louisbrulenaudet
commited on
Commit
•
bdab3c5
1
Parent(s):
e926f26
Upload folder using huggingface_hub
Browse files- README.md +52 -0
- config.json +29 -0
- mergekit_config.yml +7 -0
- model-00001-of-00036.safetensors +3 -0
- model-00002-of-00036.safetensors +3 -0
- model-00003-of-00036.safetensors +3 -0
- model-00004-of-00036.safetensors +3 -0
- model-00005-of-00036.safetensors +3 -0
- model-00006-of-00036.safetensors +3 -0
- model-00007-of-00036.safetensors +3 -0
- model-00008-of-00036.safetensors +3 -0
- model-00009-of-00036.safetensors +3 -0
- model-00010-of-00036.safetensors +3 -0
- model-00011-of-00036.safetensors +3 -0
- model-00012-of-00036.safetensors +3 -0
- model-00013-of-00036.safetensors +3 -0
- model-00014-of-00036.safetensors +3 -0
- model-00015-of-00036.safetensors +3 -0
- model-00016-of-00036.safetensors +3 -0
- model-00017-of-00036.safetensors +3 -0
- model-00018-of-00036.safetensors +3 -0
- model-00019-of-00036.safetensors +3 -0
- model-00020-of-00036.safetensors +3 -0
- model-00021-of-00036.safetensors +3 -0
- model-00022-of-00036.safetensors +3 -0
- model-00023-of-00036.safetensors +3 -0
- model-00024-of-00036.safetensors +3 -0
- model-00025-of-00036.safetensors +3 -0
- model-00026-of-00036.safetensors +3 -0
- model-00027-of-00036.safetensors +3 -0
- model-00028-of-00036.safetensors +3 -0
- model-00029-of-00036.safetensors +3 -0
- model-00030-of-00036.safetensors +3 -0
- model-00031-of-00036.safetensors +3 -0
- model-00032-of-00036.safetensors +3 -0
- model-00033-of-00036.safetensors +3 -0
- model-00034-of-00036.safetensors +3 -0
- model-00035-of-00036.safetensors +3 -0
- model-00036-of-00036.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +43 -0
README.md
ADDED
@@ -0,0 +1,52 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
{}
|
3 |
+
---
|
4 |
+
9o
|
5 |
+
---
|
6 |
+
license:
|
7 |
+
base_model:
|
8 |
+
tags:
|
9 |
+
- merge
|
10 |
+
- mergekit
|
11 |
+
- lazymergekit
|
12 |
+
---
|
13 |
+
|
14 |
+
# Maxine-34B-stock
|
15 |
+
|
16 |
+
Maxine-34B-stock is a merge of the following models:
|
17 |
+
|
18 |
+
## Configuration
|
19 |
+
|
20 |
+
```yaml
|
21 |
+
models:
|
22 |
+
- model: ConvexAI/Luminex-34B-v0.2
|
23 |
+
- model: fblgit/UNA-34BeagleSimpleMath-32K-v1
|
24 |
+
merge_method: model_stock
|
25 |
+
base_model: abacusai/Smaug-34B-v0.1
|
26 |
+
dtype: bfloat16
|
27 |
+
```
|
28 |
+
|
29 |
+
## Usage
|
30 |
+
|
31 |
+
```python
|
32 |
+
!pip install -qU transformers accelerate
|
33 |
+
|
34 |
+
from transformers import AutoTokenizer
|
35 |
+
import transformers
|
36 |
+
import torch
|
37 |
+
|
38 |
+
model = "louisbrulenaudet/Maxine-34B-stock"
|
39 |
+
messages = [{"role": "user", "content": "What is a large language model?"}]
|
40 |
+
|
41 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
42 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
43 |
+
pipeline = transformers.pipeline(
|
44 |
+
"text-generation",
|
45 |
+
model=model,
|
46 |
+
torch_dtype=torch.float16,
|
47 |
+
device_map="auto",
|
48 |
+
)
|
49 |
+
|
50 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
51 |
+
print(outputs[0]["generated_text"])
|
52 |
+
```
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "abacusai/Smaug-34B-v0.1",
|
3 |
+
"architectures": [
|
4 |
+
"LlamaForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_bias": false,
|
7 |
+
"attention_dropout": 0.0,
|
8 |
+
"bos_token_id": 1,
|
9 |
+
"eos_token_id": 2,
|
10 |
+
"hidden_act": "silu",
|
11 |
+
"hidden_size": 7168,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 20480,
|
14 |
+
"max_position_embeddings": 200000,
|
15 |
+
"model_type": "llama",
|
16 |
+
"num_attention_heads": 56,
|
17 |
+
"num_hidden_layers": 60,
|
18 |
+
"num_key_value_heads": 8,
|
19 |
+
"pad_token_id": 0,
|
20 |
+
"pretraining_tp": 1,
|
21 |
+
"rms_norm_eps": 1e-05,
|
22 |
+
"rope_scaling": null,
|
23 |
+
"rope_theta": 5000000.0,
|
24 |
+
"tie_word_embeddings": false,
|
25 |
+
"torch_dtype": "bfloat16",
|
26 |
+
"transformers_version": "4.37.2",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 64000
|
29 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
models:
|
3 |
+
- model: ConvexAI/Luminex-34B-v0.2
|
4 |
+
- model: fblgit/UNA-34BeagleSimpleMath-32K-v1
|
5 |
+
merge_method: model_stock
|
6 |
+
base_model: abacusai/Smaug-34B-v0.1
|
7 |
+
dtype: bfloat16
|
model-00001-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45067b3b4ff5578f93140ace03b9c1e23fd85f7a41d6aa7f1f0e2a94c2582b2f
|
3 |
+
size 1937798888
|
model-00002-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:048b784faa5369552f9f7a5596c62c2eeb5c9f776b2e37f815ce4e3663fa217d
|
3 |
+
size 1937827776
|
model-00003-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f529cf674a4327c1c61e190ec1f87a522eda1282cbeb62942df689f6210943e1
|
3 |
+
size 1739588416
|
model-00004-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0ca92d0d14d1338cfafc3ceaaafda07d036bd4a9e587c971a541f91fb5eca53
|
3 |
+
size 1996533240
|
model-00005-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89fe4ac408bfd0f931701130d639f66d2bae8331d1b2bae72fd790b866bf4101
|
3 |
+
size 1937842224
|
model-00006-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f4ff56327099502d940b65c8a013aeafb3f8d8bbd5c7d4d1716abc9f1238a7df
|
3 |
+
size 1937798904
|
model-00007-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:946a0f42775572060f072184b45a24b0c6dd9c5c084aab11b5ded19a019e423d
|
3 |
+
size 1937827776
|
model-00008-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff2b43bf557b342edfb0d6c9a408bcffa541faba4e9f23576afd71e83276852b
|
3 |
+
size 1937827792
|
model-00009-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c5d00e2e6691f9b5d759d016c5b3c1b2938c1561c7ed7df6205ab630590a4b46
|
3 |
+
size 1937827792
|
model-00010-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:43f0c4780b17014ed7be7917c9ae65ec40b577b819e1d82ccc1e27073ba1f31f
|
3 |
+
size 1996547696
|
model-00011-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d0bbc88b10da94f584a673f89dcb89c8bd973ae87f7f4e83d1ac74399edebb81
|
3 |
+
size 1937798888
|
model-00012-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:641a76ec29ce9615cdacfdab89d1adfd223d281e0b8f45f59ae0936411c217fb
|
3 |
+
size 1996533256
|
model-00013-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a5c6246021b29dda4c9f14474b0aa78f9586baf2a9b69024da5e0c45853b515
|
3 |
+
size 1937827784
|
model-00014-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e49737b7bc06dd138244ee305c95b0a429f8ff1f213fad4694498cfef16a2b3b
|
3 |
+
size 1937813352
|
model-00015-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b245e8cf99706c0c9c106c9cf89f3731c185a2c00627fc574c7b11f2f9d184bd
|
3 |
+
size 1937856696
|
model-00016-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7272feba5cc45e5c3ebb49937927d44f4960f3941afb9651d0ce20d0aa9994f
|
