初始化项目,由ModelHub XC社区提供模型
Model: alpindale/pygmalion-instruct Source: Original Platform
This commit is contained in:
34
.gitattributes
vendored
Normal file
34
.gitattributes
vendored
Normal file
@@ -0,0 +1,34 @@
|
||||
*.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
|
||||
*.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
|
||||
50
README.md
Normal file
50
README.md
Normal file
@@ -0,0 +1,50 @@
|
||||
---
|
||||
license: mit
|
||||
---
|
||||
|
||||
## Model Details
|
||||
|
||||
Experimental model. Trained with the [Pygmalion](https://huggingface.co/PygmalionAI/pygmalion-6b/tree/dev) and the [WizardLM](https://huggingface.co/ehartford/WizardLM-7B-Uncensored) datasets.
|
||||
|
||||
The purpose of this model is to enable complex Instruct prompting but with the RP capabilties of Pygmalion.
|
||||
|
||||
### Prompting format
|
||||
```
|
||||
instruction:
|
||||
output:
|
||||
```
|
||||
|
||||
<!-- Provide the basic links for the model. -->
|
||||
|
||||
- **Repository:** [More Information Needed]
|
||||
- **Paper [optional]:** [More Information Needed]
|
||||
- **Demo [optional]:** [More Information Needed]
|
||||
|
||||
### Uses
|
||||
|
||||
The intended use-case is Role-Playing with Instruct prompts. Guiding the bot towards a certain conversation style should be easier this way. Subject to experimentation.
|
||||
|
||||
|
||||
|
||||
### Out-of-Scope Use
|
||||
|
||||
- Assistant Bot [subject to providing incorrect instructions]
|
||||
- Complex multi-character chat
|
||||
|
||||
### Risks
|
||||
|
||||
The model can generate potentially harmful or NSFW outputs. Please use with caution.
|
||||
|
||||
### Citation
|
||||
|
||||
WizardLM:
|
||||
```
|
||||
@misc{xu2023wizardlm,
|
||||
title={WizardLM: Empowering Large Language Models to Follow Complex Instructions},
|
||||
author={Can Xu and Qingfeng Sun and Kai Zheng and Xiubo Geng and Pu Zhao and Jiazhan Feng and Chongyang Tao and Daxin Jiang},
|
||||
year={2023},
|
||||
eprint={2304.12244},
|
||||
archivePrefix={arXiv},
|
||||
primaryClass={cs.CL}
|
||||
}
|
||||
```
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "/home/alpin/ramdisk/pygmalion-instruct",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"badwordsids": [
|
||||
[
|
||||
0
|
||||
]
|
||||
],
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 4096,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 11008,
|
||||
"max_position_embeddings": 2048,
|
||||
"max_sequence_length": 2048,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 32,
|
||||
"pad_token_id": 0,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.30.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.30.0.dev0"
|
||||
}
|
||||
3
model-00001-of-00039.safetensors
Normal file
3
model-00001-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fab1f3b2a2c5242771209d8453c17f95a7cb571302fa4c15ce19e38a3c484919
|
||||
size 396362680
|
||||
3
model-00002-of-00039.safetensors
Normal file
3
model-00002-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cbbbec3bffac74fa27eeabde6d1e8cc713319404f03792a4957661b8aac5f5b8
|
||||
size 371213218
|
||||
3
model-00003-of-00039.safetensors
Normal file
3
model-00003-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8a89fedffb3cd14e45b62f271c2e4c2fc9aea89afa97df1f12ed7566fbf90677
|
||||
size 371213580
|
||||
3
model-00004-of-00039.safetensors
Normal file
3
model-00004-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c7a2a6acb373266cfee04898d1a071b36f95648098cbae06b97ff23b7c1c3ce8
|
||||
size 371213580
|
||||
3
model-00005-of-00039.safetensors
Normal file
3
model-00005-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8c5512caec8cd60d09d2c73368764a8d6d7ef3589a68bfa0cae68b79a6186f52
|
||||
size 371213580
|
||||
3
model-00006-of-00039.safetensors
Normal file
3
model-00006-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cfa9feedd79021baee29a9186c400414aa19f82ebf1ac78a809838c98b9fb143
|
||||
size 314573874
|
||||
3
model-00007-of-00039.safetensors
Normal file
3
model-00007-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8f15946feba63a640a9591a0fcdf50d8b966be507c31fd4ec658290b6a6e4d47
|
||||
size 314590476
|
||||
3
model-00008-of-00039.safetensors
Normal file
3
model-00008-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:91027c0b7c8375c07ce372a8c6444a8acdd879e5e51438eb450dc01a05e15b57
|
||||
size 314590472
|
||||
3
model-00009-of-00039.safetensors
Normal file
3
model-00009-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d59a489da40d74552d1831de52d0730ff3e28c06b859e2532fcf8e2303452832
|
||||
size 371213218
|
||||
3
model-00010-of-00039.safetensors
Normal file
3
model-00010-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2184a684987e7c67149bf04799ece69b4f3d2b6dd2499995939ee758d6b90a65
|
||||
size 371213580
|
||||
3
model-00011-of-00039.safetensors
Normal file
3
model-00011-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:08a35f56ebd6e875efb7a5b36b872dcfa2d9ad47a9f8d3c1db4ae71c01e30a3e
|
||||
size 371213580
|
||||
3
model-00012-of-00039.safetensors
Normal file
3
model-00012-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c9f7f7f5ba6336dfe263f9e43c699987ba8371a960f9c1ddf759aa0ca7355227
|
||||
size 371213580
|
||||
3
model-00013-of-00039.safetensors
Normal file
3
model-00013-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1eb9d43f745b5983acde4fc08f0b2b1d32212d6609f61f6ca8217633583141ff
|
||||
size 314573880
|
||||
3
model-00014-of-00039.safetensors
Normal file
3
model-00014-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:54b4e198dc13a36eb94d577d7196cc34a248b1155f7049b3a6b04c2fec7107f8
|
||||
size 314590486
|
||||
3
model-00015-of-00039.safetensors
Normal file
3
model-00015-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3b4dfd123b7161a3cc467c5344e4b4c48b9d35b1e7f2854325d76b4bf6bd647b
|
||||
size 314590482
|
||||
3
model-00016-of-00039.safetensors
Normal file
3
model-00016-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0ecb499e93f7deb0402d644bc6d4d778c26b6841b6667a1c05ddb73950aa0475
|
||||
size 371213226
|
||||
3
model-00017-of-00039.safetensors
Normal file
3
model-00017-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:50798a957169b65a6ea5321dcfb5bf428e099614b77cf51cd8bc406688100c4d
|
||||
size 371213590
|
||||
3
model-00018-of-00039.safetensors
Normal file
3
model-00018-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3ace60a3975d8e48aa4a782069a266608539756869470b5193206aeb0b6550d0
|
||||
size 371213590
|
||||
3
model-00019-of-00039.safetensors
Normal file
3
model-00019-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c9b576f912d27393fb59337d0e7dff6463f1db4ab8780becf5b8b5d007c0a8f7
|
||||
size 371213590
|
||||
3
model-00020-of-00039.safetensors
Normal file
3
model-00020-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:39c288c3058f6e3205446316ede0675a3daefe2b87292278d2702d45f789ba9d
|
||||
size 314573880
|
||||
3
model-00021-of-00039.safetensors
Normal file
3
model-00021-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f3ebec001cc81b34c9c715941e0322d7b92ee51bdd9b90286c10e43dfa65b150
|
||||
size 314590486
|
||||
3
model-00022-of-00039.safetensors
Normal file
3
model-00022-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e6c7b03472ac8175812e49f95ff3730d26538a8eeab9ac85b4d275ccd037b16c
|
||||
size 314590482
|
||||
3
model-00023-of-00039.safetensors
Normal file
3
model-00023-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1cbad7618cc218776c871ac4ea3edceafafd6f00795c7252a660ed2b837a1f30
|
||||
size 371213226
|
||||
3
model-00024-of-00039.safetensors
Normal file
3
model-00024-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:31b4b96f71273103490828f85acc8847def7f52d194e45a817def019602fba94
|
||||
size 371213590
|
||||
3
model-00025-of-00039.safetensors
Normal file
3
model-00025-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f0b92604b795cf9dd069d8fd134f34a8121e90fdc4614fe9af9d9fd042a9b32c
|
||||
size 371213590
|
||||
3
model-00026-of-00039.safetensors
Normal file
3
model-00026-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5f5b72e57ce48f0931f6b85763b3345039aa47f28011b9c629286e5acd6a2185
|
||||
size 371213590
|
||||
3
model-00027-of-00039.safetensors
