Reiterate3680
commited on
Commit
•
babc610
1
Parent(s):
6bfd714
Upload folder using huggingface_hub
Browse files- README.md +81 -0
- config.json +28 -0
- mergekit_config.yml +14 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +35 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +48 -0
README.md
ADDED
@@ -0,0 +1,81 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model:
|
3 |
+
- matchaaaaa/Honey-Yuzu-13B
|
4 |
+
tags:
|
5 |
+
- merge
|
6 |
+
- mergekit
|
7 |
+
---
|
8 |
+
|
9 |
+
MERGE BROUGHT TO YOU BY:
|
10 |
+
- Mergekit Config Stolen From matchaaaaa/Honey-Yuzu-13B
|
11 |
+
- Trying to use lazymergekit at first except I had to throw everything out anyway and do the multi-step merge by hand
|
12 |
+
|
13 |
+
```yaml
|
14 |
+
slices: # this is a quick float32 restack of BLC using the OG recipe
|
15 |
+
- sources:
|
16 |
+
- model: SanjiWatsuki/Kunoichi-7B
|
17 |
+
layer_range: [0, 24]
|
18 |
+
- sources:
|
19 |
+
- model: SanjiWatsuki/Silicon-Maid-7B
|
20 |
+
layer_range: [8, 24]
|
21 |
+
- sources:
|
22 |
+
- model: KatyTheCutie/LemonadeRP-4.5.3
|
23 |
+
layer_range: [24, 32]
|
24 |
+
merge_method: passthrough
|
25 |
+
dtype: float32
|
26 |
+
name: Big-Lemon-Cookie-11B
|
27 |
+
---
|
28 |
+
models: # this is a remake of CLC with the newer Fimbul v2.1 version
|
29 |
+
- model: Big-Lemon-Cookie-11B
|
30 |
+
parameters:
|
31 |
+
weight: 0.8
|
32 |
+
- model: Sao10K/Fimbulvetr-11B-v2 # Fim 2.1 performs significantly worse imo, and we don't care about 16k
|
33 |
+
parameters:
|
34 |
+
weight: 0.2
|
35 |
+
merge_method: linear
|
36 |
+
dtype: float32
|
37 |
+
name: Chunky-Lemon-Cookie-11B
|
38 |
+
---
|
39 |
+
slices: # 8 layers of WL for the splice
|
40 |
+
- sources:
|
41 |
+
- model: senseable/WestLake-7B-v2
|
42 |
+
layer_range: [8, 16]
|
43 |
+
merge_method: passthrough
|
44 |
+
dtype: float32
|
45 |
+
name: WL-splice
|
46 |
+
---
|
47 |
+
slices: # 8 layers of CLC for the splice
|
48 |
+
- sources:
|
49 |
+
- model: Chunky-Lemon-Cookie-11B
|
50 |
+
layer_range: [8, 16]
|
51 |
+
merge_method: passthrough
|
52 |
+
dtype: float32
|
53 |
+
name: CLC-splice
|
54 |
+
---
|
55 |
+
models: # this is the splice, a gradient merge meant to gradually and smoothly interpolate between stacks of different models
|
56 |
+
- model: WL-splice
|
57 |
+
parameters:
|
58 |
+
weight: [1, 1, 0.75, 0.625, 0.5, 0.375, 0.25, 0, 0] # 0.125 / 0.875 values removed here - "math gets screwy"
|
59 |
+
- model: CLC-splice
|
60 |
+
parameters:
|
61 |
+
weight: [0, 0, 0.25, 0.375, 0.5, 0.625, 0.75, 1, 1] # 0.125 / 0.875 values removed here - "math gets screwy"
|
62 |
+
merge_method: della_linear # New Meme
|
63 |
+
base_model: WL-splice
|
64 |
+
dtype: float32
|
65 |
+
name: splice
|
66 |
+
---
|
67 |
+
slices: # putting it all together
|
68 |
+
- sources:
|
69 |
+
- model: senseable/WestLake-7B-v2
|
70 |
+
layer_range: [0, 16]
|
71 |
+
- sources:
|
72 |
+
- model: splice
|
73 |
+
layer_range: [0, 8]
|
74 |
+
- sources:
|
75 |
+
- model: Chunky-Lemon-Cookie-11B
|
76 |
+
layer_range: [16, 48]
|
77 |
+
merge_method: passthrough
|
78 |
+
dtype: float32
|
79 |
+
name: Honey-Yuzu-Mod-13B
|
80 |
+
|
81 |
+
```
|
config.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "splice",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
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": 56,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"pad_token_id": 2,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_theta": 10000.0,
|
21 |
+
"sliding_window": 4096,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "float32",
|
24 |
+
"transformers_version": "4.42.4",
|
25 |
+
"unsloth_version": "2024.1",
|
26 |
+
"use_cache": true,
|
27 |
+
"vocab_size": 32000
|
28 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
slices: # putting it all together
|
2 |
+
- sources:
|
3 |
+
