DenisTheDev
commited on
Commit
•
4cead74
1
Parent(s):
c59cb88
Upload folder using huggingface_hub
Browse files- README.md +30 -0
- added_tokens.json +4 -0
- config.json +25 -0
- mergekit_config.yml +11 -0
- model-00001-of-00011.safetensors +3 -0
- model-00002-of-00011.safetensors +3 -0
- model-00003-of-00011.safetensors +3 -0
- model-00004-of-00011.safetensors +3 -0
- model-00005-of-00011.safetensors +3 -0
- model-00006-of-00011.safetensors +3 -0
- model-00007-of-00011.safetensors +3 -0
- model-00008-of-00011.safetensors +3 -0
- model-00009-of-00011.safetensors +3 -0
- model-00010-of-00011.safetensors +3 -0
- model-00011-of-00011.safetensors +3 -0
- model.safetensors.index.json +1 -0
- special_tokens_map.json +27 -0
- tokenizer.json +0 -0
- tokenizer.model +3 -0
- tokenizer_config.json +60 -0
README.md
ADDED
@@ -0,0 +1,30 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- merge
|
5 |
+
- mergekit
|
6 |
+
- lazymergekit
|
7 |
+
- openchat/openchat-3.5-1210
|
8 |
+
- openchat/openchat-3.5-0106
|
9 |
+
---
|
10 |
+
|
11 |
+
# Openchat-Passthrough-2
|
12 |
+
|
13 |
+
Openchat-Passthrough-2 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
14 |
+
* [openchat/openchat-3.5-1210](https://huggingface.co/openchat/openchat-3.5-1210)
|
15 |
+
* [openchat/openchat-3.5-0106](https://huggingface.co/openchat/openchat-3.5-0106)
|
16 |
+
|
17 |
+
## 🧩 Configuration
|
18 |
+
|
19 |
+
```yaml
|
20 |
+
slices:
|
21 |
+
- sources:
|
22 |
+
- model: openchat/openchat-3.5-1210
|
23 |
+
layer_range: [0, 24]
|
24 |
+
- sources:
|
25 |
+
- model: openchat/openchat-3.5-0106
|
26 |
+
layer_range: [8, 32]
|
27 |
+
merge_method: passthrough
|
28 |
+
dtype: bfloat16
|
29 |
+
|
30 |
+
```
|
added_tokens.json
ADDED
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<|end_of_turn|>": 32000,
|
3 |
+
"<|pad_0|>": 32001
|
4 |
+
}
|
config.json
ADDED
@@ -0,0 +1,25 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "openchat/openchat-3.5-1210",
|
3 |
+
"architectures": [
|
4 |
+
"MistralForCausalLM"
|
5 |
+
],
|
6 |
+
"bos_token_id": 1,
|
7 |
+
"eos_token_id": 32000,
|
8 |
+
"hidden_act": "silu",
|
9 |
+
"hidden_size": 4096,
|
10 |
+
"initializer_range": 0.02,
|
11 |
+
"intermediate_size": 14336,
|
12 |
+
"max_position_embeddings": 8192,
|
13 |
+
"model_type": "mistral",
|
14 |
+
"num_attention_heads": 32,
|
15 |
+
"num_hidden_layers": 48,
|
16 |
+
"num_key_value_heads": 8,
|
17 |
+
"rms_norm_eps": 1e-05,
|
18 |
+
"rope_theta": 10000.0,
|
19 |
+
"sliding_window": 4096,
|
20 |
+
"tie_word_embeddings": false,
|
21 |
+
"torch_dtype": "bfloat16",
|
22 |
+
"transformers_version": "4.35.2",
|
23 |
+
"use_cache": true,
|
24 |
+
"vocab_size": 32002
|
25 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,11 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
slices:
|
3 |
+
- sources:
|
4 |
+
- model: openchat/openchat-3.5-1210
|
5 |
+
layer_range: [0, 24]
|
6 |
+
- sources:
|
7 |
+
- model: openchat/openchat-3.5-0106
|
8 |
+
layer_range: [8, 32]
|
9 |
+
merge_method: passthrough
|
10 |
+
dtype: bfloat16
|
11 |
+
|
model-00001-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:c2b08f6e0b2fd215c45517bd7bd075d60a8d12119be7a47152f00f7ad1351880
|
3 |
+
size 1889595120
|
model-00002-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:942625b4569edb26e9c1eb0c2eba27a067c872a406f52b62296f4e5d761af2bc
|
3 |
+
size 1988178456
|
model-00003-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:68aa753524ef655210fbe4897976096213987100e63d1bd0fbc35e167fc61373
|
3 |
+
size 1971392688
|
model-00004-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a60969dc3f04d15c4d73f4abdedce56a562fe924b7b9aae9a142391a94eb14fd
|
3 |
+
size 1979814680
|
model-00005-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d20e3f832d0702a105fa30c8ec0747c210677bd6fa05b1716f9022865050563d
|
3 |
+
size 1979798528
|
model-00006-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ac6004342ea739f03ec384f938b852a1cdc90707af81399db473fa003a5f239e
|
3 |
+
size 1912689424
|
model-00007-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:eb47810cf6d15d04ed40deec115cce4477363264b40eda0fb50147432cf1bc98
|
3 |
+
size 1979781456
|
model-00008-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:ed47b9002d4f9b12ed42468df5c3d64ceabcae08345d83e8cf03a16c4dbed493
|
3 |
+
size 1979781456
|
model-00009-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:447ee22b0514a6083584d2279f43ba7d6e08c389163f2eaf4a92e3fe4fc42fb5
|
3 |
+
size 1889620056
|
model-00010-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3766f463bc8d3a103c76dfc7ca0a12729cbbbf82b65964e95bd59b0e66b6bbe5
|
3 |
+
size 1946235680
|
model-00011-of-00011.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:d7c2ec835f64714f6f1b455fe1172c13d24d7bdd8c9361e4685f510dbae781d3
|
3 |
+
size 1946243968
|