Normal file
3
model-00027-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:23bb6b0234f65f1fa4ee1cb557e8bcc880f10ea379a9b33abbc86d3d039628fe
|
||||
size 314573880
|
||||
3
model-00028-of-00039.safetensors
Normal file
3
model-00028-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:62c0b3ce08e770b12d696e534601df908f8c9049f53100286d6760badc22ff48
|
||||
size 314590486
|
||||
3
model-00029-of-00039.safetensors
Normal file
3
model-00029-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e8fdec09b354e1d6e69528fb5eff1a825d61ada8104cc9aec6b642dcf145bb84
|
||||
size 314590482
|
||||
3
model-00030-of-00039.safetensors
Normal file
3
model-00030-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:64ebb59ad29dbcdae3ae9a5bfd88da3e45e4bd3170a4876bb5014fde640a39b3
|
||||
size 371213226
|
||||
3
model-00031-of-00039.safetensors
Normal file
3
model-00031-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:15c166317581179c9d1373ed627c514dece2c8d8b763e454fd7f51351ab1d83c
|
||||
size 371213590
|
||||
3
model-00032-of-00039.safetensors
Normal file
3
model-00032-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ab98cb80bd5986bd426a67d2ac196cef397483ce35d629aaada942a3c7eb5d68
|
||||
size 371213590
|
||||
3
model-00033-of-00039.safetensors
Normal file
3
model-00033-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4840205ea77414e334638561e0d98d50d6a78f145a28f4ae980cc1931cdcb16e
|
||||
size 371213590
|
||||
3
model-00034-of-00039.safetensors
Normal file
3
model-00034-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:200224d4b5b9bdf37659fbdc4ed5b6067b4c309d3ed92865f0fca3517a8ee227
|
||||
size 314573880
|
||||
3
model-00035-of-00039.safetensors
Normal file
3
model-00035-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4526597ed9718065ccd8136f642e5d70129516eff1403d6729c0147d3dba144b
|
||||
size 314590486
|
||||
3
model-00036-of-00039.safetensors
Normal file
3
model-00036-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dd23bc7e90a9c55c2916a36377fc36a41daf1246a86795707346803e5ae734ca
|
||||
size 314590482
|
||||
3
model-00037-of-00039.safetensors
Normal file
3
model-00037-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f22f9ba6010995996fcb7ef02d0e41e3b49ca032c3136ba67e6d00c31a863329
|
||||
size 371213226
|
||||
3
model-00038-of-00039.safetensors
Normal file
3
model-00038-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0d3fad5252e30908a1592f4b21957b9f9d0fe5a1f2df1743b8a6ab0f01f54a77
|
||||
size 304112768
|
||||
3
model-00039-of-00039.safetensors
Normal file
3
model-00039-of-00039.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1bd0e78de8793c97830f171d22b15d81a01924301ff48d2d4a5d0016707d1074
|
||||
size 262144128
|
||||
330
model.safetensors.index.json
Normal file
330
model.safetensors.index.json
Normal file
@@ -0,0 +1,330 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13476839424
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00039-of-00039.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00039.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00002-of-00039.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00039.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00039.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00039.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00039.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00039.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00039.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00039.safetensors",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "model-00001-of-00039.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00039.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00003-of-00039.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00003-of-00039.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00003-of-00039.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00003-of-00039.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00003-of-00039.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00039.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00003-of-00039.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00039.safetensors",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "model-00003-of-00039.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00039.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00014-of-00039.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00013-of-00039.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00013-of-00039.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00014-of-00039.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00014-of-00039.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00013-of-00039.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00013-of-00039.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00013-of-00039.safetensors",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "model-00013-of-00039.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00013-of-00039.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00015-of-00039.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00015-of-00039.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00014-of-00039.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00015-of-00039.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00015-of-00039.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00014-of-00039.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00014-of-00039.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00014-of-00039.safetensors",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "model-00014-of-00039.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00014-of-00039.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00016-of-00039.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00016-of-00039.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00016-of-00039.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00016-of-00039.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00016-of-00039.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00015-of-00039.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00015-of-00039.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00015-of-00039.safetensors",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "model-00015-of-00039.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00015-of-00039.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00017-of-00039.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00017-of-00039.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00017-of-00039.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00017-of-00039.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00017-of-00039.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00016-of-00039.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00017-of-00039.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00016-of-00039.safetensors",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "model-00017-of-00039.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00016-of-00039.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00018-of-00039.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00018-of-00039.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00018-of-00039.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00018-of-00039.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00018-of-00039.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00017-of-00039.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00018-of-00039.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00017-of-00039.safetensors",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "model-00018-of-00039.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00018-of-00039.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00019-of-00039.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00019-of-00039.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00019-of-00039.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00019-of-00039.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00019-of-00039.