初始化项目，由ModelHub XC社区提供模型
Model: chlee10/T3Q-MSlerp-7Bx2 Source: Original Platform
This commit is contained in:
ModelHub XC
35
.gitattributes
vendored
Normal file
35
.gitattributes
vendored
Normal 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
|
||||
38
README.md
Normal file
38
README.md
Normal file
@@ -0,0 +1,38 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: apache-2.0
|
||||
---
|
||||
|
||||
## T3Q-MSlerp-7Bx2
|
||||
|
||||
T3Q-MSlerp-7Bx2 is a merge of the following models using [mergekit](https://github.com/cg123/mergekit):
|
||||
* [zhengr/MixTAO-7Bx2-MoE-v8.1](https://huggingface.co/zhengr/MixTAO-7Bx2-MoE-v8.1)
|
||||
* [yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B](https://huggingface.co/yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B)
|
||||
|
||||
|
||||
**Model Developers** Chihoon Lee(chlee10), T3Q
|
||||
|
||||
|
||||
```yaml
|
||||
|
||||
slices:
|
||||
- sources:
|
||||
- model: zhengr/MixTAO-7Bx2-MoE-v8.1
|
||||
layer_range: [0, 32]
|
||||
- model: yunconglong/Truthful_DPO_TomGrc_FusionNet_7Bx2_MoE_13B
|
||||
layer_range: [0, 32]
|
||||
|
||||
merge_method: slerp
|
||||
base_model: zhengr/MixTAO-7Bx2-MoE-v8.1
|
||||
|
||||
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 # fallback for rest of tensors
|
||||
|
||||
dtype: float16
|
||||
|
||||
```
|
||||
32
config.json
Normal file
32
config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"_name_or_path": "./merged",
|
||||
"architectures": [
|
||||
"MixtralForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 14336,
|
||||
"max_position_embeddings": 32768,
|
||||
"model_type": "mixtral",
|
||||
"num_attention_heads": 32,
|
||||
"num_experts_per_tok": 2,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 8,
|
||||
"num_local_experts": 2,
|
||||
"output_router_logits": false,
|
||||
"pad_token_id": 2,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 10000.0,
|
||||
"router_aux_loss_coef": 0.001,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float32",
|
||||
"transformers_version": "4.38.2",
|
||||
"unsloth_version": "2024.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 2,
|
||||
"transformers_version": "4.38.2",
|
||||
"use_cache": false
|
||||
}
|
||||
3
model-00001-of-00011.safetensors
Normal file
3
model-00001-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bf1725e49c91f7e82bf1031b897761eba66f61c8d657e1a170ecab6a1648d129
|
||||
size 4785869120
|
||||
3
model-00002-of-00011.safetensors
Normal file
3
model-00002-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:357e95fe372d92dd72e6c9d3910e941c2077d63b97455d3b81d12d198a9197ef
|
||||
size 4966257472
|
||||
3
model-00003-of-00011.safetensors
Normal file
3
model-00003-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5a119e36898b38f035b44f13c0acaaaa743b5c568ae700ee39b56e3c2e9147e2
|
||||
size 4966290464
|
||||
3
model-00004-of-00011.safetensors
Normal file
3
model-00004-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5f2214489d8a3f0a2bf193d9dbd129c29ce99582816427e6172484df683cee86
|
||||
size 4899181864
|
||||
3
model-00005-of-00011.safetensors
Normal file
3
model-00005-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:574f08aded6455846cc79fad55742a51b34e8e48ff73487635de873e99e7b989
|
||||
size 4966257512
|
||||
3
model-00006-of-00011.safetensors
Normal file
3
model-00006-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4c5612b16576e7f345b777288241aded0c20b38fd59b8b3f770171557ec1be33
|
||||
size 4966257512
|
||||
3
model-00007-of-00011.safetensors
Normal file
3
model-00007-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9bfc0cd8713d2cd1177a00f5c2c3920938e3f4d3ec5f6c3914cf673c7ef65eec
|
||||
size 4966257512
|
||||
3
model-00008-of-00011.safetensors
Normal file
3
model-00008-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dc85961d237594adc6fd78737f809190e7d145e2520611666cc82776718459a0
|
||||
size 4966257512
|
||||
3
model-00009-of-00011.safetensors
Normal file
3
model-00009-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6b0355e5f2711e7837d4808c59cf8ba5c168324e77fc5c2331c13313a6c7ccc1
|
||||
size 4966257512
|
||||
3
model-00010-of-00011.safetensors
Normal file
3
model-00010-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:602a5e235ad721936efd249e45a306d6ef7d4d64647a6309ff2adaddb9e6709a
|
||||
size 4966290512
|
||||
3
model-00011-of-00011.safetensors
Normal file
3
model-00011-of-00011.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:083db142fae83f73746b643fafb79060d8890c8b35c6e9a66bdd8f9508899add
|
||||
size 2101430040
|
||||
426
model.safetensors.index.json
Normal file
426
model.safetensors.index.json
Normal file
@@ -0,0 +1,426 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 51516555264
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00011-of-00011.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.0.input_layernorm.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.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.1.input_layernorm.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.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.10.block_sparse_moe.gate.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.11.block_sparse_moe.gate.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.11.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.11.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.12.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.12.block_sparse_moe.gate.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.13.block_sparse_moe.gate.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.13.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.13.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.14.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.14.block_sparse_moe.gate.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.14.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.14.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.15.block_sparse_moe.gate.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00005-of-00011.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.16.block_sparse_moe.gate.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.16.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.16.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.17.