70B-v1.5](https://huggingface.co/sophosympatheia/Midnight-Miqu-70B-v1.5)
|
25 |
+
|
26 |
+
### Configuration
|
27 |
+
|
28 |
+
The following YAML configuration was used to produce this model:
|
29 |
+
|
30 |
+
```yaml
|
31 |
+
models:
|
32 |
+
- model: BeaverAI/Moist-Miqu-70B-v1-RC1
|
33 |
+
parameters:
|
34 |
+
weight: 0.75
|
35 |
+
- model: sophosympatheia/Midnight-Miqu-70B-v1.5
|
36 |
+
parameters:
|
37 |
+
weight: 0.25
|
38 |
+
merge_method: linear
|
39 |
+
|
40 |
+
#
|
41 |
+
```
|
config.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "BeaverAI/Moist-Miqu-70B-v1-RC1",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 8192,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 28672,
|
14 |
+
"max_position_embeddings": 32764,
|
15 |
+
"mlp_bias": false,
|
16 |
+
"model_type": "llama",
|
17 |
+
"num_attention_heads": 64,
|
18 |
+
"num_hidden_layers": 80,
|
19 |
+
"num_key_value_heads": 8,
|
20 |
+
"pad_token_id": 0,
|
21 |
+
"pretraining_tp": 1,
|
22 |
+
"rms_norm_eps": 1e-05,
|
23 |
+
"rope_scaling": null,
|
24 |
+
"rope_theta": 1000000,
|
25 |
+
"tie_word_embeddings": false,
|
26 |
+
"torch_dtype": "float16",
|
27 |
+
"transformers_version": "4.41.1",
|
28 |
+
"use_cache": true,
|
29 |
+
"vocab_size": 32000
|
30 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: BeaverAI/Moist-Miqu-70B-v1-RC1
|
3 |
+
parameters:
|
4 |
+
weight: 0.75
|
5 |
+
- model: sophosympatheia/Midnight-Miqu-70B-v1.5
|
6 |
+
parameters:
|
7 |
+
weight: 0.25
|
8 |
+
merge_method: linear
|
9 |
+
|
10 |
+
#
|
model-00001-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:381b0c5478c3da0b1e2b24adfcc78de8c132bcbae0fc582562ba2ff1cf6cc94e
|
3 |
+
size 4940974552
|
model-00002-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4640e6d02bafd3dab8b792e414d996cc4123780ed79d5276b4b0ee9cac6e0a4c
|
3 |
+
size 4664167392
|
model-00003-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:af905f978479ab11c03265a5f5bd8bedc11755fc4bae2af99ee4ac02c3928447
|
3 |
+
size 4982917880
|
model-00004-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b712ca8ce2a7aa7caae2b2a556745306e4f79635a7a5e781f32da77705c10edf
|
3 |
+
size 4999711704
|
model-00005-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5c62f2b7f92490ae0991ca921f897335fcaa12ab7e4c53d6c17dd4c4ca9c674d
|
3 |
+
size 4647373544
|
model-00006-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7544b26e481efd3f7ef1ebae608c986f1c8bb5468f8712695f449ec1dc3f548a
|
3 |
+
size 4664167384
|
model-00007-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e918f94b2ca12edd085f321c5f506e84a20a66332f3d0462161aa0bee894fcc
|
3 |
+
size 4664167392
|
model-00008-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fc4c4b837da655fd4a3339dfc585c427f75fba66efb9bcb02db626baa9cede69
|
3 |
+
size 4982917880
|
model-00009-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a250e9c239462ae1e3f280b19025ef25c395257238d8370f196b86769ae84dce
|
3 |
+
size 4999711696
|
model-00010-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a8c7ef9b8449ff8b038a070e89b32d2cedfbc950a9df2c9adcc7ff1e3ad2ff5
|
3 |
+
size 4647373552
|
model-00011-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:225fdd5f5b8b5638bbb6f82d79db97ebbc53a8f98c7a6fceb56b7ffe9c375482
|
3 |
+
size 4664167384
|
model-00012-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d4ce9ae0c404123f9edf429dc1921c9b6219000bb4292c91f086b5803adcaab
|
3 |
+
size 4664167392
|
model-00013-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01b04912b05c4b686b4c96c0685390c13f7449360ad3ab2b793b41006e324fc0
|
3 |
+
size 4982917872
|
model-00014-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f03addd6c2ad0bb35a9092b7f6bdaaeb2177fd9decebb5a8854bcc06c3fb9a50
|
3 |
+
size 4999711704
|
model-00015-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e45ecd5b34679e021a763dc2ba1d026e1a118bed088f18a97aba2a5a1a0206e0
|
3 |
+
size 4647373552
|
model-00016-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f158dc23ba2c30dbc3ffd9fd3bb16b54a68e69bc8bf45da23e4c490f4829374
|
3 |
+
size 4664167384
|
model-00017-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef658f26bba6169f17b480fba258fb5da87a0fd3dd402f4dd0eb98d35856b613
|
3 |
+
size 4664167384
|
model-00018-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:790b8686633c41dc6252a3f56582e2f41343667c0c681f36841e54a0880ef958
|
3 |
+
size 4982917880
|
model-00019-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45a1da87ddd6b2ca3eef3a269010dda4677f7f73b630651eda45508e9ee3593d
|
3 |
+
size 4999711704
|
model-00020-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f242e860ee45895f262c48a0d2a623938cc53da05857d68fe2565cf25610ab56
|
3 |
+
size 4647373552
|
model-00021-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:daf654afca4998a4458e67f69cd3147da4e0fcb1736c73ac0b826543e8dee04d
|
3 |
+
size 4664167376
|
model-00022-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e53224340ae070eff043e903caae2830f58aad1f223eb8d7fdb00a621b140b86
|
3 |
+
size 4664167392
|
model-00023-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:97619c34dd962614de052549afc19090b40cc1a556ad20da5167ee2eaef324ab
|
3 |
+
size 4982917880
|
model-00024-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad069c3ff36f76357e4991a3684d521212e6086aec860784a16dc6df9ae85891
|
3 |
+
size 4999711704
|
model-00025-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be0ca53409da93f0267086fe3fda4f9640d17052e2b48af19e5eb8f046115369
|
3 |
+
size 4647373544
|
model-00026-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4f47461674c842e14a10d9b1e3b5484979cf7d0ca34b5492ed377312a18ed96c
|
3 |
+
size 4664167384
|
model-00027-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c813c0793a6e192f14d4e35ab791c9679d0a33597bf67c5c7299a66bdd6e42c2
|
3 |
+
size 4664167392
|
model-00028-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:612ce6dad040013c11198e9be5623454ca0383d767d01d3c012b9571f7481515
|
3 |
+
size 4982917880
|
model-00029-of-00029.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb8be38676a4ea987b8e1d2b6e88f5bfdee381853b028f61085e82b3cb8d14fa
|
3 |
+
size 3573631344
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 137953296384}, "weight_map": {"lm_head.weight": "model-00001-of-00029.safetensors", "model.embed_tokens.weight": "model-00001-of-00029.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00029.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00029.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00029.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00029.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00029.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00029.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00029.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00029.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00029.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00029.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00029.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00029.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00029.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00029.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00029.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00029.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00029.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00029.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00029.