Upload folder using huggingface_hub
Browse files- README.md +76 -0
- config.json +33 -0
- mergekit_moe_config.yml +28 -0
- model-00001-of-00012.safetensors +3 -0
- model-00002-of-00012.safetensors +3 -0
- model-00003-of-00012.safetensors +3 -0
- model-00004-of-00012.safetensors +3 -0
- model-00005-of-00012.safetensors +3 -0
- model-00006-of-00012.safetensors +3 -0
- model-00007-of-00012.safetensors +3 -0
- model-00008-of-00012.safetensors +3 -0
- model-00009-of-00012.safetensors +3 -0
- model-00010-of-00012.safetensors +3 -0
- model-00011-of-00012.safetensors +3 -0
- model-00012-of-00012.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +24 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +47 -0
README.md
ADDED
@@ -0,0 +1,76 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- moe
|
5 |
+
- frankenmoe
|
6 |
+
- merge
|
7 |
+
- mergekit
|
8 |
+
- lazymergekit
|
9 |
+
- damerajee/Gaja-v1.00
|
10 |
+
- ai4bharat/Airavata
|
11 |
+
base_model:
|
12 |
+
- damerajee/Gaja-v1.00
|
13 |
+
- ai4bharat/Airavata
|
14 |
+
---
|
15 |
+
|
16 |
+
# Hixtral-test
|
17 |
+
|
18 |
+
Hixtral-test is a Mixure of Experts (MoE) made with the following models using [LazyMergekit](https://colab.research.google.com/drive/1obulZ1ROXHjYLn6PPZJwRR6GzgQogxxb?usp=sharing):
|
19 |
+
* [damerajee/Gaja-v1.00](https://huggingface.co/damerajee/Gaja-v1.00)
|
20 |
+
* [ai4bharat/Airavata](https://huggingface.co/ai4bharat/Airavata)
|
21 |
+
|
22 |
+
## 🧩 Configuration
|
23 |
+
|
24 |
+
```yaml
|
25 |
+
base_model: damerajee/Gaja-v1.00
|
26 |
+
gate_mode: random
|
27 |
+
dtype: float16
|
28 |
+
experts_per_token: 2
|
29 |
+
experts:
|
30 |
+
- source_model: damerajee/Gaja-v1.00
|
31 |
+
positive_prompts:
|
32 |
+
- "What are some fun activities to do in Bangalore?,Answer in hindi "
|
33 |
+
- "What is deep learning,Answer in english"
|
34 |
+
- "Talk to me about deep learning?"
|
35 |
+
- "what are the Best thing to do when travelling in India?"
|
36 |
+
negative_prompts:
|
37 |
+
- "Write a Python script to scrape data from a website."
|
38 |
+
- "Explain the key differences between Bayesian and frequentist statistics."
|
39 |
+
- "भारत में लोग अपने बड़ों के पैरों को छूते हैं जब हम उन्हें नमस्कार करते हैं, ऐसा क्यों होता है?"
|
40 |
+
- "मशीन लर्निंग कैसे आपके व्यवसाय या परियोजना को बेहतर बना सकता है?"
|
41 |
+
- source_model: ai4bharat/Airavata
|
42 |
+
positive_prompts:
|
43 |
+
- "भारत में लोग अपने बड़ों के पैरों को छूते हैं जब हम उन्हें नमस्कार करते हैं, ऐसा क्यों होता है?"
|
44 |
+
- "मशीन लर्निंग कैसे आपके व्यवसाय या परियोजना को बेहतर बना सकता है?"
|
45 |
+
- "एक आयत के लंबाई, चौड़ाई और ऊंचाई 8, 5 और 3 इकाई हैं। इस आयत का क्षेत्रफल क्या होगा?"
|
46 |
+
- "एक व्यक्ति एक साल में अपनी परिमिति का 3/5 हिस्सा चलता है। अगर वह प्रतिदिन 12 किलोमीटर चलता है, तो उसकी परिमिति क्या होगी?"
|
47 |
+
negative_prompts:
|
48 |
+
- "Write a heartfelt poem about the beauty of nature."
|
49 |
+
- "What year did World War II end?"
