powermove72
commited on
Commit
•
001f009
1
Parent(s):
bb068cd
Upload folder using huggingface_hub
Browse files- README.md +63 -0
- config.json +26 -0
- mergekit_config.yml +18 -0
- model-00001-of-00015.safetensors +3 -0
- model-00002-of-00015.safetensors +3 -0
- model-00003-of-00015.safetensors +3 -0
- model-00004-of-00015.safetensors +3 -0
- model-00005-of-00015.safetensors +3 -0
- model-00006-of-00015.safetensors +3 -0
- model-00007-of-00015.safetensors +3 -0
- model-00008-of-00015.safetensors +3 -0
- model-00009-of-00015.safetensors +3 -0
- model-00010-of-00015.safetensors +3 -0
- model-00011-of-00015.safetensors +3 -0
- model-00012-of-00015.safetensors +3 -0
- model-00013-of-00015.safetensors +3 -0
- model-00014-of-00015.safetensors +3 -0
- model-00015-of-00015.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +35 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +48 -0
README.md
ADDED
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
tags:
|
3 |
+
- merge
|
4 |
+
- mergekit
|
5 |
+
- lazymergekit
|
6 |
+
- argilla/notus-7b-v1
|
7 |
+
- MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1
|
8 |
+
base_model:
|
9 |
+
- argilla/notus-7b-v1
|
10 |
+
- MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1
|
11 |
+
---
|
12 |
+
|
13 |
+
# Notus-TheTop-7b-Slerp
|
14 |
+
|
15 |
+
Notus-TheTop-7b-Slerp is a merge of the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
16 |
+
* [argilla/notus-7b-v1](https://huggingface.co/argilla/notus-7b-v1)
|
17 |
+
* [MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1](https://huggingface.co/MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1)
|
18 |
+
|
19 |
+
## 🧩 Configuration
|
20 |
+
|
21 |
+
```yaml
|
22 |
+
slices:
|
23 |
+
- sources:
|
24 |
+
- model: argilla/notus-7b-v1
|
25 |
+
layer_range: [0, 32]
|
26 |
+
- model: MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1
|
27 |
+
layer_range: [0, 32]
|
28 |
+
merge_method: slerp
|
29 |
+
base_model: argilla/notus-7b-v1
|
30 |
+
parameters:
|
31 |
+
t:
|
32 |
+
- filter: self_attn
|
33 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
34 |
+
- filter: mlp
|
35 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
36 |
+
- value: 0.5
|
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 = "powermove72/Notus-TheTop-7b-Slerp"
|
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 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "argilla/notus-7b-v1",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.41.2",
|
24 |
+
"use_cache": false,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,18 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
slices:
|
3 |
+
- sources:
|
4 |
+
- model: argilla/notus-7b-v1
|
5 |
+
layer_range: [0, 32]
|
6 |
+
- model: MaziyarPanahi/TheTop-5x7B-Instruct-S3-v0.1
|
7 |
+
layer_range: [0, 32]
|
8 |
+
merge_method: slerp
|
9 |
+
base_model: argilla/notus-7b-v1
|
10 |
+
parameters:
|
11 |
+
t:
|
12 |
+
- filter: self_attn
|
13 |
+
value: [0, 0.5, 0.3, 0.7, 1]
|
14 |
+
- filter: mlp
|
15 |
+
value: [1, 0.5, 0.7, 0.3, 0]
|
16 |
+
- value: 0.5
|
17 |
+
dtype: bfloat16
|
18 |
+
|
model-00001-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5da276bc0f4e754146ccbde57b021757d5b0cf3d19d68e13897d3590036247b4
|
3 |
+
size 960521552
|
model-00002-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d14e8a2d1d4baf4ca1f768b078d039452ce0141756022ce17287bb05e9836e02
|
3 |
+
size 989890720
|
model-00003-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d3c5346259933adf2d6563361a6ded9b6743e6f1de8302ca4157b160be3045da
|
3 |
+
size 989890728
|
model-00004-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5d6645ae48abaad6a42e3edfea553b3c378b3c997ee5334b38845c9968b31e73
|
3 |
+
size 998287760
|
model-00005-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8ba2617c6383127fd91b8fc90e6a5978c7c9e17f51c959cef28936ce753aa94c
|
3 |
+
size 947956216
|
model-00006-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f16f4ec17d8ac98512671e98ce65bc5e3f8b32415a5d70a655f139dfa613a880
|
3 |
+
size 989890728
|
model-00007-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1c207506e29a0540442c1bf915dab5851f8577fe60b8800b68bd18fc04b30ac2
|
3 |
+
size 989890720
|
model-00008-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5eeb7fc1b3b054c06688a7243b014a4b541dddccb25d2537884ef769808aed25
|
3 |
+
size 998287760
|
model-00009-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8873a83ea0c97a4c70c4a00805cab38cf49a485e96cf4a2aae545c84ce16065f
|
3 |
+
size 947956216
|
model-00010-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:01ecf241c2251280dad88695d5914f5fba1f26cdbfb9bdfc2688b6baec5a5db4
|
3 |
+
size 989890728
|
