Upload folder using huggingface_hub
Browse files- README.md +35 -0
- config.json +27 -0
- mergekit_config.yml +16 -0
- model-00001-of-00016.safetensors +3 -0
- model-00002-of-00016.safetensors +3 -0
- model-00003-of-00016.safetensors +3 -0
- model-00004-of-00016.safetensors +3 -0
- model-00005-of-00016.safetensors +3 -0
- model-00006-of-00016.safetensors +3 -0
- model-00007-of-00016.safetensors +3 -0
- model-00008-of-00016.safetensors +3 -0
- model-00009-of-00016.safetensors +3 -0
- model-00010-of-00016.safetensors +3 -0
- model-00011-of-00016.safetensors +3 -0
- model-00012-of-00016.safetensors +3 -0
- model-00013-of-00016.safetensors +3 -0
- model-00014-of-00016.safetensors +3 -0
- model-00015-of-00016.safetensors +3 -0
- model-00016-of-00016.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +35 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +46 -0
README.md
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- merge
|
5 |
+
- mergekit
|
6 |
+
- lazymergekit
|
7 |
+
- Rakuten/RakutenAI-7B-chat
|
8 |
+
- Rakuten/RakutenAI-7B
|
9 |
+
---
|
10 |
+
|
11 |
+
# without_chat_RakutenAI-7B_task_arithmetic
|
12 |
+
|
13 |
+
without_chat_RakutenAI-7B_task_arithmetic is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
14 |
+
* [Rakuten/RakutenAI-7B-chat](https://huggingface.co/Rakuten/RakutenAI-7B-chat)
|
15 |
+
* [Rakuten/RakutenAI-7B](https://huggingface.co/Rakuten/RakutenAI-7B)
|
16 |
+
|
17 |
+
## 🧩 Configuration
|
18 |
+
|
19 |
+
```yaml
|
20 |
+
models:
|
21 |
+
- model: Rakuten/RakutenAI-7B-chat
|
22 |
+
parameters:
|
23 |
+
weight: 0.5
|
24 |
+
- model: Rakuten/RakutenAI-7B
|
25 |
+
parameters:
|
26 |
+
weight: 0.5
|
27 |
+
|
28 |
+
merge_method: task_arithmetic
|
29 |
+
base_model: Rakuten/RakutenAI-7B
|
30 |
+
parameters:
|
31 |
+
normalize: true
|
32 |
+
int8_mask: true
|
33 |
+
|
34 |
+
dtype: bfloat16
|
35 |
+
```
|
config.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "Rakuten/RakutenAI-7B",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"attention_dropout": 0.0,
|
7 |
+
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
+
"hidden_act": "silu",
|
10 |
+
"hidden_size": 4096,
|
11 |
+
"initializer_range": 0.02,
|
12 |
+
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
+
"model_type": "mistral",
|
15 |
+
"num_attention_heads": 32,
|
16 |
+
"num_hidden_layers": 32,
|
17 |
+
"num_key_value_heads": 8,
|
18 |
+
"rms_norm_eps": 1e-05,
|
19 |
+
"rope_theta": 10000.0,
|
20 |
+
"sliding_window": 4096,
|
21 |
+
"tie_word_embeddings": false,
|
22 |
+
"torch_dtype": "bfloat16",
|
23 |
+
"transformers_version": "4.40.2",
|
24 |
+
"use_cache": true,
|
25 |
+
"use_transformers_inputs": true,
|
26 |
+
"vocab_size": 48000
|
27 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
models:
|
3 |
+
- model: Rakuten/RakutenAI-7B-chat
|
4 |
+
parameters:
|
5 |
+
weight: 0.5
|
6 |
+
- model: Rakuten/RakutenAI-7B
|
7 |
+
parameters:
|
8 |
+
weight: 0.5
|
9 |
+
|
10 |
+
merge_method: task_arithmetic
|
11 |
+
base_model: Rakuten/RakutenAI-7B
|
12 |
+
parameters:
|
13 |
+
normalize: true
|
14 |
+
int8_mask: true
|
15 |
+
|
16 |
+
dtype: bfloat16
|
model-00001-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ab661957b04800eb93b3e9bfb8cb0bbc73f72fb4ffe9d4a25e92271990d37bf1
|
3 |
+
size 903881160
|
model-00002-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d4d285ab895df2e8c15135a424545dd931ff8bd33fe4486c47e72b671a353a3b
|
3 |
+
size 989890712
|
model-00003-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:058b548915353ae980a15a8a1895cd30eec43359389d6090d2ca3536a4b85f62
|
3 |
+
size 998287760
|
model-00004-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:db8926bd7bd4b0e659d164bc9fcc728e98449d2b035230ddcab35647db037683
|
3 |
+
size 947956216
|
model-00005-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:26f4246946842db5327013fdb65cc5cd1ca1869ed70dd03b000f1be1ae7747c9
|
3 |
+
size 989890728
|
model-00006-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f78c016fd18ddf8de6a4a56fd7f5feb73fb1a94f5f164ee610022560c41120be
|
3 |
+
size 989890728
|
model-00007-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:60d27b20b65a8a415e2f30f0fd704ddcf661795a9c9dbb2970922ca9a3f275fc
|
3 |
+
size 998287752
|
model-00008-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:4dd2129796b92c711f4d513f60ddff5f25a684bd5aff80f334dd71aadc35439f
|
3 |
+
size 947956216
|
model-00009-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5edf6d80348c9fe06d0e9d9b9f09e8be0fce0d28e6aba382d886a14d88cdcac5
|
3 |
+
size 989890728
|
model-00010-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d67a659d42bfce3a451dcc9de400b2e9385dbdb925a83d9bc4465bde4bce4cbf
|
3 |
+
size 989890728
|
model-00011-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f8e602003505c98f7fd46ae23e512d0ea353ef12882516ebc6d8139aaf813e39
|
3 |
+
size 998287760
|
model-00012-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:5fb7a3343a856885d82f86b326355f7418b0fef7c099509b49b6ae2f3cfd1420
|
3 |
+
size 947956208
|
model-00013-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3b38a09cb984f95b9a162635eb283927238aa6897f0f68bd6d1a2dae32f5ba73
|
3 |
+
size 989890720
|
model-00014-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3f4e1ba009424d13dc38c903ceb56d38b59019f1e4f3f448f5888fbedaab12c0
|
3 |
+
size 989890712
|
model-00015-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e1e87e90156efb22e20f004ca65ba7ef4e094c8954cc6bb6a5c9e5610065e9fa
|
3 |
+
size 998287736
|
model-00016-of-00016.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:533fe23927ecbffd7ab5417da6797e6b3d204419faf3728d26152403f4db066d
|
3 |
+
size 75506128
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.2", "total_size": 14745608192}, "weight_map": {"lm_head.weight": "model-00001-of-00016.safetensors", "model.embed_tokens.weight": "model-00001-of-00016.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00016.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00016.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.input_layernorm.weight": "model-00002-of-00016.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00016.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.11.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00003-of-00016.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00003-of-00016.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.input_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00003-of-00016.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.13.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00004-of-00016.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00004-of-00016.safetensors", "model.layers.15.input_layernorm.weight": "model-00004-of-00016.