|
50 |
+
- "What are some fun activities to do in Seattle?,Answer in hindi "
|
51 |
+
- "What is deep learning,Answer in english"
|
52 |
+
```
|
53 |
+
|
54 |
+
## 💻 Usage
|
55 |
+
|
56 |
+
```python
|
57 |
+
!pip install -qU transformers bitsandbytes accelerate
|
58 |
+
|
59 |
+
from transformers import AutoTokenizer
|
60 |
+
import transformers
|
61 |
+
import torch
|
62 |
+
|
63 |
+
model = "damerajee/Hixtral-test"
|
64 |
+
|
65 |
+
tokenizer = AutoTokenizer.from_pretrained(model)
|
66 |
+
pipeline = transformers.pipeline(
|
67 |
+
"text-generation",
|
68 |
+
model=model,
|
69 |
+
model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
|
70 |
+
)
|
71 |
+
|
72 |
+
messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
|
73 |
+
prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
74 |
+
outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
|
75 |
+
print(outputs[0]["generated_text"])
|
76 |
+
```
|
config.json
ADDED
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "damerajee/Gaja-v1.00",
|
3 |
+
"architectures": [
|
4 |
+
"MixtralForCausalLM"
|
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": 4096,
|
12 |
+
"initializer_range": 0.02,
|
13 |
+
"intermediate_size": 11008,
|
14 |
+
"max_position_embeddings": 4096,
|
15 |
+
"model_type": "mixtral",
|
16 |
+
"num_attention_heads": 32,
|
17 |
+
"num_experts_per_tok": 2,
|
18 |
+
"num_hidden_layers": 32,
|
19 |
+
"num_key_value_heads": 32,
|
20 |
+
"num_local_experts": 2,
|
21 |
+
"output_router_logits": false,
|
22 |
+
"pretraining_tp": 1,
|
23 |
+
"rms_norm_eps": 1e-05,
|
24 |
+
"rope_scaling": null,
|
25 |
+
"rope_theta": 10000.0,
|
26 |
+
"router_aux_loss_coef": 0.001,
|
27 |
+
"sliding_window": null,
|
28 |
+
"tie_word_embeddings": false,
|
29 |
+
"torch_dtype": "float16",
|
30 |
+
"transformers_version": "4.39.2",
|
31 |
+
"use_cache": true,
|
32 |
+
"vocab_size": 48064
|
33 |
+
}
|
mergekit_moe_config.yml
ADDED
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
base_model: damerajee/Gaja-v1.00
|
3 |
+
gate_mode: random
|
4 |
+
dtype: float16
|
5 |
+
experts_per_token: 2
|
6 |
+
experts:
|
7 |
+
- source_model: damerajee/Gaja-v1.00
|
8 |
+
positive_prompts:
|
9 |
+
- "What are some fun activities to do in Bangalore?,Answer in hindi "
|
10 |
+
- "What is deep learning,Answer in english"
|
11 |
+
- "Talk to me about deep learning?"
|
12 |
+
- "what are the Best thing to do when travelling in India?"
|
13 |
+
negative_prompts:
|
14 |
+
- "Write a Python script to scrape data from a website."
|
15 |
+
- "Explain the key differences between Bayesian and frequentist statistics."
|
16 |
+
- "भारत में लोग अपने बड़ों के पैरों को छूते हैं जब हम उन्हें नमस्कार करते हैं, ऐसा क्यों होता है?"
|
17 |
+
- "मशीन लर्निंग कैसे आपके व्यवसाय या परियोजना को बेहतर बना सकता है?"
|
18 |
+
- source_model: ai4bharat/Airavata
|
19 |
+
positive_prompts:
|
20 |
+
- "भारत में लोग अपने बड़ों के पैरों को छूते हैं जब हम उन्हें नमस्कार करते हैं, ऐसा क्यों होता है?"
|
21 |
+
- "मशीन लर्निंग कैसे आपके व्यवसाय या परियोजना को बेहतर बना सकता है?"
|
22 |
+
- "एक आयत के लंबाई, चौड़ाई और ऊंचाई 8, 5 और 3 इकाई हैं। इस आयत का क्षेत्रफल क्या होगा?"
|
23 |
+
- "एक व्यक्ति एक साल में अपनी परिमिति का 3/5 हिस्सा चलता है। अगर वह प्रतिदिन 12 किलोमीटर चलता है, तो उसकी परिमिति क्या होगी?"
|
24 |
+
negative_prompts:
|
25 |
+
- "Write a heartfelt poem about the beauty of nature."
|
26 |
+
- "What year did World War II end?"