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00019-of-00039.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00019-of-00039.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00018-of-00039.safetensors",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "model-00019-of-00039.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00019-of-00039.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00021-of-00039.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00020-of-00039.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00020-of-00039.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00021-of-00039.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00021-of-00039.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00020-of-00039.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00020-of-00039.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00020-of-00039.safetensors",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "model-00020-of-00039.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00020-of-00039.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00022-of-00039.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00022-of-00039.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00021-of-00039.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00022-of-00039.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00022-of-00039.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00021-of-00039.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00021-of-00039.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00021-of-00039.safetensors",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "model-00021-of-00039.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00021-of-00039.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00023-of-00039.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00023-of-00039.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00023-of-00039.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00023-of-00039.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00023-of-00039.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00022-of-00039.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00022-of-00039.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00022-of-00039.safetensors",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "model-00022-of-00039.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00022-of-00039.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00024-of-00039.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00024-of-00039.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00024-of-00039.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00024-of-00039.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00024-of-00039.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00023-of-00039.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00024-of-00039.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00023-of-00039.safetensors",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "model-00024-of-00039.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00023-of-00039.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00004-of-00039.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00004-of-00039.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00004-of-00039.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00004-of-00039.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00004-of-00039.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00003-of-00039.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00004-of-00039.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00003-of-00039.safetensors",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "model-00004-of-00039.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00004-of-00039.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00025-of-00039.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00025-of-00039.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00025-of-00039.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00025-of-00039.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00025-of-00039.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00024-of-00039.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00025-of-00039.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00024-of-00039.safetensors",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "model-00025-of-00039.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00025-of-00039.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00026-of-00039.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00026-of-00039.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00026-of-00039.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00026-of-00039.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00026-of-00039.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00026-of-00039.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00026-of-00039.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00025-of-00039.safetensors",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "model-00026-of-00039.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00026-of-00039.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00028-of-00039.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00027-of-00039.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00027-of-00039.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00028-of-00039.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00028-of-00039.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00027-of-00039.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00027-of-00039.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00027-of-00039.safetensors",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "model-00027-of-00039.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00027-of-00039.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00029-of-00039.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00029-of-00039.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00028-of-00039.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00029-of-00039.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00029-of-00039.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00028-of-00039.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00028-of-00039.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00028-of-00039.safetensors",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "model-00028-of-00039.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00028-of-00039.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00030-of-00039.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00030-of-00039.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00030-of-00039.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00030-of-00039.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00030-of-00039.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00029-of-00039.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00029-of-00039.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00029-of-00039.safetensors",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "model-00029-of-00039.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00029-of-00039.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00031-of-00039.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00031-of-00039.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00031-of-00039.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00031-of-00039.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00031-of-00039.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00030-of-00039.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00031-of-00039.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00030-of-00039.safetensors",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "model-00031-of-00039.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00030-of-00039.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00032-of-00039.