specialv/Vims-7b
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: specialv/Vims-7b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-04-30 16:55:48 +08:00
commit d96c57839d
18 changed files with 91671 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -0,0 +1,35 @@
*.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

65
README.md Normal file
View File

@@ -0,0 +1,65 @@
---
base_model:
- Open-Orca/Mistral-7B-OpenOrca
- mistralai/Mistral-7B-v0.1
library_name: transformers
tags:
- mergekit
- merge
- mixtral
license: apache-2.0
language:
- en
---
# merged_model
This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
## Merge Details
### Merge Method
This model was merged using the [SLERP](https://en.wikipedia.org/wiki/Slerp) merge method.
### Models Merged
The following models were included in the merge:
* [Open-Orca/Mistral-7B-OpenOrca](https://huggingface.co/Open-Orca/Mistral-7B-OpenOrca)
* [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1)
### Configuration
The following YAML configuration was used to produce this model:
```yaml
base_model: mistralai/Mistral-7B-v0.1
dtype: float16
merge_method: slerp
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
slices:
- sources:
- layer_range:
- 0
- 32
model: mistralai/Mistral-7B-v0.1
- layer_range:
- 0
- 32
model: Open-Orca/Mistral-7B-OpenOrca
```

30
config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "float16",
"eos_token_id": 2,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"pad_token_id": null,
"rms_norm_eps": 1e-05,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"sliding_window": 4096,
"tie_word_embeddings": false,
"transformers_version": "5.0.0",
"use_cache": true,
"vocab_size": 32000
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.34.0.dev0"
}

30
mergekit_config.yml Normal file
View File

@@ -0,0 +1,30 @@
base_model: mistralai/Mistral-7B-v0.1
dtype: float16
merge_method: slerp
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
slices:
- sources:
- layer_range:
- 0
- 32
model: mistralai/Mistral-7B-v0.1
- layer_range:
- 0
- 32
model: Open-Orca/Mistral-7B-OpenOrca

3
model-00001-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:18c59b89f255408b8822c55e9d2d3679c73b192fa053ad6d641fb53a5673c5ec
size 1950412248

3
model-00002-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6d3df602ac1b6408cfdc65cd4a97e17f5ce1eb34a4e74e880e0a50c519628173
size 1988178456

3
model-00003-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e5b9b2bb4750c468e56419ff81f67fe7bb43a730007822a27cc9f5c34e637ea8
size 1937846904

3
model-00004-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ee5d77fea2a8247f461f8523626247334ea31924591b92773d74bdb36908df81
size 1988178448

3
model-00005-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:66f8797084204c5befeca7ff6ea1c04998a5f408f3c847716cf240205888dd24
size 1937846904

3
model-00006-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44fd65d72dbeb168a519729a6b40888557f7736b5e0c09c1cc0b24f3157ef3b5
size 1988178448

3
model-00007-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9daa032f6a5adff60ba13ac86a53102cecdaa6cb1c82576a6a8268dd0f2fbdb5
size 1937846864

3
model-00008-of-00008.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ad910d3d2a6e070c18e74b0fa9ffba8e36175188c8cb5de69ad78753a0de40de
size 755009424

299
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,299 @@
{
"metadata": {
"total_size": 14483464192,
"mergekit_version": "0.1.4"
},
"weight_map": {
"lm_head.weight": "model-00001-of-00008.safetensors",
"model.embed_tokens.weight": "model-00001-of-00008.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.10.input_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.11.input_layernorm.weight": "model-00001-of-00008.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.16.input_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.17.input_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.18.input_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.19.input_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.2.input_layernorm.weight": "model-00003-of-00008.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.20.input_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.21.input_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.22.input_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.23.input_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.24.input_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.25.input_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.26.input_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.27.input_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.28.input_layernorm.weight": "model-00005-of-00008.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.29.input_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.3.input_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.30.input_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.31.input_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.4.input_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.5.input_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.6.input_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.7.input_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.8.input_layernorm.weight": "model-00007-of-00008.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.9.input_layernorm.weight": "model-00008-of-00008.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
"model.norm.weight": "model-00008-of-00008.safetensors"
}
}

23
special_tokens_map.json Normal file
View File

@@ -0,0 +1,23 @@
{
"bos_token": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

91113
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

43
tokenizer_config.json Normal file
View File

@@ -0,0 +1,43 @@
{
"add_bos_token": true,
"add_eos_token": false,
"add_prefix_space": null,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": false,
"model_max_length": 1000000000000000019884624838656,
"pad_token": null,
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"tokenizer_class": "LlamaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}