|
27 |
+
- "What are some fun activities to do in Seattle?,Answer in hindi "
|
28 |
+
- "What is deep learning,Answer in english"
|
model-00001-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:349f98fece3f37b2a44815cebe79ec382f9a520d6c5d919eb3d969f2bd1e1562
|
3 |
+
size 1960064424
|
model-00002-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ea09ea0d0a4e89da9bcfaf152eea7a0c420bbc75d4eea6d3114f4eefc7a4fc0c
|
3 |
+
size 1983908680
|
model-00003-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7e903475a4bbec8bf7d9f02ed791696dcccf54c68c761448a26dab08dc981c9f
|
3 |
+
size 1983908688
|
model-00004-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a437d8139b970f2e6b92d7e7f37a0b88cc25bca79734fc6f0bf03db1619bc15
|
3 |
+
size 1983908672
|
model-00005-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47c0c97479030ab7243280f83d08d0f113530ca8ed7c1ecdf31da148dd8ff182
|
3 |
+
size 1983908680
|
model-00006-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6c1768c30274a0ae25c218e45716548dece7e7b78349b40be59b442153ac134a
|
3 |
+
size 1983908688
|
model-00007-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f7ce45b6b90cb1f56c4ac965a85821f716896ace7f490b97a7d6e6713956978d
|
3 |
+
size 1983908664
|
model-00008-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ff8ffec9ddee1d62c8df2203e7fff2125785a03c380ec057138b38f8efce6b33
|
3 |
+
size 1983908680
|
model-00009-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:67f36f0c58318082651866c7bc04b3a266451578bd13c2bab49dd7c6483d4407
|
3 |
+
size 1983908688
|
model-00010-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89a352bf908abf052b9feac8304f056bdde668dfd9dec642dcd1c6dcd2f7bc58
|
3 |
+
size 1982080880
|
model-00011-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:51752c1c6a3ac5ea1621ee1ba7c9df26a71df70bdbd9d27551b0a5b93674de5e
|
3 |
+
size 1979718344
|
model-00012-of-00012.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7ade54b2e525525042cfec813b5630687f5bb36d1a2c81c7de6d1b1f5f40b5a0
|
3 |
+
size 604509840
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00012.safetensors", "model.norm.weight": "model-00001-of-00012.safetensors", "lm_head.weight": "model-00001-of-00012.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.10.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.11.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.12.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.13.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.14.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.15.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.16.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.17.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.18.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.19.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.20.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.21.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.22.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.23.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.24.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.25.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.26.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.27.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.28.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.29.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.30.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.31.input_layernorm.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00012.safetensors", "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00012.safetensors", "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00012.safetensors", "model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00012.safetensors", "model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00012.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00010-of-00012.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00010-of-00012.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00010-of-00012.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00011-of-00012.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00011-of-00012.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00011-of-00012.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00012-of-00012.safetensors", "model.layers.0.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.1.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.2.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.3.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.4.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.5.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.6.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.7.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.8.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.9.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.10.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.11.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.12.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.13.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.14.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.15.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.16.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.17.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.18.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.19.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.20.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.21.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.22.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.23.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.24.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.25.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.26.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.27.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.28.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.29.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.30.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors", "model.layers.31.block_sparse_moe.gate.weight": "model-00012-of-00012.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|im_end|>",
|
11 |
+
"lstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"rstrip": false,
|
14 |
+
"single_word": false
|
15 |
+
},
|
16 |
+
"pad_token": "<s>",
|
17 |
+
"unk_token": {
|
18 |
+
"content": "<unk>",
|
19 |
+
"lstrip": false,
|
20 |
+
"normalized": false,
|
21 |
+
"rstrip": false,
|
22 |
+
"single_word": false
|
23 |
+
}
|
24 |
+
}
|
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 sha256:9c384835e29a2bcdc9af37e169f13978dc6fbf2f94274f956ed2a42afa4b7e87
|
3 |
+
size 967614
|
tokenizer_config.json
ADDED
@@ -0,0 +1,47 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": "<|im_end|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "[PAD]",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
}
|
37 |
+
},
|
38 |
+
"bos_token": "<s>",
|
39 |
+
"chat_template": "{% for message in messages %}{% if message['role'] == 'user' %}{{'<|im_start|>user\n' + message['content'] + '<|im_end|>\n'}}{% elif message['role'] == 'assistant' %}{{'<|im_start|>assistant\n' + message['content'] + '<|im_end|>\n' }}{% else %}{{ '<|im_start|>system\n' + message['content'] + '<|im_end|>\n' }}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
40 |
+
"clean_up_tokenization_spaces": false,
|
41 |
+
"eos_token": "<|im_end|>",
|
42 |
+
"model_max_length": 1000000000000000019884624838656,
|
43 |
+
"pad_token": "<s>",
|
44 |
+
"tokenizer_class": "LlamaTokenizer",
|
45 |
+
"unk_token": "<unk>",
|
46 |
+
"use_default_system_prompt": false
|
47 |
+
}
|