Upload folder using huggingface_hub
Browse files- README.md +145 -0
- config.json +38 -0
- measurement.json +0 -0
- mergekit_config.yml +35 -0
- model.safetensors.index.json +1 -0
- output-00001-of-00003.safetensors +3 -0
- output-00002-of-00003.safetensors +3 -0
- output-00003-of-00003.safetensors +3 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
README.md
ADDED
@@ -0,0 +1,145 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: Nohobby/MS-Schisandra-22B-v0.1
|
3 |
+
quantized_by: waldie
|
4 |
+
library_name: transformers
|
5 |
+
tags:
|
6 |
+
- mergekit
|
7 |
+
- merge
|
8 |
+
license: other
|
9 |
+
language:
|
10 |
+
- en
|
11 |
+
---
|
12 |
+
***
|
13 |
+
## Schisandra
|
14 |
+
|
15 |
+
Many thanks to the authors of the models used!
|
16 |
+
|
17 |
+
[RPMax v1.1](https://huggingface.co/ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1) | [Pantheon-RP](https://huggingface.co/Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small) | [Cydonia v1.2](https://huggingface.co/TheDrummer/Cydonia-22B-v1.2) | [Magnum V4](https://huggingface.co/anthracite-org/magnum-v4-22b) | [ChatWaifu v2.0](https://huggingface.co/spow12/ChatWaifu_v2.0_22B) | [SorcererLM](https://huggingface.co/InferenceIllusionist/SorcererLM-22B) | [Acolyte](https://huggingface.co/rAIfle/Acolyte-22B) | [NovusKyver](https://huggingface.co/Envoid/Mistral-Small-NovusKyver)
|
18 |
+
***
|
19 |
+
|
20 |
+
### Overview
|
21 |
+
|
22 |
+
Main uses: RP, Storywriting
|
23 |
+
|
24 |
+
Merge of 8 Mistral Small finetunes in total, which were then merged back into the original model to make it less stupid. Worked somehow? Definitely smarter than my previous MS merge and maybe some finetunes. Seems to really adhere to the writing style of the previous output, so you'll need either a good character card or an existing chat for a better replies.
|
25 |
+
|
26 |
+
***
|
27 |
+
|
28 |
+
### Quants
|
29 |
+
|
30 |
+
[Static](https://huggingface.co/mradermacher/MS-Schisandra-22B-vB-GGUF)
|
31 |
+
|
32 |
+
[Imatrix](https://huggingface.co/mradermacher/MS-Schisandra-22B-vB-i1-GGUF)
|
33 |
+
|
34 |
+
***
|
35 |
+
|
36 |
+
### Settings
|
37 |
+
|
38 |
+
Prompt format: Mistral-V3 Tekken
|
39 |
+
|
40 |
+
Samplers: [These](https://qu.ax/OusTx.json) or [These](https://huggingface.co/ToastyPigeon/ST-Presets-Mistral-Small/resolve/main/ST-sampling-preset-Mistral-Small.json?download=true)
|
41 |
+
|
42 |
+
***
|
43 |
+
|
44 |
+
## Merge Details
|
45 |
+
### Merging steps
|
46 |
+
|
47 |
+
## QCmix
|
48 |
+
|
49 |
+
```yaml
|
50 |
+
base_model: InferenceIllusionist/SorcererLM-22B
|
51 |
+
parameters:
|
52 |
+
int8_mask: true
|
53 |
+
rescale: true
|
54 |
+
normalize: false
|
55 |
+
dtype: bfloat16
|
56 |
+
tokenizer_source: base
|
57 |
+
merge_method: della
|
58 |
+
models:
|
59 |
+
- model: Envoid/Mistral-Small-NovusKyver
|
60 |
+
parameters:
|
61 |
+
density: [0.35, 0.65, 0.5, 0.65, 0.35]
|
62 |
+
epsilon: [0.1, 0.1, 0.25, 0.1, 0.1]
|
63 |
+
lambda: 0.85
|
64 |
+
weight: [-0.01891, 0.01554, -0.01325, 0.01791, -0.01458]
|
65 |
+
- model: rAIfle/Acolyte-22B
|
66 |
+
parameters:
|
67 |
+
density: [0.6, 0.4, 0.5, 0.4, 0.6]
|
68 |
+
epsilon: [0.15, 0.15, 0.25, 0.15, 0.15]
|
69 |
+
lambda: 0.85
|
70 |
+
weight: [0.01768, -0.01675, 0.01285, -0.01696, 0.01421]
|
71 |
+
```
|
72 |
+
|
73 |
+
## Schisandra-vA
|
74 |
+
|
75 |
+
```yaml
|
76 |
+
merge_method: della_linear
|
77 |
+
dtype: bfloat16
|
78 |
+
parameters:
|
79 |
+
normalize: true
|
80 |
+
int8_mask: true
|
81 |
+
tokenizer_source: union
|
82 |
+
base_model: TheDrummer/Cydonia-22B-v1.2
|
83 |
+
models:
|
84 |
+
- model: ArliAI/Mistral-Small-22B-ArliAI-RPMax-v1.1
|
85 |
+
parameters:
|
86 |
+
density: 0.55
|
87 |
+
weight: 1
|
88 |
+
- model: Gryphe/Pantheon-RP-Pure-1.6.2-22b-Small
|
89 |
+
parameters:
|
90 |
+
density: 0.55
|
91 |
+
weight: 1
|
92 |
+
- model: spow12/ChatWaifu_v2.0_22B
|
93 |
+
parameters:
|
94 |
+
density: 0.55
|
95 |
+
weight: 1
|
96 |
+
- model: anthracite-org/magnum-v4-22b
|
97 |
+
parameters:
|
98 |
+
density: 0.55
|
99 |
+
weight: 1
|
100 |
+
- model: QCmix
|
101 |
+
parameters:
|
102 |
+
density: 0.55
|
103 |
+
weight: 1
|
104 |
+
```
|
105 |
+
|
106 |
+
## Schisandra
|
107 |
+
|
108 |
+
```yaml
|
109 |
+
dtype: bfloat16
|
110 |
+
tokenizer_source: base
|
111 |
+
merge_method: della_linear
|
112 |
+
parameters:
|
113 |
+
density: 0.5
|
114 |
+
base_model: Schisandra
|
115 |
+
models:
|
116 |
+
- model: unsloth/Mistral-Small-Instruct-2409
|
117 |
+
parameters:
|
118 |
+
weight:
|
119 |
+
- filter: v_proj
|
120 |
+
value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
|
121 |
+
- filter: o_proj
|
122 |
+
value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
|
123 |
+
- filter: up_proj
|
124 |
+