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00032-of-00039.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00032-of-00039.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00032-of-00039.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00032-of-00039.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00031-of-00039.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00032-of-00039.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00031-of-00039.safetensors",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "model-00032-of-00039.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00032-of-00039.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00033-of-00039.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00033-of-00039.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00033-of-00039.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00033-of-00039.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00033-of-00039.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00033-of-00039.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00033-of-00039.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00032-of-00039.safetensors",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "model-00033-of-00039.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00033-of-00039.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00035-of-00039.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00034-of-00039.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00034-of-00039.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00035-of-00039.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00035-of-00039.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00034-of-00039.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00034-of-00039.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00034-of-00039.safetensors",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "model-00034-of-00039.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00034-of-00039.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00036-of-00039.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00036-of-00039.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00035-of-00039.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00036-of-00039.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00036-of-00039.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00035-of-00039.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00035-of-00039.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00035-of-00039.safetensors",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "model-00035-of-00039.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00035-of-00039.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00005-of-00039.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00005-of-00039.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00005-of-00039.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00005-of-00039.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00005-of-00039.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00005-of-00039.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00005-of-00039.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00004-of-00039.safetensors",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "model-00005-of-00039.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00005-of-00039.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00037-of-00039.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00037-of-00039.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00037-of-00039.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00037-of-00039.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00037-of-00039.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00036-of-00039.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00036-of-00039.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00036-of-00039.safetensors",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "model-00036-of-00039.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00036-of-00039.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00038-of-00039.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00038-of-00039.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00038-of-00039.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00038-of-00039.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00038-of-00039.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00037-of-00039.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00038-of-00039.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00037-of-00039.safetensors",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "model-00038-of-00039.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00037-of-00039.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00007-of-00039.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00006-of-00039.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00006-of-00039.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00007-of-00039.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00007-of-00039.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00006-of-00039.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00006-of-00039.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00006-of-00039.safetensors",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "model-00006-of-00039.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00006-of-00039.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00008-of-00039.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00008-of-00039.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00007-of-00039.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00008-of-00039.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00008-of-00039.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00007-of-00039.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00007-of-00039.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00007-of-00039.safetensors",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "model-00007-of-00039.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00007-of-00039.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00009-of-00039.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00009-of-00039.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00009-of-00039.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00009-of-00039.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00009-of-00039.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00008-of-00039.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00008-of-00039.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00008-of-00039.safetensors",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "model-00008-of-00039.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00008-of-00039.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00010-of-00039.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00010-of-00039.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00010-of-00039.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00010-of-00039.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00010-of-00039.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00009-of-00039.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00010-of-00039.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00009-of-00039.safetensors",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "model-00010-of-00039.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00009-of-00039.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00011-of-00039.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00011-of-00039.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00011-of-00039.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00011-of-00039.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00011-of-00039.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00010-of-00039.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00011-of-00039.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00010-of-00039.safetensors",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "model-00011-of-00039.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00011-of-00039.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00012-of-00039.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00012-of-00039.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00012-of-00039.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00012-of-00039.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00012-of-00039.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00012-of-00039.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00012-of-00039.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00011-of-00039.safetensors",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "model-00012-of-00039.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00012-of-00039.safetensors",