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-00011.safetensors", "model.layers.0.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00011.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.input_layernorm.weight": "model-00001-of-00011.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00001-of-00011.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00011.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00011.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.24.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00011.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.25.input_layernorm.weight": "model-00003-of-00011.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00011.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00003-of-00011.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00011.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.28.input_layernorm.weight": "model-00004-of-00011.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00011.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00004-of-00011.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.29.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.30.input_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00011.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00011.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00011.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.31.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.32.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00011.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00011.safetensors", "model.layers.17.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.33.input_layernorm.weight": "model-00006-of-00011.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00006-of-00011.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.34.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00007-of-00011.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.35.input_layernorm.weight": "model-00007-of-00011.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00007-of-00011.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00007-of-00011.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00011.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00011.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00011.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00008-of-00011.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00009-of-00011.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00009-of-00011.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00009-of-00011.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00009-of-00011.safetensors", "lm_head.weight": "model-00009-of-00011.safetensors", "model.layers.22.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00009-of-00011.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.23.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.39.input_layernorm.weight": "model-00009-of-00011.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00009-of-00011.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00010-of-00011.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.input_layernorm.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00010-of-00011.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.input_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00011-of-00011.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00011-of-00011.safetensors", "model.norm.weight": "model-00011-of-00011.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<|end_of_turn|>",
|
4 |
+
"<|pad_0|>"
|
5 |
+
],
|
6 |
+
"bos_token": {
|
7 |
+
"content": "<s>",
|
8 |
+
"lstrip": false,
|
9 |
+
"normalized": false,
|
10 |
+
"rstrip": false,
|
11 |
+
"single_word": false
|
12 |
+
},
|
13 |
+
"eos_token": {
|
14 |
+
"content": "<|end_of_turn|>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false
|
19 |
+
},
|
20 |
+
"unk_token": {
|
21 |
+
"content": "<unk>",
|
22 |
+
"lstrip": false,
|
23 |
+
"normalized": false,
|
24 |
+
"rstrip": false,
|
25 |
+
"single_word": false
|
26 |
+
}
|
27 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<unk>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<s>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"32000": {
|
28 |
+
"content": "<|end_of_turn|>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"32001": {
|
36 |
+
"content": "<|pad_0|>",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
}
|
43 |
+
},
|
44 |
+
"additional_special_tokens": [
|
45 |
+
"<|end_of_turn|>",
|
46 |
+
"<|pad_0|>"
|
47 |
+
],
|
48 |
+
"bos_token": "<s>",
|
49 |
+
"chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
|
50 |
+
"clean_up_tokenization_spaces": false,
|
51 |
+
"eos_token": "<|end_of_turn|>",
|
52 |
+
"legacy": true,
|
53 |
+
"model_max_length": 1000000000000000019884624838656,
|
54 |
+
"pad_token": null,
|
55 |
+
"sp_model_kwargs": {},
|
56 |
+
"spaces_between_special_tokens": false,
|
57 |
+
"tokenizer_class": "LlamaTokenizer",
|
58 |
+
"unk_token": "<unk>",
|
59 |
+
"use_default_system_prompt": true
|
60 |
+
}
|