初始化项目,由ModelHub XC社区提供模型
Model: arcee-ai/llama-3-zilo-sql Source: Original Platform
This commit is contained in:
52
.gitattributes
vendored
Normal file
52
.gitattributes
vendored
Normal file
@@ -0,0 +1,52 @@
|
|||||||
|
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.model filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||||
|
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00001-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00002-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00003-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00004-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00005-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00006-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00007-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00008-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00009-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00010-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00011-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00012-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00013-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00014-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00015-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00016-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
|
model-00017-of-00017.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||||
36
README.md
Normal file
36
README.md
Normal file
@@ -0,0 +1,36 @@
|
|||||||
|
---
|
||||||
|
license: apache-2.0
|
||||||
|
tags:
|
||||||
|
- merge
|
||||||
|
- mergekit
|
||||||
|
- meta-llama/Meta-Llama-3-8B-Instruct
|
||||||
|
- arcee-ai/llama3-sqlcoder-zilo
|
||||||
|
---
|
||||||
|
|
||||||
|
# llama-3-zilo-sql
|
||||||
|
|
||||||
|
llama-3-zilo-sql is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
||||||
|
* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
|
||||||
|
* [arcee-ai/llama3-sqlcoder-zilo](https://huggingface.co/arcee-ai/llama3-sqlcoder-zilo)
|
||||||
|
|
||||||
|
## 🧩 Configuration
|
||||||
|
|
||||||
|
```yaml
|
||||||
|
slices:
|
||||||
|
- sources:
|
||||||
|
- model: meta-llama/Meta-Llama-3-8B-Instruct
|
||||||
|
layer_range: [0, 32]
|
||||||
|
- model: arcee-ai/llama3-sqlcoder-zilo
|
||||||
|
layer_range: [0, 32]
|
||||||
|
merge_method: slerp
|
||||||
|
base_model: arcee-ai/llama3-sqlcoder-zilo
|
||||||
|
parameters:
|
||||||
|
t:
|
||||||
|
- filter: self_attn
|
||||||
|
value: [0, 0.5, 0.3, 0.7, 1]
|
||||||
|
- filter: mlp
|
||||||
|
value: [1, 0.5, 0.7, 0.3, 0]
|
||||||
|
- value: 0.5
|
||||||
|
dtype: bfloat16
|
||||||
|
|
||||||
|
```
|
||||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "arcee-ai/llama3-sqlcoder-zilo",
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"attention_bias": false,
|
||||||
|
"attention_dropout": 0.0,
|
||||||
|
"bos_token_id": 128000,
|
||||||
|
"eos_token_id": 128001,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 4096,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 14336,
|
||||||
|
"max_position_embeddings": 8192,
|
||||||
|
"mlp_bias": false,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 32,
|
||||||
|
"num_hidden_layers": 32,
|
||||||
|
"num_key_value_heads": 8,
|
||||||
|
"pretraining_tp": 1,
|
||||||
|
"rms_norm_eps": 1e-05,
|
||||||
|
"rope_scaling": null,
|
||||||
|
"rope_theta": 500000.0,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "bfloat16",
|
||||||
|
"transformers_version": "4.41.1",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 128256
|
||||||
|
}
|
||||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
|||||||
|
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||||
18
mergekit_config.yml
Normal file
18
mergekit_config.yml
Normal file
@@ -0,0 +1,18 @@
|
|||||||
|
|
||||||
|
slices:
|
||||||
|
- sources:
|
||||||
|
- model: meta-llama/Meta-Llama-3-8B-Instruct
|
||||||
|
layer_range: [0, 32]
|
||||||
|
- model: arcee-ai/llama3-sqlcoder-zilo
|
||||||
|
layer_range: [0, 32]
|
||||||
|
merge_method: slerp
|
||||||
|
base_model: arcee-ai/llama3-sqlcoder-zilo
|
||||||
|
parameters:
|
||||||
|
t:
|
||||||
|
- filter: self_attn
|
||||||
|
value: [0, 0.5, 0.3, 0.7, 1]
|
||||||
|
- filter: mlp
|
||||||
|
value: [1, 0.5, 0.7, 0.3, 0]
|
||||||
|
- value: 0.5
|
||||||
|
dtype: bfloat16
|
||||||
|
|
||||||
3
model-00001-of-00017.safetensors
Normal file
3