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00029.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00029.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00029.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00029.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00029.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00029.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00003-of-00029.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00029.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00029.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00029.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.input_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00029.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00003-of-00029.safetensors", "model.layers.15.input_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00003-of-00029.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00003-of-00029.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00003-of-00029.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00029.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00003-of-00029.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00029.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00004-of-00029.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.input_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00004-of-00029.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.input_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00004-of-00029.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00004-of-00029.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00029.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00029.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00029.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00029.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00029.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00005-of-00029.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00005-of-00029.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00005-of-00029.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.input_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00005-of-00029.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00005-of-00029.safetensors", "model.layers.20.input_layernorm.weight": "model-00005-of-00029.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00005-of-00029.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00005-of-00029.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00006-of-00029.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00006-of-00029.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00006-of-00029.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00006-of-00029.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.input_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00006-of-00029.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.input_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00006-of-00029.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00006-of-00029.safetensors", "model.layers.23.input_layernorm.weight": "model-00006-of-00029.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00029.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00029.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00029.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00029.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00029.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00029.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.input_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00007-of-00029.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.input_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00007-of-00029.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00007-of-00029.safetensors", "model.layers.26.input_layernorm.weight": "model-00007-of-00029.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00008-of-00029.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00008-of-00029.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00008-of-00029.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00008-of-00029.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00008-of-00029.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00008-of-00029.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.input_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00008-of-00029.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00008-of-00029.safetensors", "model.layers.28.input_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00008-of-00029.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00008-of-00029.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00008-of-00029.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00008-of-00029.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00008-of-00029.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00008-of-00029.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00009-of-00029.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.input_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00009-of-00029.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.input_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00009-of-00029.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00009-of-00029.safetensors", "model.layers.30.input_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00009-of-00029.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00009-of-00029.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00009-of-00029.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00009-of-00029.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00009-of-00029.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00010-of-00029.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00029.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.input_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00029.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.input_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00010-of-00029.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00010-of-00029.safetensors", "model.layers.33.input_layernorm.weight": "model-00010-of-00029.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00010-of-00029.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00010-of-00029.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00011-of-00029.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00011-of-00029.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00011-of-00029.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00011-of-00029.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.input_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00011-of-00029.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.input_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00011-of-00029.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00011-of-00029.safetensors", "model.layers.36.input_layernorm.weight": "model-00011-of-00029.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00011-of-00029.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00012-of-00029.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00012-of-00029.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00012-of-00029.