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.17.block_sparse_moe.gate.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.18.block_sparse_moe.gate.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00006-of-00011.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.19.block_sparse_moe.gate.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.input_layernorm.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-00001-of-00011.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00011.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.20.block_sparse_moe.gate.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.21.block_sparse_moe.gate.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00007-of-00011.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.22.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.22.block_sparse_moe.gate.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.1.w2.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.23.block_sparse_moe.experts.1.w3.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.23.block_sparse_moe.gate.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.0.w1.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.0.w2.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.0.w3.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.1.w1.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.24.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.24.block_sparse_moe.gate.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00008-of-00011.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.25.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.25.block_sparse_moe.gate.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.26.block_sparse_moe.experts.1.w3.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.26.block_sparse_moe.gate.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.0.w1.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.0.w2.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.0.w3.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.1.w1.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.1.w2.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.27.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.27.block_sparse_moe.gate.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00009-of-00011.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.28.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.28.block_sparse_moe.gate.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.29.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.29.block_sparse_moe.gate.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.3.block_sparse_moe.gate.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.3.input_layernorm.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.30.block_sparse_moe.experts.0.w1.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.0.w2.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.0.w3.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.1.w1.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.1.w2.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.30.block_sparse_moe.experts.1.w3.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.30.block_sparse_moe.gate.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00010-of-00011.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.0.w1.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.0.w2.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.0.w3.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.1.w1.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.1.w2.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.31.block_sparse_moe.experts.1.w3.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.31.block_sparse_moe.gate.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00011-of-00011.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.4.block_sparse_moe.gate.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.4.input_layernorm.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.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.5.block_sparse_moe.gate.weight": "model-00002-of-00011.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00003-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.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.6.block_sparse_moe.gate.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-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.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.7.block_sparse_moe.gate.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.7.input_layernorm.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.block_sparse_moe.experts.0.w1.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.8.block_sparse_moe.gate.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00011.safetensors",
|
||||
"model.layers.8.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.8.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.9.block_sparse_moe.experts.0.w1.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.9.block_sparse_moe.gate.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.9.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.9.self_attn.q_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00011.safetensors",
|
||||
"model.norm.weight": "model-00011-of-00011.safetensors"
|
||||
}
|
||||
}
|
||||
35
special_tokens_map.json
Normal file
35
special_tokens_map.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<unk>",
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"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
|
||||
},
|
||||
"pad_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
|
||||
}
|
||||
}
|
||||
91122
tokenizer.json
Normal file
91122
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
49
tokenizer_config.json
Normal file
49
tokenizer_config.json
Normal file
@@ -0,0 +1,49 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"add_prefix_space": true,
|
||||
"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": [
|
||||
"<unk>",
|
||||
"<s>",
|
||||
"</s>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 255,
|
||||
"pad_token": "<s>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": true
|
||||
}
|
||||
Reference in New Issue
Block a user