brucethemoose
commited on
Commit
•
b312616
1
Parent(s):
107f452
Upload folder using huggingface_hub
Browse files- README.md +62 -0
- config.json +29 -0
- mergekit_config.yml +25 -0
- model-00001-of-00007.safetensors +3 -0
- model-00002-of-00007.safetensors +3 -0
- model-00003-of-00007.safetensors +3 -0
- model-00004-of-00007.safetensors +3 -0
- model-00005-of-00007.safetensors +3 -0
- model-00006-of-00007.safetensors +3 -0
- model-00007-of-00007.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +30 -0
- tokenizer.json +0 -0
- tokenizer_config.json +59 -0
README.md
ADDED
@@ -0,0 +1,62 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
base_model: []
|
3 |
+
tags:
|
4 |
+
- mergekit
|
5 |
+
- merge
|
6 |
+
|
7 |
+
---
|
8 |
+
Just an experiment to try and extend the context of SUS, a 4K Yi model, and DPO Bagel, which breaks down after 4K context. Yi 4K was used as a base (even for bagel which is technically a Yi 200K model), and Yi 200K is merged in with a density of 1.
|
9 |
+
|
10 |
+
I wanted to include Hermes 34B, but something funky about its tokenizer breaks mergekit.
|
11 |
+
|
12 |
+
A component of another merge. Auto generated mergekit description below:
|
13 |
+
|
14 |
+
***
|
15 |
+
|
16 |
+
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
|
17 |
+
|
18 |
+
## Merge Details
|
19 |
+
### Merge Method
|
20 |
+
|
21 |
+
This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using /home/alpha/Models/Raw/chargoddard_Yi-34B-Llama as a base.
|
22 |
+
|
23 |
+
### Models Merged
|
24 |
+
|
25 |
+
The following models were included in the merge:
|
26 |
+
* /home/alpha/Models/Raw/SUSTech_SUS-Chat-34B
|
27 |
+
* /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
|
28 |
+
* /home/alpha/Models/Raw/jondurbin_bagel-34b-v0.2
|
29 |
+
* /home/alpha/Models/Raw/jondurbin_bagel-dpo-34b-v0.2
|
30 |
+
|
31 |
+
### Configuration
|
32 |
+
|
33 |
+
The following YAML configuration was used to produce this model:
|
34 |
+
|
35 |
+
```yaml
|
36 |
+
models:
|
37 |
+
- model: /home/alpha/Models/Raw/chargoddard_Yi-34B-Llama
|
38 |
+
# No parameters necessary for base model
|
39 |
+
- model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
|
40 |
+
parameters:
|
41 |
+
weight: 0.5
|
42 |
+
density: 1
|
43 |
+
- model: /home/alpha/Models/Raw/SUSTech_SUS-Chat-34B
|
44 |
+
parameters:
|
45 |
+
weight: 0.2
|
46 |
+
density: 0.12
|
47 |
+
- model: /home/alpha/Models/Raw/jondurbin_bagel-dpo-34b-v0.2
|
48 |
+
parameters:
|
49 |
+
weight: 0.2
|
50 |
+
density: 0.15
|
51 |
+
- model: /home/alpha/Models/Raw/jondurbin_bagel-34b-v0.2
|
52 |
+
parameters:
|
53 |
+
weight: 0.1
|
54 |
+
density: 0.12
|
55 |
+
merge_method: dare_ties
|
56 |
+
tokenizer_source: union
|
57 |
+
base_model: /home/alpha/Models/Raw/chargoddard_Yi-34B-Llama
|
58 |
+
parameters:
|
59 |
+
int8_mask: true
|
60 |
+
dtype: bfloat16
|
61 |
+
|
62 |
+
```
|
config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "/home/alpha/Models/Raw/chargoddard_Yi-34B-Llama",
|
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": 4096,
|
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": "4.36.2",
|
27 |
+
"use_cache": true,
|
28 |
+
"vocab_size": 64002
|
29 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
models:
|
2 |
+
- model: /home/alpha/Models/Raw/chargoddard_Yi-34B-Llama
|
3 |
+
# No parameters necessary for base model
|
4 |
+
- model: /home/alpha/Storage/Models/Raw/chargoddard_Yi-34B-200K-Llama
|
5 |
+
parameters:
|
6 |
+
weight: 0.5
|
7 |
+
density: 1
|
8 |
+
- model: /home/alpha/Models/Raw/SUSTech_SUS-Chat-34B
|
9 |
+
parameters:
|
10 |
+
weight: 0.2
|
11 |
+
density: 0.12
|
12 |
+
- model: /home/alpha/Models/Raw/jondurbin_bagel-dpo-34b-v0.2
|
13 |
+
parameters:
|
14 |
+
weight: 0.2
|
15 |
+
density: 0.15
|
16 |
+
- model: /home/alpha/Models/Raw/jondurbin_bagel-34b-v0.2
|
17 |
+
parameters:
|
18 |
+
weight: 0.1
|
19 |
+
density: 0.12
|
20 |
+
merge_method: dare_ties
|
21 |
