eldogbbhed
commited on
Commit
•
180270c
1
Parent(s):
e99b1c2
Upload folder using huggingface_hub
Browse files- README.md +29 -0
- config.json +26 -0
- mergekit_config.yml +9 -0
- model-00001-of-00010.safetensors +3 -0
- model-00002-of-00010.safetensors +3 -0
- model-00003-of-00010.safetensors +3 -0
- model-00004-of-00010.safetensors +3 -0
- model-00005-of-00010.safetensors +3 -0
- model-00006-of-00010.safetensors +3 -0
- model-00007-of-00010.safetensors +3 -0
- model-00008-of-00010.safetensors +3 -0
- model-00009-of-00010.safetensors +3 -0
- model-00010-of-00010.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 +49 -0
README.md
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
license: apache-2.0
|
3 |
+
tags:
|
4 |
+
- merge
|
5 |
+
- mergekit
|
6 |
+
- vortexmergekit
|
7 |
+
- mlabonne/NeuralBeagle14-7B
|
8 |
+
- eldogbbhed/NeuralPearlBeagle
|
9 |
+
---
|
10 |
+
|
11 |
+
# Peagle-14b
|
12 |
+
|
13 |
+
Hey there! 👋 Welcome to the Peagle-14b! This is a merge of multiple models brought together using the awesome [VortexMerge kit](https://colab.research.google.com/drive/1YjcvCLuNG1PK7Le6_4xhVU5VpzTwvGhk#scrollTo=UG5H2TK4gVyl).
|
14 |
+
|
15 |
+
Let's see what we've got in this merge:
|
16 |
+
* [mlabonne/NeuralBeagle14-7B](https://huggingface.co/mlabonne/NeuralBeagle14-7B) 🚀
|
17 |
+
* [eldogbbhed/NeuralPearlBeagle](https://huggingface.co/eldogbbhed/NeuralPearlBeagle) 🚀
|
18 |
+
|
19 |
+
## 🧩 Configuration
|
20 |
+
|
21 |
+
```yaml
|
22 |
+
slices:
|
23 |
+
- sources:
|
24 |
+
- model: mlabonne/NeuralBeagle14-7B
|
25 |
+
layer_range: [0, 20]
|
26 |
+
- sources:
|
27 |
+
- model: eldogbbhed/NeuralPearlBeagle
|
28 |
+
layer_range: [12, 32]
|
29 |
+
merge_method: passthrough
|
config.json
ADDED
@@ -0,0 +1,26 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"_name_or_path": "eldogbbhed/NeuralPearlBeagle",
|
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": 40,
|
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": "float16",
|
23 |
+
"transformers_version": "4.39.0.dev0",
|
24 |
+
"use_cache": false,
|
25 |
+
"vocab_size": 32000
|
26 |
+
}
|
mergekit_config.yml
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
|
2 |
+
slices:
|
3 |
+
- sources:
|
4 |
+
- model: mlabonne/NeuralBeagle14-7B
|
5 |
+
layer_range: [0, 20]
|
6 |
+
- sources:
|
7 |
+
- model: eldogbbhed/NeuralPearlBeagle
|
8 |
+
layer_range: [12, 32]
|
9 |
+
merge_method: passthrough
|
model-00001-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a61bef2265344780af1f34c82a0ba3952982b7c073d34be66a78030d17f72ba9
|
3 |
+
size 1979773096
|
model-00002-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f28028dde165f6f8bb0cdb6ca854718e47f26c025934d0cb3040b7c12cf23968
|
3 |
+
size 1946235600
|
model-00003-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:913df6e0a5d52950526623bdd9e0e4b6e269abc1d27088f086205f8d8ac988e0
|
3 |
+
size 1973490176
|
model-00004-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:a16426259fc38f767af2ffebf1c569df8f0492be36201df35a9bb8249e6897e4
|
3 |
+
size 1946235648
|
model-00005-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:23bc844f71bc6e20e6b71ddaf0e39183f6836106b7e960c20f1ff8170a4b61eb
|
3 |
+
size 1979789736
|
model-00006-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0a7b1f91e19a3b83659fce6ce798904fb31a5bc9976425f2c7931f4b4e006521
|
3 |
+
size 1979798008
|
model-00007-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de690d6c4da4ed2c3a1a90a26d594565b52aa562f7e2ff40edc9df6a5b797b08
|
3 |
+
size 1889611928
|
model-00008-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0ae21382bacbc9939a13f4a8cf61736ea14e4f793a203f822240f5796b08c90
|
3 |
+
size 1979781432
|
model-00009-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:47254199d1036b332f62dada0c25c1fca76a9a01a2436bf5c50b64e010c70f62
|
3 |
+
size 1946243944
|
model-00010-of-00010.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f3efcac14ce9186d682ce070b3272d49dffdd48ea319cfb20dd15c8a70afbe26
|
3 |
+
size 352338512
|
model.safetensors.index.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"metadata": {"mergekit_version": "0.0.4.1"}, "weight_map": {"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.9.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.8.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00010.safetensors", "model.layers.7.input_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00001-of-00010.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00010.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.6.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.5.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.4.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.3.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00010.safetensors", "model.layers.2.input_layernorm.weight": "model-00002-of-00010.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00002-of-00010.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.0.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.embed_tokens.weight": "model-00003-of-00010.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.29.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00003-of-00010.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00010.