初始化项目，由ModelHub XC社区提供模型
Model: cloudyu/mistral_18B_instruct_v0.1 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
|
||||
28
README.md
Normal file
28
README.md
Normal file
@@ -0,0 +1,28 @@
|
||||
---
|
||||
license: cc-by-4.0
|
||||
---
|
||||
```
|
||||
this is a 80 layers model based on mistral architecture
|
||||
sft by vicgalle/alpaca-gpt4.
|
||||
template is "{instruction} {inputs} \n {output}"
|
||||
```
|
||||
|
||||
example output
|
||||
|
||||
```
|
||||
<s> write a story about yosemite.
|
||||
Once upon a time, in the heart of California's Sierra Nevada Mountains, there was a place known as Yosemite National Park. This breathtaking landscape was home to some of nature's most stunning creations - towering redwood trees, crystal-clear streams, and cascading waterfalls that tumbled down from the mountainside.
|
||||
|
||||
In this magical land lived a young girl named Emily. She had grown up in the small village at the base of the mountain, surrounded by the beauty of nature. Every day, she would wander through the forests, exploring every nook and cranny of her beloved home.
|
||||
|
||||
One day, while wandering along the banks of the Merced River, Emily stumbled across something unusual. A small, shimmering object lay among the rocks. It was a piece of amber, with a trapped insect inside. The insect was an ancient one, unlike any she had ever seen before. It was a prehistoric butterfly, its wings spanned over 6 inches, and it was covered in intricate patterns.
|
||||
|
||||
Emily was fascinated by the creature and took it back to her village. She showed it to the elder of the village, who told her that the butterfly was a sign of good luck. He also shared with her the legend of the park, which spoke of a great spirit living within the mountains, protecting all those who lived within its borders.
|
||||
|
||||
From that day on, Emily dedicated herself to preserving the natural beauty of Yosemite. She spent her days helping to clean up trash, planting new trees, and teaching others about the importance of taking care of Mother Nature. And as she did so, she felt a sense of peace and happiness like never before.
|
||||
|
||||
Years passed, and Emily grew old. But even in her twilight years, she continued to wander the forests of Yosemite, sharing her love for nature with everyone she met. And as she looked out at the beautiful landscapes around her, she knew that she had done her part in keeping the spirit of Yosemite alive.
|
||||
|
||||
The end.</s>
|
||||
|
||||
```
|
||||
26
config.json
Normal file
26
config.json
Normal file
@@ -0,0 +1,26 @@
|
||||
{
|
||||
"_name_or_path": "./mistral_19B",
|
||||
"architectures": [
|
||||
"MistralForCausalLM"
|
||||
],
|
||||
"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": "mistral",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 80,
|
||||
"num_key_value_heads": 8,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.38.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32001
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.38.2"
|
||||
}
|
||||
3
model-00001-of-00008.safetensors
Normal file
3
model-00001-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9c492b8f57497a3414e7823a4f8816e5a34fe6768b97cafd3142495e3bba9350
|
||||
size 4943170528
|
||||
3
model-00002-of-00008.safetensors
Normal file
3
model-00002-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e41b0ae03342309a7fe502a70086bb992b87ef8756b717a8202ea04be913c964
|
||||
size 4999819336
|
||||
3
model-00003-of-00008.safetensors
Normal file
3
model-00003-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:60cb992cebd1827b15b6c3fb7f116dbe43bcbaf630dcb0c8915b25013c31a3a4
|
||||
size 4915916184
|
||||
3
model-00004-of-00008.safetensors
Normal file
3
model-00004-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f684c364172cd72291cb50dd78de356dcf9d2ee688e4c229a92334d4364d0034
|
||||
size 4915916176
|
||||
3
model-00005-of-00008.safetensors
Normal file
3
model-00005-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:73b9f8d9b8741a872f003307d3a872034797bfc94736ac6e013e4c051b32c1c8
|
||||
size 4999819336
|
||||
3
model-00006-of-00008.safetensors
Normal file
3
model-00006-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b83e3289cc01caa802261db2b9ed3d662f9aa612383f9b332f1424e35cc3d838
|
||||
size 4915916184
|
||||
3
model-00007-of-00008.safetensors
Normal file
3
model-00007-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a5b6648473d0e9e5818c781cd900297368263166ed67f375bb4aa31bb1cb15a5
|
||||
size 4915916176
|
||||
3
model-00008-of-00008.safetensors
Normal file
3
model-00008-of-00008.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9fd5c7f3b3e8a4e8cc3ecedbd8e10e9978843c65df599fb05f66ff8dbf0584cb
|
||||
size 815842872
|
||||
730
model.safetensors.index.json
Normal file
730
model.safetensors.index.json
Normal file
@@ -0,0 +1,730 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 35422232576
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00008-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-00002-of-00008.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00002-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-00002-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-00002-of-00008.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00002-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-00002-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00002-of-00008.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00003-of-00008.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00004-of-00008.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00005-of-00008.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.60.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.60.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.60.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.60.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.60.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.60.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.60.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.60.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.60.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.61.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.61.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.61.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.61.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.61.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.61.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.61.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.61.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.61.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.62.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.62.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.62.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.62.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.62.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.62.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.62.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.62.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.62.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.63.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.63.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.63.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.63.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.63.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.63.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.63.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.63.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.63.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.64.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.64.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.64.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.64.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.64.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.64.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.64.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.64.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.64.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.65.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.65.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.65.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.65.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.65.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.65.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.65.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.65.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.65.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.66.input_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.66.mlp.down_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.66.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.66.mlp.up_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.66.post_attention_layernorm.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.66.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.66.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.66.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.66.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.67.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.67.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.67.mlp.gate_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.67.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.67.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.67.self_attn.k_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.67.self_attn.o_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.67.self_attn.q_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.67.self_attn.v_proj.weight": "model-00006-of-00008.safetensors",