|
||||
"model.norm.weight": "model-00038-of-00039.safetensors"
|
||||
}
|
||||
}
|
||||
3
pytorch_model-00001-of-00039.bin
Normal file
3
pytorch_model-00001-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:72fd1e08167f7bbc6125928bfb70662d2d4d1e54e9db51e383028b5f1345c9e3
|
||||
size 396364479
|
||||
3
pytorch_model-00002-of-00039.bin
Normal file
3
pytorch_model-00002-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7d16c21ab3768a64ec8c29582d05f780b5f330ba9955645e375d50766e2d7b4c
|
||||
size 371215393
|
||||
3
pytorch_model-00003-of-00039.bin
Normal file
3
pytorch_model-00003-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e1ec5cd25e5d55ca5fb9d6a1c3657fc4d4ed86b3321074cb6956cd1ccd453e4e
|
||||
size 371215986
|
||||
3
pytorch_model-00004-of-00039.bin
Normal file
3
pytorch_model-00004-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:92a09cb4f6ab666bc45b9aafcb9e07177c60ed738940737dd94260ee6ff3bdbc
|
||||
size 371215986
|
||||
3
pytorch_model-00005-of-00039.bin
Normal file
3
pytorch_model-00005-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c15eca097f646d55a4076ed4b87e6ac85e5f9f15964aaf3952ec26bbc780695a
|
||||
size 371215986
|
||||
3
pytorch_model-00006-of-00039.bin
Normal file
3
pytorch_model-00006-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:077d91a9e7bf4aa5ff3696f8da36cb9965c9ff78a46987cb0b0563263eeb0898
|
||||
size 314575888
|
||||
3
pytorch_model-00007-of-00039.bin
Normal file
3
pytorch_model-00007-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a580f0c5b4e83160cb413ed8fd1149e21a9a240350480ece13b11cd863f9ab54
|
||||
size 314592882
|
||||
3
pytorch_model-00008-of-00039.bin
Normal file
3
pytorch_model-00008-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:614efe32f43cd9017a203123e2669e8b37916c855dc3276365801d19796cdb16
|
||||
size 314592882
|
||||
3
pytorch_model-00009-of-00039.bin
Normal file
3
pytorch_model-00009-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3b45324908a286cd6b1a791e3158c5e43e95656f7b2283f7a5547404118ef9d8
|
||||
size 371215393
|
||||
3
pytorch_model-00010-of-00039.bin
Normal file
3
pytorch_model-00010-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cd188d2273e3ad7b9be8ce05d4ac8f542af4522a8f7c46a0f359c4638df247c6
|
||||
size 371215986
|
||||
3
pytorch_model-00011-of-00039.bin
Normal file
3
pytorch_model-00011-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:57a3bf7234f6d98036eb2e8888aad2a56d4a44a1701b305796bd235e73a14a12
|
||||
size 371215986
|
||||
3
pytorch_model-00012-of-00039.bin
Normal file
3
pytorch_model-00012-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f940bafe801c472ef13a21604ca57b445896f0aaeea4c75c2959bba966f2fcb3
|
||||
size 371215986
|
||||
3
pytorch_model-00013-of-00039.bin
Normal file
3
pytorch_model-00013-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:94a3ca01cee937ead8dd09e9f64d0638c1567920457ab172f307e18b727331d4
|
||||
size 314575888
|
||||
3
pytorch_model-00014-of-00039.bin
Normal file
3
pytorch_model-00014-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:654f6f17ff70de33e723bca43f6877db5a96c4265626f96a152f42b83e6832ab
|
||||
size 314592882
|
||||
3
pytorch_model-00015-of-00039.bin
Normal file
3
pytorch_model-00015-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:09da62eff9def8ced0e8ef043bf3a8881f10afe9ae907cf0d21c7c9d95c476e8
|
||||
size 314592882
|
||||
3
pytorch_model-00016-of-00039.bin
Normal file
3
pytorch_model-00016-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2b456b4620b70e8e6af708eab202346a649441b2643107f2d181a5e402052c3b
|
||||
size 371215393
|
||||
3
pytorch_model-00017-of-00039.bin
Normal file
3
pytorch_model-00017-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0b1855c13a3db719650e0e57618467b75d5acec066da55831474835e093d6665
|
||||
size 371215986
|
||||
3
pytorch_model-00018-of-00039.bin
Normal file
3
pytorch_model-00018-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a906d4bc00690eb03a57fb2d94102854102f086cf87cb980bb18eae19a0290b0
|
||||
size 371215986
|
||||
3
pytorch_model-00019-of-00039.bin
Normal file
3
pytorch_model-00019-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7e2aa038c26e97780f48aca7810b5f8af5fa445c851e1745c445c6067290f7e9
|
||||
size 371215986
|
||||
3
pytorch_model-00020-of-00039.bin
Normal file
3
pytorch_model-00020-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:15c0fe7990e0ff66d6e97f4e417a243bd6c410f9c68c5550e16d45a540c77e55
|
||||
size 314575888
|
||||
3
pytorch_model-00021-of-00039.bin
Normal file
3
pytorch_model-00021-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:854d7f2bcdbcfef9c2da10715db16655ffb01208d3a8676270b2c9a3c2d7ed4b
|
||||
size 314592882
|
||||
3
pytorch_model-00022-of-00039.bin
Normal file
3
pytorch_model-00022-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2e3923a8d03407b7de9f21b8674a76fa452411bb9a978c396d5fa8e68f68ead0
|
||||
size 314592882
|
||||
3
pytorch_model-00023-of-00039.bin
Normal file
3
pytorch_model-00023-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4906a6adb941ea070f4dfecbab38758d2204510f3876abe4dfa755dcdc03dfce
|
||||
size 371215393
|
||||
3
pytorch_model-00024-of-00039.bin
Normal file
3
pytorch_model-00024-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ce2a8e47e385ca658ac40755bc01437025a23b4c8834c4e2e9ce7d46af10aa89
|
||||
size 371215986
|
||||
3
pytorch_model-00025-of-00039.bin
Normal file
3
pytorch_model-00025-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aee532bdb0eaac63f5469dc4f7065287d80b260eba0c626ef65dfcc2644b3f83
|
||||
size 371215986
|
||||
3
pytorch_model-00026-of-00039.bin
Normal file
3
pytorch_model-00026-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b8aebbdff9ed4a9bc32f465fa10dfa8f6c9ce21da27a692e486fa72ac43be9be
|
||||
size 371215986
|
||||
3
pytorch_model-00027-of-00039.bin
Normal file
3
pytorch_model-00027-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a73936ca41e140ae510fb88017a9d60c070b9670350277444cd1ee13547bbee7
|
||||
size 314575888
|
||||
3
pytorch_model-00028-of-00039.bin
Normal file
3
pytorch_model-00028-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:fc05ba29101a6e25b03fe74025f34c76d0ce82329b108719cd813c68978f6493
|
||||
size 314592882
|
||||
3
pytorch_model-00029-of-00039.bin
Normal file
3
pytorch_model-00029-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0791b02f3854a8f51747032af40418cee3fc1f1ad1bff921200d60fa3a22d9fb
|
||||
size 314592882
|
||||
3
pytorch_model-00030-of-00039.bin
Normal file
3
pytorch_model-00030-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5459d1784c919e074910aef7c130d7487ebd35a6918c98a136bf09bcc3b46228
|
||||
size 371215393
|
||||
3
pytorch_model-00031-of-00039.bin
Normal file
3
pytorch_model-00031-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5c21b13c13393328c797df56640d5df422b2a2d428b52dfecb63ca2732f6374d
|
||||
size 371215986
|
||||
3
pytorch_model-00032-of-00039.bin
Normal file
3
pytorch_model-00032-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b427c9daecad1d3c8430b3ddea343714cb1c2f2784346b44b9eb2f8d14a5dae2
|
||||
size 371215986
|
||||
3
pytorch_model-00033-of-00039.bin
Normal file
3
pytorch_model-00033-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e8b0590d14d4427e8141a4574c6f7bba1ee6d4528c8a78d013f14763cc1bf28b