+
tokenizer_source: union
|
22 |
+
base_model: /home/alpha/Models/Raw/chargoddard_Yi-34B-Llama
|
23 |
+
parameters:
|
24 |
+
int8_mask: true
|
25 |
+
dtype: bfloat16
|
model-00001-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ca861a9ba55df5c68391da3394d2350d5c7ded14b8ba1880ad85015bc1e8c5d4
|
3 |
+
size 9843263880
|
model-00002-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:605142e13531ba6ce82ec049b3357c10b19f508962d65c345344403fc03ad67f
|
3 |
+
size 9747800976
|
model-00003-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:324ebcae173408452cf1dba2b4d36e9981a540ebe575e6c9c9259f9bb0f31556
|
3 |
+
size 9806549816
|
model-00004-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6bc27bbbfa233742c9cff163cb5a6df98e66d2369c4862664170aeca46e7d208
|
3 |
+
size 9982711400
|
model-00005-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:45c321b87bc567b80f5b89b4962368c0f8973aabb474608b3a8ed7d0b585b090
|
3 |
+
size 9806549808
|
model-00006-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cac39b700744306458230ef8aeeb97c11e9caafcf499573f85399e906c3a91cc
|
3 |
+
size 9747829904
|
model-00007-of-00007.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7445e0a57a267245a626fa94ad8048bd8f752b559112b25c2d286acefecb08b8
|
3 |
+
size 9843249472
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.3.2"}, "weight_map": {"model.embed_tokens.weight": "model-00001-of-00007.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00007.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors", "model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.input_layernorm.weight": "model-00004-of-00007.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00004-of-00007.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.35.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.input_layernorm.weight": "model-00005-of-00007.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00005-of-00007.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.45.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.52.input_layernorm.weight": "model-00006-of-00007.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.56.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "lm_head.weight": "model-00007-of-00007.safetensors", "model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors", "model.norm.weight": "model-00007-of-00007.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token": {
|
3 |
+
"content": "<|startoftext|>",
|
4 |
+
"lstrip": false,
|
5 |
+
"normalized": false,
|
6 |
+
"rstrip": false,
|
7 |
+
"single_word": false
|
8 |
+
},
|
9 |
+
"eos_token": {
|
10 |
+
"content": "<|endoftext|>",
|
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_config.json
ADDED
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": false
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<|startoftext|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": false
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "<|endoftext|>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": false
|
28 |
+
},
|
29 |
+
"64000": {
|
30 |
+
"content": "<s>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": true,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": false
|
36 |
+
},
|
37 |
+
"64001": {
|
38 |
+
"content": "</s>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": true,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": false
|
44 |
+
}
|
45 |
+
},
|
46 |
+
"bos_token": "<|startoftext|>",
|
47 |
+
"clean_up_tokenization_spaces": false,
|
48 |
+
"eos_token": "<|endoftext|>",
|
49 |
+
"legacy": false,
|
50 |
+
"model_max_length": 4096,
|
51 |
+
"pad_token": "<unk>",
|
52 |
+
"padding_side": "right",
|
53 |
+
"sp_model_kwargs": {},
|
54 |
+
"spaces_between_special_tokens": false,
|
55 |
+
"tokenizer_class": "LlamaTokenizer",
|
56 |
+
"truncation_side": "right",
|
57 |
+
"unk_token": "<unk>",
|
58 |
+
"use_default_system_prompt": false
|
59 |
+
}
|