|
||||
"model.layers.68.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.68.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.68.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.68.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.68.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.68.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.68.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.68.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.68.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.69.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.69.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.69.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.69.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.69.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.69.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.69.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.69.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.69.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.70.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.70.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.70.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.70.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.70.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.70.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.70.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.70.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.70.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.71.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.71.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.71.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.71.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.71.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.71.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.71.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.71.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.71.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.72.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.72.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.72.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.72.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.72.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.72.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.72.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.72.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.72.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.73.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.73.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.73.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.73.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.73.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.73.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.73.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.73.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.73.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.74.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.74.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.74.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.74.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.74.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.74.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.74.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.74.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.74.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.75.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.75.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.75.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.75.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.75.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.75.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.75.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.75.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.75.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.76.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.76.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.76.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.76.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.76.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.76.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.76.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.76.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.76.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.77.input_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.77.mlp.down_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.77.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.77.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.77.post_attention_layernorm.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.77.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.77.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.77.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.77.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.78.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.78.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.78.mlp.gate_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.78.mlp.up_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.78.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.78.self_attn.k_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.78.self_attn.o_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.78.self_attn.q_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.78.self_attn.v_proj.weight": "model-00007-of-00008.safetensors",
|
||||
"model.layers.79.input_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.79.mlp.down_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.79.mlp.gate_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.79.mlp.up_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.79.post_attention_layernorm.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.79.self_attn.k_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.79.self_attn.o_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.79.self_attn.q_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.79.self_attn.v_proj.weight": "model-00008-of-00008.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00001-of-00008.safetensors",
|
||||
"model.norm.weight": "model-00008-of-00008.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"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": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
91136
tokenizer.json
Normal file
91136
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
55
tokenizer_config.json
Normal file
55
tokenizer_config.json
Normal file
@@ -0,0 +1,55 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"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
|
||||
},
|
||||
"32000": {
|
||||
"content": "[PAD]",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [],
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{{ bos_token }}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if message['role'] == 'user' %}{{ '[INST] ' + message['content'] + ' [/INST]' }}{% elif message['role'] == 'assistant' %}{{ message['content'] + eos_token}}{% else %}{{ raise_exception('Only user and assistant roles are supported!') }}{% endif %}{% endfor %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"max_length": 4096,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "[PAD]",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"stride": 0,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"truncation_side": "right",
|
||||
"truncation_strategy": "longest_first",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user