3 |
+
size 1937798904
|
model-00017-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dd5ea9876dd64a4e4a06f0e537b35d0f830668016caf52dc9ebf85349bf9e4fa
|
3 |
+
size 1937827792
|
model-00018-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:efb6c0c11029e0f58bf72679c0006b11a44cf402ddcc88331b005eeefdb62a58
|
3 |
+
size 1996518792
|
model-00019-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dfc8054140c1f5ffed0721bd13db3ead5879589d0f0fb5832fc1befe1e130cbb
|
3 |
+
size 1937827792
|
model-00020-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4eb9b9760c27ac2ae3618961cd7c7395dd5643a1b88487ba02635dcde2381fac
|
3 |
+
size 1937827792
|
model-00021-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e11e16c94d6175ae47088beef0333c3b32914b98286489829c950b523d6a9cec
|
3 |
+
size 1996533256
|
model-00022-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:62905cb5fa555c498508c84d48f5b60c2a930d5fc71d8b6ffe59a70fdabf7c69
|
3 |
+
size 1937813352
|
model-00023-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:573f0c7073a38968065da41f5a7e74a3bc7c30e398ffdd9065a55c68ca9f4ddf
|
3 |
+
size 1937827784
|
model-00024-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ce7ce0daa583811c058b3be674c27307aad2e870def490b289d37bf9352c74fe
|
3 |
+
size 1937827808
|
model-00025-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:77f44d54392059496d4185bdf7b1674bd8b46b599892a959095505d419cced60
|
3 |
+
size 1996547696
|
model-00026-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:81ce9ada4a214d70b476b54a44d0e79da901da23a8ad803c38662c375514e3ea
|
3 |
+
size 1937798896
|
model-00027-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cd3ed89b2e6eed9a1ea4fbf229077b67bc893b0b5548f7500cb699d18b424026
|
3 |
+
size 1937827792
|
model-00028-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:477646632595fdf7b43eb7965d3a5698ad1fe9c1414f18a05b681c7329ee5c84
|
3 |
+
size 1937827792
|
model-00029-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e39a5ae5e9560e4ced334f15c711798232eb7a12a7fa58febfc432970f7161e7
|
3 |
+
size 1996533256
|
model-00030-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ef8475d8e2b20a0fe93d4f7b4e257a8c049f30e930262fd2a393780271c4f3a4
|
3 |
+
size 1937842240
|
model-00031-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff99b305363830d4170ef368595b2618145893caacedfc873aea899dc15b4280
|
3 |
+
size 1937798904
|
model-00032-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de0044109ec948cd03a9a5a2e224b875b7509302b04c6c832b83a822d66ee1be
|
3 |
+
size 1937827808
|
model-00033-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7a45baf20ee7256c21c4211203474be8b800857b7fe705ca580a43970f00c25c
|
3 |
+
size 1996518792
|
model-00034-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f49f41a52414ad4b14ce08baaabc88b6df5ce6a272ef9b9476f0a7b128f767f7
|
3 |
+
size 1937827808
|
model-00035-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:897d9c40e273bf091b2d80ca4675135b086eb80558a928802c2ce0b25e9e1ed2
|
3 |
+
size 1409344904
|
model-00036-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:16eba56c61a12a8d96b5063e7182721448686ca406730fda8ff1bf55b54268db
|
3 |
+
size 1211148856
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 68777834496}, "weight_map": {"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00036.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00036.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00036.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00036.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00036.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00036.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00036.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00036.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00036.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00036.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00036.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00036.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00036.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00036.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00036.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00036.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00036.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00036.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00036.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00036.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00036.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00036.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00036.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00002-of-00036.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00036.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00036.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00036.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00036.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00036.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00036.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00036.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00036.safetensors", "model.embed_tokens.weight": "model-00003-of-00036.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00036.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00036.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00036.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00036.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00036.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00036.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00004-of-00036.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00036.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00004-of-00036.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00036.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00036.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00036.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00036.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00036.safetensors", "model.layers.6.input_layernorm.weight": "model-00004-of-00036.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00004-of-00036.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00036.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00004-of-00036.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00036.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00036.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00036.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00036.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00036.safetensors", "model.layers.5.input_layernorm.weight": "model-00005-of-00036.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00005-of-00036.