model-00001-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:b3d177c7213846da807e1318ea23bfac370dec9aa4b18c65ef1e39993df8a331
|
||||||
|
size 1050673280
|
||||||
3
model-00002-of-00017.safetensors
Normal file
3
model-00002-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:4270d13d8ac54ae1d23378d105012a9599c6bfe0d099a9f5f548149f8bb29b75
|
||||||
|
size 1050673296
|
||||||
3
model-00003-of-00017.safetensors
Normal file
3
model-00003-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:310ab6e6f95aa8b809256f67d588fb7fa118e7f842e9bee6346424b5fef46dd8
|
||||||
|
size 989899000
|
||||||
3
model-00004-of-00017.safetensors
Normal file
3
model-00004-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:35cf57f534397a078ebf92e2496bd8cd4292b40b2f2672ceb10524dfaf2bfe1a
|
||||||
|
size 989890728
|
||||||
3
model-00005-of-00017.safetensors
Normal file
3
model-00005-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:d4e83f3413fb95a805eb48c1ff87c7838ebdaaba6a2e5e45d29799d0311dedf2
|
||||||
|
size 998287760
|
||||||
3
model-00006-of-00017.safetensors
Normal file
3
model-00006-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:191515ef5bb3bc202fb721e0e88bea97c68bc0b9dc9bc7e92e5c9ae24ba3d7e8
|
||||||
|
size 947956216
|
||||||
3
model-00007-of-00017.safetensors
Normal file
3
model-00007-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:520bd377980748e3ebfb59cb59bf8cdf36e60bcea5cc4cc3b53097800df62934
|
||||||
|
size 989890728
|
||||||
3
model-00008-of-00017.safetensors
Normal file
3
model-00008-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a72a695b71d54a9a77aed42734e05f74136ec62202c969e58ef5873f5218c724
|
||||||
|
size 989890720
|
||||||
3
model-00009-of-00017.safetensors
Normal file
3
model-00009-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:eeebc077a6c78773debb58305ab9040811468639b0f766321b5719182ff52d15
|
||||||
|
size 998287760
|
||||||
3
model-00010-of-00017.safetensors
Normal file
3
model-00010-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:fcd249c43699f91bdaf96ead1c2704c21d7aa64e46002fb07d07ea51f27facb6
|
||||||
|
size 947956216
|
||||||
3
model-00011-of-00017.safetensors
Normal file
3
model-00011-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:a2e50f3344c1d833ad5e246e442a03c983ae5ceebf208cf710fafc8cc85f48bb
|
||||||
|
size 989890728
|
||||||
3
model-00012-of-00017.safetensors
Normal file
3
model-00012-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:2e04c1b5094631ed4fe0ed431b7cd0e1999ef53b374ca6320d93d0e3a4d4259b
|
||||||
|
size 989890728
|
||||||
3
model-00013-of-00017.safetensors
Normal file
3
model-00013-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:537272f0128a0d312bc319ab0f2dcc3d1c6113a599960dba2af961e5b1580f7f
|
||||||
|
size 998287752
|
||||||
3
model-00014-of-00017.safetensors
Normal file
3
model-00014-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:404d97d277dca307e589998cd87afada4beefb52a01e0dfb95704ce45d92f052
|
||||||
|
size 947956208
|
||||||
3
model-00015-of-00017.safetensors
Normal file
3
model-00015-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:25de6a1eded9d94b2f0505a98b735242c5a4f620fdc313d6ffed3db4d043e569
|
||||||
|
size 989890712
|
||||||
3
model-00016-of-00017.safetensors
Normal file
3
model-00016-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:6fe99d5508e5d489a459188ff309f593026cf5ead5d22492a6456477b303d897
|
||||||
|
size 989890712
|
||||||
3
model-00017-of-00017.safetensors
Normal file
3
model-00017-of-00017.safetensors
Normal file
@@ -0,0 +1,3 @@
|
|||||||
|
version https://git-lfs.github.com/spec/v1
|
||||||
|
oid sha256:747c43652ae7d51043ee8dc1c38c552349053935698b6f9af8cb2914dbb31767
|
||||||
|
size 201343792
|
||||||
1
model.safetensors.index.json
Normal file
1
model.safetensors.index.json
Normal file
File diff suppressed because one or more lines are too long
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<|begin_of_text|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "<|eot_id|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"pad_token": {
|
||||||
|
"content": "<|eot_id|>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": false,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
410563
tokenizer.json
Normal file
410563
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
2063
tokenizer_config.json
Normal file
2063
tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user