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00012-of-00029.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00012-of-00029.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.input_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00012-of-00029.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.input_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00012-of-00029.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00012-of-00029.safetensors", "model.layers.39.input_layernorm.weight": "model-00012-of-00029.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00013-of-00029.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00013-of-00029.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00013-of-00029.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00013-of-00029.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00013-of-00029.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00013-of-00029.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.input_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00013-of-00029.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00029.safetensors", "model.layers.40.input_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00013-of-00029.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00013-of-00029.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00013-of-00029.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00013-of-00029.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00013-of-00029.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00013-of-00029.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00014-of-00029.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.input_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00014-of-00029.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.input_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00014-of-00029.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00014-of-00029.safetensors", "model.layers.43.input_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00014-of-00029.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00014-of-00029.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00014-of-00029.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00014-of-00029.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00014-of-00029.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00015-of-00029.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00015-of-00029.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.input_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00015-of-00029.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.input_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00015-of-00029.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00015-of-00029.safetensors", "model.layers.46.input_layernorm.weight": "model-00015-of-00029.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00015-of-00029.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00015-of-00029.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00016-of-00029.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00016-of-00029.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00016-of-00029.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00016-of-00029.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.input_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00016-of-00029.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.input_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00016-of-00029.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00016-of-00029.safetensors", "model.layers.49.input_layernorm.weight": "model-00016-of-00029.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00016-of-00029.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00017-of-00029.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00017-of-00029.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00017-of-00029.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00017-of-00029.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00017-of-00029.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.input_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00017-of-00029.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.input_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00017-of-00029.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00017-of-00029.safetensors", "model.layers.51.input_layernorm.weight": "model-00017-of-00029.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00018-of-00029.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00018-of-00029.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00018-of-00029.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00018-of-00029.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00018-of-00029.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00018-of-00029.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.input_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00018-of-00029.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00018-of-00029.safetensors", "model.layers.53.input_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00018-of-00029.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00018-of-00029.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00018-of-00029.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00018-of-00029.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00018-of-00029.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00018-of-00029.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00019-of-00029.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.input_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00019-of-00029.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.input_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00019-of-00029.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00019-of-00029.safetensors", "model.layers.56.input_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00019-of-00029.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00019-of-00029.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00019-of-00029.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00019-of-00029.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00019-of-00029.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00020-of-00029.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00020-of-00029.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.input_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00020-of-00029.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.input_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00020-of-00029.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00020-of-00029.safetensors", "model.layers.59.input_layernorm.weight": "model-00020-of-00029.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00020-of-00029.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00020-of-00029.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00021-of-00029.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00021-of-00029.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00021-of-00029.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00021-of-00029.