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00005-of-00036.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00005-of-00036.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00036.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00005-of-00036.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00005-of-00036.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00005-of-00036.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00005-of-00036.safetensors", "model.layers.4.input_layernorm.weight": "model-00005-of-00036.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00005-of-00036.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00005-of-00036.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00005-of-00036.safetensors", "model.layers.3.input_layernorm.weight": "model-00005-of-00036.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00036.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00036.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00036.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00036.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00036.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00036.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00036.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00036.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00036.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00036.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00036.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00036.safetensors", "model.layers.11.input_layernorm.weight": "model-00006-of-00036.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00006-of-00036.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00036.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00007-of-00036.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00036.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00007-of-00036.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00007-of-00036.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00007-of-00036.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00007-of-00036.safetensors", "model.layers.10.input_layernorm.weight": "model-00007-of-00036.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00007-of-00036.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00007-of-00036.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00007-of-00036.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00007-of-00036.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00007-of-00036.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00007-of-00036.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00007-of-00036.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00007-of-00036.safetensors", "model.layers.9.input_layernorm.weight": "model-00007-of-00036.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00007-of-00036.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00008-of-00036.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00008-of-00036.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00036.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00008-of-00036.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00008-of-00036.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00008-of-00036.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00008-of-00036.safetensors", "model.layers.8.input_layernorm.weight": "model-00008-of-00036.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00008-of-00036.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00008-of-00036.safetensors", "model.layers.7.input_layernorm.weight": "model-00008-of-00036.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00036.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00036.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00036.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00036.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00036.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00036.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00009-of-00036.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00009-of-00036.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00009-of-00036.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00009-of-00036.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00036.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00009-of-00036.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00036.safetensors", "model.layers.15.input_layernorm.weight": "model-00009-of-00036.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00009-of-00036.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00009-of-00036.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00009-of-00036.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00009-of-00036.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00036.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00009-of-00036.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00009-of-00036.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00009-of-00036.safetensors", "model.layers.14.input_layernorm.weight": "model-00009-of-00036.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00010-of-00036.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00010-of-00036.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00010-of-00036.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00036.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00010-of-00036.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00010-of-00036.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00036.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00036.safetensors", "model.layers.13.input_layernorm.weight": "model-00010-of-00036.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00010-of-00036.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00010-of-00036.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00010-of-00036.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00036.safetensors", "model.layers.12.input_layernorm.weight": "model-00010-of-00036.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00011-of-00036.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00011-of-00036.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00011-of-00036.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00036.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00036.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00011-of-00036.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00011-of-00036.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00036.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00036.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00036.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00036.