|
||||
size 371215986
|
||||
3
pytorch_model-00034-of-00039.bin
Normal file
3
pytorch_model-00034-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e6ab507db375d2a0936ae6e77626df6df8ff8109d65d0bb2478f0a65da2b4a2
|
||||
size 314575888
|
||||
3
pytorch_model-00035-of-00039.bin
Normal file
3
pytorch_model-00035-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f1332fa25ea9db394d8b73502b2a5bb18d5e43b54f8d4998d26b164ed10ec681
|
||||
size 314592882
|
||||
3
pytorch_model-00036-of-00039.bin
Normal file
3
pytorch_model-00036-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:48647abb12226d4b582224bec091b6547d5ec3625a7c8a2d0cb07e3d54e769be
|
||||
size 314592882
|
||||
3
pytorch_model-00037-of-00039.bin
Normal file
3
pytorch_model-00037-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:7bfcb8b24b97ca4dbd30e74d376a74df691f039c67a822ba10f2833877f23407
|
||||
size 371215393
|
||||
3
pytorch_model-00038-of-00039.bin
Normal file
3
pytorch_model-00038-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a3b0b8fdad8412d629b685e0165d390aa00bd45848447a9073298e7a53c9897b
|
||||
size 304114977
|
||||
3
pytorch_model-00039-of-00039.bin
Normal file
3
pytorch_model-00039-of-00039.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5baa80a36adc9a292d9ef211ae373f0c365c56c489fb44f90055cc6195963e74
|
||||
size 262144938
|
||||
330
pytorch_model.bin.index.json
Normal file
330
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,330 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 13476839424
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00039-of-00039.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00039.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00002-of-00039.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00002-of-00039.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00002-of-00039.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00002-of-00039.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00002-of-00039.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00039.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00039.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00039.bin",
|
||||
"model.layers.0.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00039.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00039.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00003-of-00039.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00003-of-00039.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00003-of-00039.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00003-of-00039.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00003-of-00039.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00002-of-00039.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00003-of-00039.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00002-of-00039.bin",
|
||||
"model.layers.1.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00039.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00002-of-00039.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00014-of-00039.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00013-of-00039.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00013-of-00039.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00014-of-00039.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00014-of-00039.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00013-of-00039.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00013-of-00039.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00013-of-00039.bin",
|
||||
"model.layers.10.self_attn.rotary_emb.inv_freq": "pytorch_model-00013-of-00039.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00013-of-00039.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00015-of-00039.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00015-of-00039.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00014-of-00039.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00015-of-00039.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00015-of-00039.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00014-of-00039.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00014-of-00039.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00014-of-00039.bin",
|
||||
"model.layers.11.self_attn.rotary_emb.inv_freq": "pytorch_model-00014-of-00039.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00014-of-00039.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00016-of-00039.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00016-of-00039.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00016-of-00039.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00016-of-00039.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00016-of-00039.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00015-of-00039.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00015-of-00039.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00015-of-00039.bin",
|
||||
"model.layers.12.self_attn.rotary_emb.inv_freq": "pytorch_model-00015-of-00039.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00015-of-00039.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00017-of-00039.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00017-of-00039.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00017-of-00039.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00017-of-00039.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00017-of-00039.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00016-of-00039.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00017-of-00039.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00016-of-00039.bin",
|
||||
"model.layers.13.self_attn.rotary_emb.inv_freq": "pytorch_model-00017-of-00039.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00016-of-00039.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00018-of-00039.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00018-of-00039.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00018-of-00039.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00018-of-00039.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00018-of-00039.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00017-of-00039.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00018-of-00039.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00017-of-00039.bin",
|
||||
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00018-of-00039.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00018-of-00039.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00019-of-00039.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00019-of-00039.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00019-of-00039.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00019-of-00039.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00019-of-00039.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00019-of-00039.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00019-of-00039.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00018-of-00039.bin",
|
||||
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00019-of-00039.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00019-of-00039.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00021-of-00039.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00020-of-00039.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00020-of-00039.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00021-of-00039.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00021-of-00039.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00020-of-00039.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00020-of-00039.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00020-of-00039.bin",
|
||||