model-00011-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d9060898e1ece956de6eec3e2eed78eec1a445b29df7e5a1e8ca637c5420a558
|
3 |
+
size 989890728
|
model-00012-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1cdf0e5b916aaad57a61f6891c1ec481598555cbc05bcab3e90e1fa539fbf419
|
3 |
+
size 998287752
|
model-00013-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e105b0f63cf57773c7d3859937656030e4e91a36642972f835c1a5359e1aec1e
|
3 |
+
size 947956200
|
model-00014-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fbf55444ec8a06cabf3eb4338aa63082fbf7512634c85f90992bb690a5504b73
|
3 |
+
size 989890712
|
model-00015-of-00015.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2f718689005ebfd28f0b6f1793a0c3c3e8a386c49ed93dd02e9ad002542f3b4f
|
3 |
+
size 755009440
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14483464192}, "weight_map": {"lm_head.weight": "model-00001-of-00015.safetensors", "model.embed_tokens.weight": "model-00001-of-00015.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00015.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00015.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.input_layernorm.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00015.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors", "model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00006-of-00015.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00006-of-00015.safetensors", "model.layers.2.input_layernorm.weight": "model-00006-of-00015.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00006-of-00015.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00015.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00015.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00015.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00015.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00008-of-00015.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00008-of-00015.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00009-of-00015.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00009-of-00015.safetensors", "model.layers.26.input_layernorm.weight": "model-00009-of-00015.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00015.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00010-of-00015.safetensors", "model.layers.28.input_layernorm.weight": "model-00010-of-00015.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00010-of-00015.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00011-of-00015.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.input_layernorm.weight": "model-00011-of-00015.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00011-of-00015.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00015.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00015.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00012-of-00015.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00012-of-00015.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00012-of-00015.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00012-of-00015.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00012-of-00015.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00013-of-00015.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00013-of-00015.safetensors", "model.layers.6.input_layernorm.weight": "model-00013-of-00015.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00014-of-00015.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.input_layernorm.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00014-of-00015.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.input_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00015-of-00015.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00015-of-00015.safetensors", "model.norm.weight": "model-00015-of-00015.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,48 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"chat_template": "{% for message in messages %}\n{% if message['role'] == 'user' %}\n{{ '<|user|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'system' %}\n{{ '<|system|>\n' + message['content'] + eos_token }}\n{% elif message['role'] == 'assistant' %}\n{{ '<|assistant|>\n' + message['content'] + eos_token }}\n{% endif %}\n{% if loop.last and add_generation_prompt %}\n{{ '<|assistant|>' }}\n{% endif %}\n{% endfor %}",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "</s>",
|
39 |
+
"legacy": true,
|
40 |
+
"model_max_length": 1000000000000000019884624838656,
|
41 |
+
"pad_token": "</s>",
|
42 |
+
"sp_model_kwargs": {},
|
43 |
+
"spaces_between_special_tokens": false,
|
44 |
+
"tokenizer_class": "LlamaTokenizer",
|
45 |
+
"truncation_side": "left",
|
46 |
+
"unk_token": "<unk>",
|
47 |
+
"use_default_system_prompt": true
|
48 |
+
}
|