- model: senseable/WestLake-7B-v2
|
4 |
+
layer_range: [0, 16]
|
5 |
+
- sources:
|
6 |
+
- model: splice
|
7 |
+
layer_range: [0, 8]
|
8 |
+
- sources:
|
9 |
+
- model: Chunky-Lemon-Cookie-11B
|
10 |
+
layer_range: [16, 48]
|
11 |
+
merge_method: passthrough
|
12 |
+
dtype: float32
|
13 |
+
name: Honey-Yuzu-Mod-13B
|
14 |
+
|
model-00001-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d6671b7f3a7deb799c014e0346c12d84ed6df17a0512221b3fb737c7e9995dca
|
3 |
+
size 4773270016
|
model-00002-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:10ebf23cd63978b40caa737562ec42da2f732c812f385818058e66564fba1e10
|
3 |
+
size 4999813128
|
model-00003-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8928d73925a9c5eaaefabd80c689ff2e4e9cef2df457ce6867fe78d308fca75b
|
3 |
+
size 4999796152
|
model-00004-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5bd01c3d93d84ced455e5d9ad1bdbce74dab4ad0208692f5ae784ab04e1da0ce
|
3 |
+
size 4832024456
|
model-00005-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:14b843bf1e4b8aa3acb3982eb611e89f17cc784469e710e06bbc1a1a98f0865b
|
3 |
+
size 4832023992
|
model-00006-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f929a79f7550e9f515e1cfbf86f143da4da5eb1a0edf19a5cacea5cdc249740f
|
3 |
+
size 4999796624
|
model-00007-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4930c8d3a4df44e3d90aaca7c3e5c5eac9aab3d4f1eaa25d5f167e5b4eac33bb
|
3 |
+
size 4999829608
|
model-00008-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74dccc2495bada975965b93af4aa6e9350495a2f82c332599603ac6d502394ea
|
3 |
+
size 4999796632
|
model-00009-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5aaf087f686a599a8fa101e9f49ab243dc6abbf1bd8f2097d2dea83c4cf949d0
|
3 |
+
size 4999796152
|
model-00010-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e67a3ae51116160b601c3d2a6199b4f499cf6747624fb4b667de9f6bb6536326
|
3 |
+
size 4832024424
|
model-00011-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f69ad5b978a93cad11a7502e8b8354c223fe58f9e627dd9bb2d73aef45ea45a7
|
3 |
+
size 637567896
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 49905680384}, "weight_map": {"lm_head.weight": "model-00001-of-00011.safetensors", "model.embed_tokens.weight": "model-00001-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.49.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.50.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.51.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.52.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.54.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.55.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "<unk>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
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:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"add_prefix_space": null,
|
5 |
+
"added_tokens_decoder": {
|
6 |
+
"0": {
|
7 |
+
"content": "<unk>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false,
|
12 |
+
"special": true
|
13 |
+
},
|
14 |
+
"1": {
|
15 |
+
"content": "<s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false,
|
20 |
+
"special": true
|
21 |
+
},
|
22 |
+
"2": {
|
23 |
+
"content": "</s>",
|
24 |
+
"lstrip": false,
|
25 |
+
"normalized": false,
|
26 |
+
"rstrip": false,
|
27 |
+
"single_word": false,
|
28 |
+
"special": true
|
29 |
+
}
|
30 |
+
},
|
31 |
+
"additional_special_tokens": [
|
32 |
+
"<unk>",
|
33 |
+
"<s>",
|
34 |
+
"</s>"
|
35 |
+
],
|
36 |
+
"bos_token": "<s>",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "</s>",
|
39 |
+
"legacy": true,
|
40 |
+
"model_max_length": 255,
|
41 |
+
"pad_token": "<unk>",
|
42 |
+
"padding_side": "right",
|
43 |
+
"sp_model_kwargs": {},
|
44 |
+
"spaces_between_special_tokens": false,
|
45 |
+
"tokenizer_class": "LlamaTokenizer",
|
46 |
+
"unk_token": "<unk>",
|
47 |
+
"use_default_system_prompt": true
|
48 |
+
}
|