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00020-of-00039.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00020-of-00039.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00022-of-00039.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00022-of-00039.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00021-of-00039.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00022-of-00039.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00022-of-00039.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00021-of-00039.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00021-of-00039.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00021-of-00039.bin",
|
||||
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00021-of-00039.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00021-of-00039.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00023-of-00039.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00023-of-00039.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00023-of-00039.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00023-of-00039.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00023-of-00039.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00022-of-00039.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00022-of-00039.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00022-of-00039.bin",
|
||||
"model.layers.18.self_attn.rotary_emb.inv_freq": "pytorch_model-00022-of-00039.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00022-of-00039.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00024-of-00039.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00024-of-00039.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00024-of-00039.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00024-of-00039.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00024-of-00039.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00023-of-00039.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00024-of-00039.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00023-of-00039.bin",
|
||||
"model.layers.19.self_attn.rotary_emb.inv_freq": "pytorch_model-00024-of-00039.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00023-of-00039.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00004-of-00039.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00004-of-00039.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00004-of-00039.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00004-of-00039.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00004-of-00039.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00003-of-00039.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00004-of-00039.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00003-of-00039.bin",
|
||||
"model.layers.2.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00039.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00004-of-00039.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00025-of-00039.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00025-of-00039.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00025-of-00039.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00025-of-00039.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00025-of-00039.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00024-of-00039.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00025-of-00039.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00024-of-00039.bin",
|
||||
"model.layers.20.self_attn.rotary_emb.inv_freq": "pytorch_model-00025-of-00039.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00025-of-00039.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00026-of-00039.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00026-of-00039.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00026-of-00039.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00026-of-00039.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00026-of-00039.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00026-of-00039.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00026-of-00039.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00025-of-00039.bin",
|
||||
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00026-of-00039.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00026-of-00039.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00028-of-00039.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00027-of-00039.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00027-of-00039.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00028-of-00039.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00028-of-00039.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00027-of-00039.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00027-of-00039.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00027-of-00039.bin",
|
||||
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00027-of-00039.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00027-of-00039.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00029-of-00039.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00029-of-00039.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00028-of-00039.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00029-of-00039.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00029-of-00039.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00028-of-00039.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00028-of-00039.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00028-of-00039.bin",
|
||||
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00028-of-00039.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00028-of-00039.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00030-of-00039.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00030-of-00039.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00030-of-00039.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00030-of-00039.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00030-of-00039.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00029-of-00039.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00029-of-00039.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00029-of-00039.bin",
|
||||
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00029-of-00039.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00029-of-00039.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00031-of-00039.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00031-of-00039.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00031-of-00039.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00031-of-00039.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00031-of-00039.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00030-of-00039.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00031-of-00039.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00030-of-00039.bin",
|
||||
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00031-of-00039.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00030-of-00039.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00032-of-00039.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00032-of-00039.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00032-of-00039.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00032-of-00039.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00032-of-00039.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00031-of-00039.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00032-of-00039.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00031-of-00039.bin",
|
||||
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00032-of-00039.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00032-of-00039.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00033-of-00039.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00033-of-00039.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00033-of-00039.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00033-of-00039.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00033-of-00039.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00033-of-00039.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00033-of-00039.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00032-of-00039.bin",
|
||||