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00036.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00036.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00011-of-00036.safetensors", "model.layers.19.input_layernorm.weight": "model-00011-of-00036.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00012-of-00036.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00012-of-00036.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00012-of-00036.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00012-of-00036.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00036.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00012-of-00036.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00012-of-00036.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00012-of-00036.safetensors", "model.layers.18.input_layernorm.weight": "model-00012-of-00036.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00012-of-00036.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00012-of-00036.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00012-of-00036.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00036.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00013-of-00036.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00013-of-00036.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00013-of-00036.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00013-of-00036.safetensors", "model.layers.17.input_layernorm.weight": "model-00013-of-00036.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00013-of-00036.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00013-of-00036.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00013-of-00036.safetensors", "model.layers.16.input_layernorm.weight": "model-00013-of-00036.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00013-of-00036.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00013-of-00036.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00013-of-00036.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00013-of-00036.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00013-of-00036.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00013-of-00036.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00013-of-00036.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00013-of-00036.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00014-of-00036.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00014-of-00036.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00014-of-00036.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00014-of-00036.safetensors", "model.layers.24.input_layernorm.weight": "model-00014-of-00036.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00014-of-00036.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00014-of-00036.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00014-of-00036.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00014-of-00036.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00014-of-00036.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00014-of-00036.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00014-of-00036.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00014-of-00036.safetensors", "model.layers.23.input_layernorm.weight": "model-00014-of-00036.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00014-of-00036.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00036.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00015-of-00036.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00015-of-00036.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00036.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00036.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00015-of-00036.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00036.safetensors", "model.layers.22.input_layernorm.weight": "model-00015-of-00036.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00015-of-00036.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00015-of-00036.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00015-of-00036.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00015-of-00036.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00015-of-00036.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00015-of-00036.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00015-of-00036.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00015-of-00036.safetensors", "model.layers.21.input_layernorm.weight": "model-00015-of-00036.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00015-of-00036.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00015-of-00036.safetensors", "model.layers.20.input_layernorm.weight": "model-00015-of-00036.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00016-of-00036.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00016-of-00036.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00016-of-00036.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00016-of-00036.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00016-of-00036.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00016-of-00036.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00016-of-00036.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00016-of-00036.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00016-of-00036.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00016-of-00036.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00016-of-00036.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00016-of-00036.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00016-of-00036.safetensors", "model.layers.28.input_layernorm.weight": "model-00016-of-00036.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00016-of-00036.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00017-of-00036.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00017-of-00036.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00017-of-00036.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00017-of-00036.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00017-of-00036.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00017-of-00036.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00017-of-00036.safetensors", "model.layers.27.input_layernorm.weight": "model-00017-of-00036.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00017-of-00036.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00017-of-00036.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00017-of-00036.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00017-of-00036.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00036.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00017-of-00036.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00017-of-00036.