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.input_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00021-of-00029.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.input_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00021-of-00029.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00021-of-00029.safetensors", "model.layers.61.input_layernorm.weight": "model-00021-of-00029.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00021-of-00029.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00022-of-00029.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00022-of-00029.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00022-of-00029.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00022-of-00029.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00022-of-00029.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.input_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00022-of-00029.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.input_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00022-of-00029.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00022-of-00029.safetensors", "model.layers.64.input_layernorm.weight": "model-00022-of-00029.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00023-of-00029.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00023-of-00029.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00023-of-00029.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00023-of-00029.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00023-of-00029.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00023-of-00029.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.input_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00023-of-00029.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00023-of-00029.safetensors", "model.layers.66.input_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00023-of-00029.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00023-of-00029.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00023-of-00029.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00023-of-00029.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00023-of-00029.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00023-of-00029.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00024-of-00029.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.input_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00024-of-00029.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.input_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00024-of-00029.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00024-of-00029.safetensors", "model.layers.69.input_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00024-of-00029.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00024-of-00029.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00024-of-00029.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00024-of-00029.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00024-of-00029.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00025-of-00029.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00025-of-00029.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.input_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00025-of-00029.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.input_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00025-of-00029.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00025-of-00029.safetensors", "model.layers.71.input_layernorm.weight": "model-00025-of-00029.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00025-of-00029.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00025-of-00029.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00026-of-00029.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00026-of-00029.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00026-of-00029.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00026-of-00029.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.input_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00026-of-00029.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.input_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00026-of-00029.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00026-of-00029.safetensors", "model.layers.74.input_layernorm.weight": "model-00026-of-00029.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00026-of-00029.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00027-of-00029.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00027-of-00029.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00027-of-00029.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00027-of-00029.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00027-of-00029.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.input_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00027-of-00029.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.input_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00027-of-00029.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00027-of-00029.safetensors", "model.layers.77.input_layernorm.weight": "model-00027-of-00029.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00028-of-00029.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00028-of-00029.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00028-of-00029.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00028-of-00029.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00028-of-00029.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00028-of-00029.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.input_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00028-of-00029.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00028-of-00029.safetensors", "model.layers.79.input_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00028-of-00029.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00028-of-00029.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00028-of-00029.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00028-of-00029.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00028-of-00029.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00028-of-00029.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00029-of-00029.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.input_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00029-of-00029.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.input_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00029-of-00029.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00029-of-00029.safetensors", "model.norm.weight": "model-00029-of-00029.safetensors"}}
|
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.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
3 |
+
size 499723
|
tokenizer_config.json
ADDED
@@ -0,0 +1,42 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"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 |
+
"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 %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": false,
|
35 |
+
"model_max_length": 1000000000000000019884624838656,
|
36 |
+
"pad_token": "<unk>",
|
37 |
+
"sp_model_kwargs": {},
|
38 |
+
"spaces_between_special_tokens": false,
|
39 |
+
"tokenizer_class": "LlamaTokenizer",
|
40 |
+
"unk_token": "<unk>",
|
41 |
+
"use_default_system_prompt": false
|
42 |
+
}
|