value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
|
125 |
+
- filter: gate_proj
|
126 |
+
value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
|
127 |
+
- filter: down_proj
|
128 |
+
value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
|
129 |
+
- value: 0
|
130 |
+
- model: Schisandra
|
131 |
+
parameters:
|
132 |
+
weight:
|
133 |
+
- filter: v_proj
|
134 |
+
value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
|
135 |
+
- filter: o_proj
|
136 |
+
value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
|
137 |
+
- filter: up_proj
|
138 |
+
value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
|
139 |
+
- filter: gate_proj
|
140 |
+
value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
|
141 |
+
- filter: down_proj
|
142 |
+
value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
|
143 |
+
- value: 1
|
144 |
+
|
145 |
+
```
|
config.json
ADDED
@@ -0,0 +1,38 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Schisandra",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"head_dim": 128,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 6144,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 16384,
|
14 |
+
"max_position_embeddings": 32768,
|
15 |
+
"model_type": "mistral",
|
16 |
+
"num_attention_heads": 48,
|
17 |
+
"num_hidden_layers": 56,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"rms_norm_eps": 1e-05,
|
20 |
+
"rope_theta": 1000000.0,
|
21 |
+
"sliding_window": null,
|
22 |
+
"tie_word_embeddings": false,
|
23 |
+
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.46.0",
|
25 |
+
"use_cache": true,
|
26 |
+
"vocab_size": 32768,
|
27 |
+
"quantization_config": {
|
28 |
+
"quant_method": "exl2",
|
29 |
+
"version": "0.2.3",
|
30 |
+
"bits": 6.5,
|
31 |
+
"head_bits": 6,
|
32 |
+
"calibration": {
|
33 |
+
"rows": 115,
|
34 |
+
"length": 2048,
|
35 |
+
"dataset": "(default)"
|
36 |
+
}
|
37 |
+
}
|
38 |
+
}
|
measurement.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
mergekit_config.yml
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
dtype: bfloat16
|
2 |
+
tokenizer_source: base
|
3 |
+
merge_method: della_linear
|
4 |
+
parameters:
|
5 |
+
density: 0.5
|
6 |
+
base_model: Schisandra
|
7 |
+
models:
|
8 |
+
- model: unsloth/Mistral-Small-Instruct-2409
|
9 |
+
parameters:
|
10 |
+
weight:
|
11 |
+
- filter: v_proj
|
12 |
+
value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
|
13 |
+
- filter: o_proj
|
14 |
+
value: [1, 0, 1, 0, 0, 0, 0, 0, 1, 1, 1]
|
15 |
+
- filter: up_proj
|
16 |
+
value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
|
17 |
+
- filter: gate_proj
|
18 |
+
value: [0, 0, 1, 1, 1, 1, 1, 1, 1, 0, 0]
|
19 |
+
- filter: down_proj
|
20 |
+
value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
|
21 |
+
- value: 0
|
22 |
+
- model: Schisandra
|
23 |
+
parameters:
|
24 |
+
weight:
|
25 |
+
- filter: v_proj
|
26 |
+
value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
|
27 |
+
- filter: o_proj
|
28 |
+
value: [0, 1, 0, 1, 1, 1, 1, 1, 0, 0, 0]
|
29 |
+
- filter: up_proj
|
30 |
+
value: [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
|
31 |
+
- filter: gate_proj
|
32 |
+
value: [1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 1]
|
33 |
+
- filter: down_proj
|
34 |
+
value: [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]
|
35 |
+
- value: 1
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 44494565376}, "weight_map": {"lm_head.weight": "model-00001-of-00010.safetensors", "model.embed_tokens.weight": "model-00001-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.48.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.53.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00010-of-00010.safetensors", "model.norm.weight": "model-00010-of-00010.safetensors"}}
|
output-00001-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2b8dc644a5d6aeb7ef401abbe29aa080cba1ae805e18417b6728727a3b0b1400
|
3 |
+
size 8541653504
|
output-00002-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dbc9bdc3ed61d270b61c16cac43eaea7bb289ecc307c4a84b48f80f37b365cb8
|
3 |
+
size 8537669336
|
output-00003-of-00003.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a8f5bb4912a63059b0a136f33039472ada9765ff7bf03657ebbdce8253ffcb41
|
3 |
+
size 1232120464
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<s>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": {
|
17 |
+
"content": "</s>",
|
18 |
+
"lstrip": false,
|
19 |
+
"normalized": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"single_word": false
|
22 |
+
},
|
23 |
+
"unk_token": {
|
24 |
+
"content": "<unk>",
|
25 |
+
"lstrip": false,
|
26 |
+
"normalized": false,
|
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_config.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|