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00033-of-00039.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00033-of-00039.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00035-of-00039.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00034-of-00039.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00034-of-00039.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00035-of-00039.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00035-of-00039.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00034-of-00039.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00034-of-00039.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00034-of-00039.bin",
|
||||
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00034-of-00039.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00034-of-00039.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00036-of-00039.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00036-of-00039.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00035-of-00039.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00036-of-00039.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00036-of-00039.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00035-of-00039.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00035-of-00039.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00035-of-00039.bin",
|
||||
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00035-of-00039.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00035-of-00039.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00005-of-00039.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00005-of-00039.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00005-of-00039.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00005-of-00039.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00005-of-00039.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00005-of-00039.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00005-of-00039.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00004-of-00039.bin",
|
||||
"model.layers.3.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00039.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00005-of-00039.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00037-of-00039.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00037-of-00039.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00037-of-00039.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00037-of-00039.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00037-of-00039.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00036-of-00039.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00036-of-00039.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00036-of-00039.bin",
|
||||
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00036-of-00039.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00036-of-00039.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00038-of-00039.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00038-of-00039.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00038-of-00039.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00038-of-00039.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00038-of-00039.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00037-of-00039.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00038-of-00039.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00037-of-00039.bin",
|
||||
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00038-of-00039.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00037-of-00039.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00007-of-00039.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00006-of-00039.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00006-of-00039.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00007-of-00039.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00007-of-00039.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00006-of-00039.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00006-of-00039.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00006-of-00039.bin",
|
||||
"model.layers.4.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00039.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00006-of-00039.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00008-of-00039.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00008-of-00039.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00007-of-00039.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00008-of-00039.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00008-of-00039.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00007-of-00039.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00007-of-00039.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00007-of-00039.bin",
|
||||
"model.layers.5.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00039.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00007-of-00039.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00009-of-00039.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00009-of-00039.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00009-of-00039.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00009-of-00039.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00009-of-00039.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00008-of-00039.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00008-of-00039.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00008-of-00039.bin",
|
||||
"model.layers.6.self_attn.rotary_emb.inv_freq": "pytorch_model-00008-of-00039.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00008-of-00039.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00010-of-00039.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00010-of-00039.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00010-of-00039.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00010-of-00039.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00010-of-00039.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00009-of-00039.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00010-of-00039.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00009-of-00039.bin",
|
||||
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00010-of-00039.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00009-of-00039.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00011-of-00039.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00011-of-00039.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00011-of-00039.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00011-of-00039.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00011-of-00039.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00010-of-00039.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00011-of-00039.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00010-of-00039.bin",
|
||||
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00011-of-00039.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00011-of-00039.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00012-of-00039.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00012-of-00039.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00012-of-00039.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00012-of-00039.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00012-of-00039.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00012-of-00039.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00012-of-00039.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00011-of-00039.bin",
|
||||
"model.layers.9.self_attn.rotary_emb.inv_freq": "pytorch_model-00012-of-00039.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00012-of-00039.bin",
|
||||
"model.norm.weight": "pytorch_model-00038-of-00039.bin"
|
||||
}
|
||||
}
|
||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
93385
tokenizer.json
Normal file
93385
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.
34
tokenizer_config.json
Normal file
34
tokenizer_config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"model_max_length": 2048,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user