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00016.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00016.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00005-of-00016.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.18.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00006-of-00016.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00006-of-00016.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00006-of-00016.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00006-of-00016.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.input_layernorm.weight": "model-00006-of-00016.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00006-of-00016.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.2.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00007-of-00016.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00007-of-00016.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00007-of-00016.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00016.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00016.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00016.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00016.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00016.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.22.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00008-of-00016.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00008-of-00016.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00008-of-00016.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00008-of-00016.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00008-of-00016.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00008-of-00016.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00008-of-00016.safetensors", "model.layers.23.input_layernorm.weight": "model-00008-of-00016.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.24.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00009-of-00016.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00009-of-00016.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00009-of-00016.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00009-of-00016.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00009-of-00016.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00009-of-00016.safetensors", "model.layers.25.input_layernorm.weight": "model-00009-of-00016.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00009-of-00016.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.26.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00010-of-00016.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00010-of-00016.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00010-of-00016.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00010-of-00016.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00010-of-00016.safetensors", "model.layers.27.input_layernorm.weight": "model-00010-of-00016.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00010-of-00016.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00010-of-00016.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00011-of-00016.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00011-of-00016.safetensors", "model.layers.29.input_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00011-of-00016.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00011-of-00016.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00011-of-00016.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00011-of-00016.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00011-of-00016.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.3.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00012-of-00016.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00012-of-00016.safetensors", "model.layers.31.input_layernorm.weight": "model-00012-of-00016.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00013-of-00016.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00013-of-00016.safetensors", "model.layers.5.input_layernorm.weight": "model-00013-of-00016.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00013-of-00016.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.6.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00014-of-00016.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00014-of-00016.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00014-of-00016.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00014-of-00016.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00014-of-00016.safetensors", "model.layers.7.input_layernorm.weight": "model-00014-of-00016.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00014-of-00016.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00014-of-00016.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.8.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00015-of-00016.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00015-of-00016.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00015-of-00016.safetensors", "model.layers.9.input_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00015-of-00016.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00015-of-00016.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00015-of-00016.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00015-of-00016.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00015-of-00016.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00016-of-00016.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00016-of-00016.safetensors", "model.norm.weight": "model-00016-of-00016.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": true,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": true,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": true,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7978987401ef447724ded0544d048831954b7517a96555ce1593149e3678b6dc
|
3 |
+
size 755169
|
tokenizer_config.json
ADDED
@@ -0,0 +1,46 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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": true,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": true,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": true,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"clean_up_tokenization_spaces": false,
|
37 |
+
"eos_token": "</s>",
|
38 |
+
"legacy": true,
|
39 |
+
"model_max_length": 1000000000000000019884624838656,
|
40 |
+
"pad_token": "</s>",
|
41 |
+
"sp_model_kwargs": {},
|
42 |
+
"spaces_between_special_tokens": false,
|
43 |
+
"tokenizer_class": "LlamaTokenizer",
|
44 |
+
"unk_token": "<unk>",
|
45 |
+
"use_default_system_prompt": true
|
46 |
+
}
|