powermove72
commited on
Commit
•
828d2df
1
Parent(s):
2deed61
Upload folder using huggingface_hub
Browse files- README.md +59 -0
- config.json +26 -0
- mergekit_config.yml +13 -0
- model-00001-of-00023.safetensors +3 -0
- model-00002-of-00023.safetensors +3 -0
- model-00003-of-00023.safetensors +3 -0
- model-00004-of-00023.safetensors +3 -0
- model-00005-of-00023.safetensors +3 -0
- model-00006-of-00023.safetensors +3 -0
- model-00007-of-00023.safetensors +3 -0
- model-00008-of-00023.safetensors +3 -0
- model-00009-of-00023.safetensors +3 -0
- model-00010-of-00023.safetensors +3 -0
- model-00011-of-00023.safetensors +3 -0
- model-00012-of-00023.safetensors +3 -0
- model-00013-of-00023.safetensors +3 -0
- model-00014-of-00023.safetensors +3 -0
- model-00015-of-00023.safetensors +3 -0
- model-00016-of-00023.safetensors +3 -0
- model-00017-of-00023.safetensors +3 -0
- model-00018-of-00023.safetensors +3 -0
- model-00019-of-00023.safetensors +3 -0
- model-00020-of-00023.safetensors +3 -0
- model-00021-of-00023.safetensors +3 -0
- model-00022-of-00023.safetensors +3 -0
- model-00023-of-00023.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +28 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +48 -0
README.md
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- merge
|
4 |
+
- mergekit
|
5 |
+
- lazymergekit
|
6 |
+
- powermove72/Trinity_Notus-xb
|
7 |
+
- powermove72/GreenScorpius-xb-Passthrough
|
8 |
+
base_model:
|
9 |
+
- powermove72/Trinity_Notus-xb
|
10 |
+
- powermove72/GreenScorpius-xb-Passthrough
|
11 |
+
---
|
12 |
+
|
13 |
+
# Elysium2.2-task-11b
|
14 |
+
|
15 |
+
Elysium2.2-task-11b is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
16 |
+
* [powermove72/Trinity_Notus-xb](https://huggingface.co/powermove72/Trinity_Notus-xb)
|
17 |
+
* [powermove72/GreenScorpius-xb-Passthrough](https://huggingface.co/powermove72/GreenScorpius-xb-Passthrough)
|
18 |
+
|
19 |
+
## 🧩 Configuration
|
20 |
+
|
21 |
+
```yaml
|
22 |
+
models:
|
23 |
+
- model: powermove72/Trinity_Notus-xb
|
24 |
+
parameters:
|
25 |
+
weight: 1
|
26 |
+
- model: powermove72/GreenScorpius-xb-Passthrough
|
27 |
+
parameters:
|
28 |
+
weight: 1
|
29 |
+
merge_method: task_arithmetic
|
30 |
+
base_model: powermove72/GreenScorpius-xb-Passthrough
|
31 |
+
parameters:
|
32 |
+
normalize: true
|
33 |
+
dtype: float16
|
34 |
+
```
|
35 |
+
|
36 |
+
## 💻 Usage
|
37 |
+
|
38 |
+
```python
|
39 |
+
!pip install -qU transformers accelerate
|
40 |
+
|
41 |
+
from transformers import AutoTokenizer
|
42 |
+
import transformers
|
43 |
+
import torch
|
44 |
+
|
45 |
+
model = "powermove72/Elysium2.2-task-11b"
|
46 |
+
messages = [{"role": "user", "content": "What is a large language model?"}]
|
47 |
+
|
48 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
49 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
50 |
+
pipeline = transformers.pipeline(
|
51 |
+
"text-generation",
|
52 |
+
model=model,
|
53 |
+
torch_dtype=torch.float16,
|
54 |
+
device_map="auto",
|
55 |
+
)
|
56 |
+
|
57 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
58 |
+
print(outputs[0]["generated_text"])
|
59 |
+
```
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "powermove72/GreenScorpius-xb-Passthrough",
|
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": 50,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "float16",
|
23 |
+
"transformers_version": "4.41.2",
|
24 |
+
"use_cache": true,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
models:
|
3 |
+
- model: powermove72/Trinity_Notus-xb
|
4 |
+
parameters:
|
5 |
+
weight: 1
|
6 |
+
- model: powermove72/GreenScorpius-xb-Passthrough
|
7 |
+
parameters:
|
8 |
+
weight: 1
|
9 |
+
merge_method: task_arithmetic
|
10 |
+
base_model: powermove72/GreenScorpius-xb-Passthrough
|
11 |
+
parameters:
|
12 |
+
normalize: true
|
13 |
+
dtype: float16
|
model-00001-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a3041a17597fcd4395db1b8c3797683c4256daae86d965f0375e8b67b5954921
|
3 |
+
size 960521544
|
model-00002-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6476bcd7e8ec287601f21c41ff6d60b3bbb9c72919270e9f7bd8c02fe5ca94aa
|
3 |
+
size 989890704
|
model-00003-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e67f35c45e70d4ad73fe759f8430b4f9a91a86c3eda1a1fa8bae9aa45619c8a2
|
3 |
+
size 989890712
|
model-00004-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:303e8b78afb32355af3640e66d739790eb99bfa4e7a716fab5ba1cfc622ca370
|
3 |
+
size 998287736
|
model-00005-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ffe0cf40f7c022bff8a41c44eb2fccd0f2c4b2cf5b19d61bb7691ba9350e0475
|
3 |
+
size 947956192
|
model-00006-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c786f8261de6ada9cc7db05a3a9308df3a542085ed1b34fa4d2bbb18dda146d
|
3 |
+
size 989890704
|
model-00007-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:35da47ef1b58d0999f069d2b6210a81abc1ff2e9b18fcd69c8696db28d1d5ecf
|
3 |
+
size 989890704
|
model-00008-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fe4c1702a4ec7197cc4e6f729209594b45715502485616052f4dd0181d3e3319
|
3 |
+
size 998287736
|
model-00009-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:aba431d2d8da9ed807954a67ac4fbd46cc91eddc69e16393babecc3b1a793cb5
|
3 |
+
size 947956192
|
model-00010-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:09fe8402b8e90499ef686f7a0e375b7b36d8c36079cbc88a01cb7deeb8c0a5e0
|
3 |
+
size 989890712
|
model-00011-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:198324bdb2a7d0e0d69aeb4284200c9cbe61a1ab999d525850b979445965ea0d
|
3 |
+
size 989890704
|
model-00012-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ad7e1f98d4b71f79c900fc7b6181a9edea53049814c3bc629317d4b4ad7730b6
|
3 |
+
size 998287736
|
model-00013-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02e00659f959af7e7d8e2da66cf8c8880f8793dffdc5897ad7dcdb5964956337
|
3 |
+
size 947956192
|
model-00014-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:53faf15da89b7bce4f80c311ac286d9764f3643ac6321d5a79718d3819582834
|
3 |
+
size 989890712
|
model-00015-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:74374ee53cc90c583d6a1b48da9a5beb34fd5d2277789a5e2eb7b94a2ef3c1c6
|
3 |
+
size 989890712
|
model-00016-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e4cce5027c14f9caf6360ecc2c2d35020b0a7d7072b44bf61b9bd68adafc9103
|
3 |
+
size 998287736
|
model-00017-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1282c1031e3ecafe40d199fd7c4c17d4b5623e17addc911da17f01aa97f6831
|
3 |
+
size 947956192
|
model-00018-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1a800a7a760d72e345133725f625a38c59577418a1c85b473e9ad98591453e3f
|
3 |
+
size 989890712
|
model-00019-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3cde76f7e038a8288f7873d9805006357aa2494b0cd07277d3e35323eebc723
|
3 |
+
size 989890712
|
model-00020-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c3cdad170ffb5612cce206791322f221c764f1436e3647ece4aac3b5bd08113
|
3 |
