louisbrulenaudet
commited on
Upload folder using huggingface_hub
Browse files- README.md +63 -0
- config.json +29 -0
- mergekit_config.yml +17 -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 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- merge
|
4 |
+
- mergekit
|
5 |
+
- lazymergekit
|
6 |
+
- jondurbin/bagel-dpo-34b-v0.2
|
7 |
+
- abacusai/MetaMath-Bagel-DPO-34B
|
8 |
+
base_model:
|
9 |
+
- jondurbin/bagel-dpo-34b-v0.2
|
10 |
+
- abacusai/MetaMath-Bagel-DPO-34B
|
11 |
+
---
|
12 |
+
|
13 |
+
# Pearl-34B-ties
|
14 |
+
|
15 |
+
Pearl-34B-ties is a merge of the following models:
|
16 |
+
* [jondurbin/bagel-dpo-34b-v0.2](https://huggingface.co/jondurbin/bagel-dpo-34b-v0.2)
|
17 |
+
* [abacusai/MetaMath-Bagel-DPO-34B](https://huggingface.co/abacusai/MetaMath-Bagel-DPO-34B)
|
18 |
+
|
19 |
+
## Configuration
|
20 |
+
|
21 |
+
```yaml
|
22 |
+
models:
|
23 |
+
- model: abacusai/Smaug-34B-v0.1
|
24 |
+
- model: jondurbin/bagel-dpo-34b-v0.2
|
25 |
+
parameters:
|
26 |
+
density: 0.45
|
27 |
+
weight: 0.5
|
28 |
+
- model: abacusai/MetaMath-Bagel-DPO-34B
|
29 |
+
parameters:
|
30 |
+
density: 0.48
|
31 |
+
weight: 0.5
|
32 |
+
merge_method: ties
|
33 |
+
base_model: abacusai/Smaug-34B-v0.1
|
34 |
+
parameters:
|
35 |
+
normalize: true
|
36 |
+
int8_mask: true
|
37 |
+
dtype: bfloat16
|
38 |
+
```
|
39 |
+
|
40 |
+
## Usage
|
41 |
+
|
42 |
+
```python
|
43 |
+
!pip install -qU transformers accelerate
|
44 |
+
|
45 |
+
from transformers import AutoTokenizer
|
46 |
+
import transformers
|
47 |
+
import torch
|
48 |
+
|
49 |
+
model = "louisbrulenaudet/Pearl-34B-ties"
|
50 |
+
messages = [{"role": "user", "content": "What is a large language model?"}]
|
51 |
+
|
52 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
53 |
+
prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
54 |
+
pipeline = transformers.pipeline(
|
55 |
+
"text-generation",
|
56 |
+
model=model,
|
57 |
+
torch_dtype=torch.float16,
|
58 |
+
device_map="auto",
|
59 |
+
)
|
60 |
+
|
61 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
62 |
+
print(outputs[0]["generated_text"])
|
63 |
+
```
|
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 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
models:
|
3 |
+
- model: abacusai/Smaug-34B-v0.1
|
4 |
+
- model: jondurbin/bagel-dpo-34b-v0.2
|
5 |
+
parameters:
|
6 |
+
density: 0.45
|
7 |
+
weight: 0.5
|
8 |
+
- model: abacusai/MetaMath-Bagel-DPO-34B
|
9 |
+
parameters:
|
10 |
+
density: 0.48
|
11 |
+
weight: 0.5
|
12 |
+
merge_method: ties
|
13 |
+
base_model: abacusai/Smaug-34B-v0.1
|
14 |
+
parameters:
|
15 |
+
normalize: true
|
16 |
+
int8_mask: true
|
17 |
+
dtype: bfloat16
|
model-00001-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bb789204b3f606c8fb142919fefa1b84af911fd87970eb2b86c36f5b9d5f6312
|
3 |
+
size 1937798888
|
model-00002-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d9fd8f91700877e6dabae28b93dd90221e257e52baa4605ee23fcc49c891de5
|
3 |
+
size 1937827776
|
model-00003-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:338052f641e98b2e9b09eab0ec3b6c447cc200d152f5f17c6de3e86726251ca8
|
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:ac79d4db5ef0ba8b946313318304e860f399870bf2c47cf8eca8a462750e2eaa
|
3 |
+
size 1996533240
|
model-00005-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:129e3427a2979fe5bc77d6f45044c0c3d62e0b14f36f9bb9da4be3b5ad659cff
|
3 |
+
size 1937842224
|
model-00006-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90b77ef7854f51c3b8f8acb41a124ef22b2a4ada2a171486e8c07de86075cc57
|
3 |
+
size 1937798904
|
model-00007-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c29c8d6f4ad4a21ac7e79a6066d59b439dc01907844571d4dc6a04e79a30a35
|
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:b5a704f28e9cd26685afb301cfe9619010a1f37510f4d8f41eb6f1d2e0df1633
|
3 |
+
size 1937827792
|
model-00009-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3d60e7f25546fc4a15b2436c0149fe701fac90414f9b0890fde7922b9627830e
|
3 |
+