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00017-of-00036.safetensors", "model.layers.26.input_layernorm.weight": "model-00017-of-00036.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00018-of-00036.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00018-of-00036.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00018-of-00036.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00036.safetensors", "model.layers.25.input_layernorm.weight": "model-00018-of-00036.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00018-of-00036.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00018-of-00036.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00018-of-00036.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00018-of-00036.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00018-of-00036.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00018-of-00036.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00018-of-00036.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00019-of-00036.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00019-of-00036.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00019-of-00036.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00019-of-00036.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00019-of-00036.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00019-of-00036.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00019-of-00036.safetensors", "model.layers.32.input_layernorm.weight": "model-00019-of-00036.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00019-of-00036.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00019-of-00036.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00019-of-00036.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00019-of-00036.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00019-of-00036.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00019-of-00036.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00019-of-00036.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00019-of-00036.safetensors", "model.layers.31.input_layernorm.weight": "model-00019-of-00036.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00020-of-00036.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00020-of-00036.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00020-of-00036.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00020-of-00036.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00020-of-00036.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00020-of-00036.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00020-of-00036.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00020-of-00036.safetensors", "model.layers.30.input_layernorm.weight": "model-00020-of-00036.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00020-of-00036.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00020-of-00036.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00020-of-00036.safetensors", "model.layers.29.input_layernorm.weight": "model-00020-of-00036.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00020-of-00036.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00020-of-00036.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00020-of-00036.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00020-of-00036.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00021-of-00036.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00021-of-00036.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00021-of-00036.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00021-of-00036.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00021-of-00036.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00021-of-00036.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00021-of-00036.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00021-of-00036.safetensors", "model.layers.37.input_layernorm.weight": "model-00021-of-00036.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00021-of-00036.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00021-of-00036.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00021-of-00036.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00021-of-00036.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00022-of-00036.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00022-of-00036.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00022-of-00036.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00022-of-00036.safetensors", "model.layers.36.input_layernorm.weight": "model-00022-of-00036.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00022-of-00036.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00022-of-00036.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00022-of-00036.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00022-of-00036.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00022-of-00036.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00022-of-00036.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00022-of-00036.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00022-of-00036.safetensors", "model.layers.35.input_layernorm.weight": "model-00022-of-00036.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00022-of-00036.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00022-of-00036.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00023-of-00036.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00023-of-00036.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00023-of-00036.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00023-of-00036.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00023-of-00036.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00023-of-00036.safetensors", "model.layers.34.input_layernorm.weight": "model-00023-of-00036.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00023-of-00036.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00023-of-00036.safetensors", "model.layers.33.input_layernorm.weight": "model-00023-of-00036.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00023-of-00036.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00023-of-00036.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00023-of-00036.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00023-of-00036.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00023-of-00036.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00023-of-00036.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00023-of-00036.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00024-of-00036.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00024-of-00036.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00024-of-00036.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00024-of-00036.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00024-of-00036.