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00003-of-00010.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00010.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00010.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00010.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00010.safetensors", "model.layers.28.input_layernorm.weight": "model-00003-of-00010.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.27.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.26.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.19.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00004-of-00010.safetensors", "model.layers.18.input_layernorm.weight": "model-00004-of-00010.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00004-of-00010.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.17.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.16.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.15.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00005-of-00010.safetensors", "model.layers.14.input_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00005-of-00010.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00005-of-00010.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.11.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.10.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.25.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00006-of-00010.safetensors", "model.layers.24.input_layernorm.weight": "model-00006-of-00010.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00006-of-00010.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.23.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.22.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.21.input_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00007-of-00010.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00007-of-00010.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00007-of-00010.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00007-of-00010.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00007-of-00010.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00007-of-00010.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00007-of-00010.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00007-of-00010.safetensors", "model.layers.20.input_layernorm.weight": "model-00007-of-00010.safetensors", "lm_head.weight": "model-00007-of-00010.safetensors", "model.norm.weight": "model-00007-of-00010.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.39.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.38.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.37.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00008-of-00010.safetensors", "model.layers.36.input_layernorm.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00008-of-00010.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.35.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.34.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.33.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.32.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00009-of-00010.safetensors", "model.layers.31.input_layernorm.weight": "model-00009-of-00010.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00010-of-00010.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00010-of-00010.safetensors", "model.layers.30.input_layernorm.weight": "model-00010-of-00010.safetensors"}}
|
special_tokens_map.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<unk>",
|
4 |
+
"<s>",
|
5 |
+
"</s>"
|
6 |
+
],
|
7 |
+
"bos_token": {
|
8 |
+
"content": "<s>",
|
9 |
+
"lstrip": false,
|
10 |
+
"normalized": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"single_word": false
|
13 |
+
},
|
14 |
+
"eos_token": {
|
15 |
+
"content": "</s>",
|
16 |
+
"lstrip": false,
|
17 |
+
"normalized": false,
|
18 |
+
"rstrip": false,
|
19 |
+
"single_word": false
|
20 |
+
},
|
21 |
+
"pad_token": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false
|
27 |
+
},
|
28 |
+
"unk_token": {
|
29 |
+
"content": "<unk>",
|
30 |
+
"lstrip": false,
|
31 |
+
"normalized": false,
|
32 |
+
"rstrip": false,
|
33 |
+
"single_word": false
|
34 |
+
}
|
35 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer.model
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
|
3 |
+
size 493443
|
tokenizer_config.json
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
}
|
29 |
+
},
|
30 |
+
"additional_special_tokens": [
|
31 |
+
"<unk>",
|
32 |
+
"<s>",
|
33 |
+
"</s>"
|
34 |
+
],
|
35 |
+
"bos_token": "<s>",
|
36 |
+
"chat_template": "{% for message in messages %}{{bos_token + message['role'] + '\n' + message['content'] + eos_token + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ bos_token + 'assistant\n' }}{% endif %}",
|
37 |
+
"clean_up_tokenization_spaces": false,
|
38 |
+
"eos_token": "</s>",
|
39 |
+
"legacy": true,
|
40 |
+
"model_max_length": 8192,
|
41 |
+
"pad_token": "</s>",
|
42 |
+
"padding_side": "left",
|
43 |
+
"sp_model_kwargs": {},
|
44 |
+
"spaces_between_special_tokens": false,
|
45 |
+
"split_special_tokens": false,
|
46 |
+
"tokenizer_class": "LlamaTokenizer",
|
47 |
+
"unk_token": "<unk>",
|
48 |
+
"use_default_system_prompt": true
|
49 |
+
}
|