+
size 998287736
|
model-00021-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:52f6b8456f3a694f4d5e125deb3aa1f92be3d9103475f39006c8efab11a29377
|
3 |
+
size 947956184
|
model-00022-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5846904fa69a90e48b3ef1ee3cb4a8ec53438b466d11469f378f76f8b4af3c58
|
3 |
+
size 989890688
|
model-00023-of-00023.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:41f9092d5231f8c0edf5995bbe938dcb9e010b383e9007eb46a0761d0e94a3db
|
3 |
+
size 755009424
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 22335496192}, "weight_map": {"lm_head.weight": "model-00001-of-00023.safetensors", "model.embed_tokens.weight": "model-00001-of-00023.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00023.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00023.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00023.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00023.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00023.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00023.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00023.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00023.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00023.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00023.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00023.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00023.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00023.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00023.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00023.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00023.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00023.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00023.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00023.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00023.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00023.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00023.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00023.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00023.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00023.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00023.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00023.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00023.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00023.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00023.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00023.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00023.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00023.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00023.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00023.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00023.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00023.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00023.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00023.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00023.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00023.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00023.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00023.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00023.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00013-of-00023.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00013-of-00023.safetensors", "model.layers.34.input_layernorm.weight": "model-00013-of-00023.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00014-of-00023.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00014-of-00023.safetensors", "model.layers.36.input_layernorm.weight": "model-00014-of-00023.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00014-of-00023.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00015-of-00023.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00015-of-00023.safetensors", "model.layers.38.input_layernorm.weight": "model-00015-of-00023.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00015-of-00023.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00015-of-00023.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00016-of-00023.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.input_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00016-of-00023.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00016-of-00023.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00017-of-00023.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00017-of-00023.safetensors", "model.layers.42.input_layernorm.weight": "model-00017-of-00023.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00018-of-00023.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00018-of-00023.safetensors", "model.layers.44.input_layernorm.weight": "model-00018-of-00023.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00018-of-00023.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00019-of-00023.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00019-of-00023.safetensors", "model.layers.46.input_layernorm.weight": "model-00019-of-00023.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00019-of-00023.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00019-of-00023.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00020-of-00023.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.input_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00020-of-00023.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00020-of-00023.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00021-of-00023.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00021-of-00023.safetensors", "model.layers.6.input_layernorm.weight": "model-00021-of-00023.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00022-of-00023.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.input_layernorm.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00022-of-00023.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.input_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00023-of-00023.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00023-of-00023.safetensors", "model.norm.weight": "model-00023-of-00023.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
"unk_token": {
|
22 |
+
"content": "<unk>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
}
|
28 |
+
}
|
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 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"clean_up_tokenization_spaces": false,
|
37 |
+
"eos_token": "</s>",
|
38 |
+
"legacy": true,
|
39 |
+
"model_max_length": 1000000000000000019884624838656,
|
40 |
+
"pad_token": null,
|
41 |
+
"padding_side": "left",
|
42 |
+
"sp_model_kwargs": {},
|
43 |
+
"spaces_between_special_tokens": false,
|
44 |
+
"split_special_tokens": false,
|
45 |
+
"tokenizer_class": "LlamaTokenizer",
|
46 |
+
"unk_token": "<unk>",
|
47 |
+
"use_default_system_prompt": true
|
48 |
+
}
|