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00024-of-00036.safetensors", "model.layers.41.input_layernorm.weight": "model-00024-of-00036.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00024-of-00036.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00024-of-00036.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00024-of-00036.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00024-of-00036.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00024-of-00036.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00024-of-00036.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00024-of-00036.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00024-of-00036.safetensors", "model.layers.40.input_layernorm.weight": "model-00024-of-00036.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00024-of-00036.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00025-of-00036.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00025-of-00036.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00025-of-00036.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00025-of-00036.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00025-of-00036.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00025-of-00036.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00025-of-00036.safetensors", "model.layers.39.input_layernorm.weight": "model-00025-of-00036.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00025-of-00036.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00025-of-00036.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00025-of-00036.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00025-of-00036.safetensors", "model.layers.38.input_layernorm.weight": "model-00025-of-00036.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00025-of-00036.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00026-of-00036.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00026-of-00036.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00026-of-00036.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00026-of-00036.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00026-of-00036.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00026-of-00036.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00026-of-00036.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00026-of-00036.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00026-of-00036.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00026-of-00036.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00026-of-00036.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00026-of-00036.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00026-of-00036.safetensors", "model.layers.45.input_layernorm.weight": "model-00026-of-00036.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00026-of-00036.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00027-of-00036.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00027-of-00036.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00027-of-00036.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00027-of-00036.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00027-of-00036.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00027-of-00036.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00027-of-00036.safetensors", "model.layers.44.input_layernorm.weight": "model-00027-of-00036.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00027-of-00036.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00027-of-00036.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00027-of-00036.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00027-of-00036.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00027-of-00036.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00027-of-00036.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00027-of-00036.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00027-of-00036.safetensors", "model.layers.43.input_layernorm.weight": "model-00027-of-00036.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00028-of-00036.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00028-of-00036.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00028-of-00036.safetensors", "model.layers.42.input_layernorm.weight": "model-00028-of-00036.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00028-of-00036.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00028-of-00036.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00028-of-00036.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00028-of-00036.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00028-of-00036.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00028-of-00036.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00028-of-00036.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00028-of-00036.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00028-of-00036.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00028-of-00036.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00028-of-00036.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00028-of-00036.safetensors", "model.layers.50.input_layernorm.weight": "model-00028-of-00036.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00029-of-00036.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00029-of-00036.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00029-of-00036.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00029-of-00036.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00029-of-00036.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00029-of-00036.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00029-of-00036.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00029-of-00036.safetensors", "model.layers.49.input_layernorm.weight": "model-00029-of-00036.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00029-of-00036.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00029-of-00036.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00029-of-00036.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00029-of-00036.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00030-of-00036.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00030-of-00036.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00030-of-00036.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00030-of-00036.safetensors", "model.layers.48.input_layernorm.weight": "model-00030-of-00036.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00030-of-00036.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00030-of-00036.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00030-of-00036.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00030-of-00036.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00030-of-00036.