size 1937827792
|
model-00010-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1193afb2abb066bd4a7f74da882b5b3a100a04e15a1cfd42485d98bc8fcc6794
|
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:be913eb5363b96829ab118f6708ae0ec1bd95b58610d9ef868a7e6013323b017
|
3 |
+
size 1937798888
|
model-00012-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26f185de3492e4a9e35a693979c6108332b57b31335855b0ba285ca641d4d300
|
3 |
+
size 1996533256
|
model-00013-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:02543cd3b13bd32e7d6171e12d10ef29bd5f7e00e591940dfe6937ade1eb07d1
|
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:a340269f1bb247f55761a75a85739f43f7f6e5744960bfb65f93c2395526f520
|
3 |
+
size 1937813352
|
model-00015-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3c2ee5dc60aed90a55e995ab91ca35a7cab894c5ca50e76d8e994eb96ac11af4
|
3 |
+
size 1937856696
|
model-00016-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4450bd0c59ad1290a5375bdfaed4aba5aeba8e6bb2e26c2973d0ee372ed0ab3f
|
3 |
+
size 1937798904
|
model-00017-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1b91229fc7dfd6d512e07dbc01c003e11a827696251a99c89643e03442422ad3
|
3 |
+
size 1937827792
|
model-00018-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8041c3ce52eba7c2e2759b893f005a0b62afb4b9c4e9b39b2477db712ba3ce07
|
3 |
+
size 1996518792
|
model-00019-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d50a0c15cc3ce7a29b91e043af8c821fb5bd2f2e7cba0f7a3daabb03715895e
|
3 |
+
size 1937827792
|
model-00020-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7f98b919e6d6904674cf13c3ab035eb862c24a621725652447961b5f1952e5b8
|
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:e2512c6fe8127cef8035325e0da7b2303d83ab159110791220315c96b6b8d934
|
3 |
+
size 1996533256
|
model-00022-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:90ae2180e80eb40d561acd9643760ebbc53c2a8d41251caad85d0befab0658f1
|
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:aec52f70c59e732fe5716a3fc125da733a153078d7ceb93e72abf869cb8a29a7
|
3 |
+
size 1937827784
|
model-00024-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8662888f9b41733a114e3875077bf3b8d2d3c1a002447af7912339ed1d320bb5
|
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:f1ca3ac515cd2c98377d1b3198e02c2120e3dafb4d4339f8b83d41c83c6087a3
|
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:f3b94025e727734827780a4b599004331f12dc845c9696503e570495e6a31915
|
3 |
+
size 1937798896
|
model-00027-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5a71aeccf61ceb1db716b2a2a1d3fc4d2b5ef73e8b1a8cc231441ed6d59346cd
|
3 |
+
size 1937827792
|
model-00028-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:75f81dc7f7f457778c25bcbb981fb6ab995bd6015f4530576ba63e0c5ff2dc7e
|
3 |
+
size 1937827792
|
model-00029-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:072c761c669ad7c71306204b33644bdf05d8de916cb770ede24fa75bde4211e6
|
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:d03625173cebde8e6b129d603ac92bbcf7bded0a6ad80abc6caf180b0224f7c2
|
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:e74549a3f711d54b885b4f340bf5a55bb19565cf9148fc4f0fd8f78d2d34c3f6
|
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:d8d725cc632af03d98345cec30a539a5c8c883ed095c1f083241cf8e79b4c17b
|
3 |
+
size 1937827808
|
model-00033-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23765211bc0a46905b8bcbb756bb8c74df79b6211d5e7a629d7a8c85985e41a3
|
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:c48e517d0dcb86091e8bed9021655e12d10c4a9f26507602e84ac6fed9139297
|
3 |
+
size 1937827808
|
model-00035-of-00036.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:46fa50a9763089212ee0b637094d1c9cfcba7f5d9cb2d4adda457b943a953a7f
|
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:d0be2f56bf638de2ca6722eae9419f1438b3146d4f6b1af592d8af12951e9f78
|
3 |
+
size 1211148856
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.1"}, "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 |
+
}
|