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00030-of-00036.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00030-of-00036.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00030-of-00036.safetensors", "model.layers.47.input_layernorm.weight": "model-00030-of-00036.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00030-of-00036.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00030-of-00036.safetensors", "model.layers.46.input_layernorm.weight": "model-00030-of-00036.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00030-of-00036.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00031-of-00036.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00031-of-00036.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00031-of-00036.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00031-of-00036.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00031-of-00036.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00031-of-00036.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00031-of-00036.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00031-of-00036.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00031-of-00036.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00031-of-00036.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00031-of-00036.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00031-of-00036.safetensors", "model.layers.54.input_layernorm.weight": "model-00031-of-00036.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00031-of-00036.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00031-of-00036.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00032-of-00036.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00032-of-00036.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00032-of-00036.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00032-of-00036.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00032-of-00036.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00032-of-00036.safetensors", "model.layers.53.input_layernorm.weight": "model-00032-of-00036.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00032-of-00036.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00032-of-00036.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00032-of-00036.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00032-of-00036.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00032-of-00036.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00032-of-00036.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00032-of-00036.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00032-of-00036.safetensors", "model.layers.52.input_layernorm.weight": "model-00032-of-00036.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00032-of-00036.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00033-of-00036.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00033-of-00036.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00033-of-00036.safetensors", "model.layers.51.input_layernorm.weight": "model-00033-of-00036.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00033-of-00036.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00033-of-00036.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00033-of-00036.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00033-of-00036.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00033-of-00036.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00033-of-00036.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00033-of-00036.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00033-of-00036.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00034-of-00036.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00034-of-00036.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00034-of-00036.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00034-of-00036.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00034-of-00036.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00034-of-00036.safetensors", "model.layers.58.input_layernorm.weight": "model-00034-of-00036.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00034-of-00036.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00034-of-00036.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00034-of-00036.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00034-of-00036.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00034-of-00036.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00034-of-00036.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00034-of-00036.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00034-of-00036.safetensors", "model.layers.57.input_layernorm.weight": "model-00034-of-00036.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00034-of-00036.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00035-of-00036.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00035-of-00036.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00035-of-00036.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00035-of-00036.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00035-of-00036.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00035-of-00036.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00035-of-00036.safetensors", "model.layers.56.input_layernorm.weight": "model-00035-of-00036.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00035-of-00036.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00035-of-00036.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00035-of-00036.safetensors", "model.layers.55.input_layernorm.weight": "model-00035-of-00036.safetensors", "lm_head.weight": "model-00036-of-00036.safetensors", "model.norm.weight": "model-00036-of-00036.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00036-of-00036.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00036-of-00036.safetensors", "model.layers.59.input_layernorm.weight": "model-00036-of-00036.safetensors"}}
|
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": "<unk>",
|
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.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
3 |
+
size 1033105
|
tokenizer_config.json
ADDED
@@ -0,0 +1,43 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": false,
|
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 |
+
"bos_token": "<s>",
|
31 |
+
"chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
|
32 |
+
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
+
"legacy": true,
|
35 |
+
"model_max_length": 1024,
|
36 |
+
"pad_token": "<unk>",
|
37 |
+
"padding_side": "left",
|
38 |
+
"sp_model_kwargs": {},
|
39 |
+
"spaces_between_special_tokens": false,
|
40 |
+
"tokenizer_class": "LlamaTokenizer",
|
41 |
+
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
+
}
|