初始化项目，由ModelHub XC社区提供模型
Model: athirdpath/Nethena-20b-Glued 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
|
||||
21
README.md
Normal file
21
README.md
Normal file
@@ -0,0 +1,21 @@
|
||||
---
|
||||
license: cc-by-nc-4.0
|
||||
---
|
||||
This is [NeverSleep/Nethena-20B](https://huggingface.co/NeverSleep/Nethena-20B) with [athirdpath/Nethena-20b-Glue-LORA](https://huggingface.co/athirdpath/Nethena-20b-Glue-LORA) applied.
|
||||
|
||||
athirdpath/Nethena-20b-Glue-LORA is a 128 rank LORA for RP, trained on a private dataset. It is unalligned and NSFW-oriented.
|
||||
|
||||
This is a test, exploring the effects of "gluing" the components of the 20b model together to reduce the iconic word replacement errors, increase lucidity, and improve recall.
|
||||
|
||||
|
||||
|
||||
The private ~500k token dataset used to train the LORA was Alpaca formatted and focused on 4 primary categories:
|
||||
|
||||
- Medical texts (on psychology, reproductive organs, anatomy, and pregnancy). These are formatted so the model, in character as a doctor or therapist, answers a patient's question in short to medium form.
|
||||
- Excerpts from short stories and novellas (erotic and romantic) centered around both realistic and fantastic situations, covering several fetishes as well. These are sliced into ~2048 token chunks, and these long-form responses are all tied to the command “Enter narrator mode.” in the instructions.
|
||||
- A selection from PIPPA, using a wide keyword search for tokens associated with low quality human or AI data to remove those responses, then a positive search was done for words and phrases associated with a higher reading level. These are converted to Alpaca with “Enter RP mode.” in all the instruction fields.
|
||||
- ~18k tokens of GPT-4 generated data on role-playing from various characters’ perspectives, focusing on different situations and emotions. Includes many multi-turn conversations.
|
||||
|
||||
So far it is passing subjective testing with flying colors, objective numbers coming soon.
|
||||
|
||||
Trained with Alpaca-style prompts.
|
||||
3
added_tokens.json
Normal file
3
added_tokens.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"[PAD]": 32000
|
||||
}
|
||||
BIN
b5787896-afd5-44a3-b757-0e75ee28bed8.png
Normal file
BIN
b5787896-afd5-44a3-b757-0e75ee28bed8.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 751 KiB |
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "NeverSleep/Nethena-20B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13824,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 62,
|
||||
"num_key_value_heads": 40,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 10000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.34.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32001
|
||||
}
|
||||
8
generation_config.json
Normal file
8
generation_config.json
Normal file
@@ -0,0 +1,8 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.34.1",
|
||||
"use_cache": false
|
||||
}
|
||||
3
pytorch_model-00001-of-00005.bin
Normal file
3
pytorch_model-00001-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b79e712857eecc3a3c1d8bf08c00b8f7d39bad827e2cdbbd2af1d548c03e0494
|
||||
size 9948729673
|
||||
3
pytorch_model-00002-of-00005.bin
Normal file
3
pytorch_model-00002-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c99e45a794c3018c82165967e74fe3e5038d95fda4e53cf7497bad7e64e6a9e4
|
||||
size 9904155408
|
||||
3
pytorch_model-00003-of-00005.bin
Normal file
3
pytorch_model-00003-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:313287606615b6bebe5568650c990151628a06ae6cbb5d39d812d1b2bad18718
|
||||
size 9867476673
|
||||
3
pytorch_model-00004-of-00005.bin
Normal file
3
pytorch_model-00004-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:53c0160dfabc148425c3d4b95e8de0ee0d1afae953a2e6c9a2ba4834b46fafcd
|
||||
size 9940886914
|
||||
3
pytorch_model-00005-of-00005.bin
Normal file
3
pytorch_model-00005-of-00005.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0ed37cd348555434bbcb7be3f37bad715f5eee8ce64700f5a6a62389077651f4
|
||||
size 327691178
|
||||
568
pytorch_model.bin.index.json
Normal file
568
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,568 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 39988746240
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00005-of-00005.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00002-of-00005.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.40.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.41.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.42.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.43.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.44.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.45.input_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.46.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00003-of-00005.bin",
|
||||
"model.layers.47.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.48.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.49.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.50.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.51.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.52.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.53.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.54.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.55.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.56.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.57.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.58.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.59.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.60.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.60.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.60.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.60.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.60.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.60.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.60.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.60.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.60.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.61.input_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.61.mlp.down_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.61.mlp.gate_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.61.mlp.up_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.61.post_attention_layernorm.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.61.self_attn.k_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.61.self_attn.o_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.61.self_attn.q_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.61.self_attn.v_proj.weight": "pytorch_model-00004-of-00005.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00001-of-00005.bin",
|
||||
"model.norm.weight": "pytorch_model-00004-of-00005.bin"
|
||||
}
|
||||
}
|
||||
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
|
||||
}
|
||||
}
|
||||
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
52
tokenizer_config.json
Normal file
52
tokenizer_config.json
Normal file
@@ -0,0 +1,52 @@
|
||||
{
|
||||
"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
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 2048,
|
||||
"pad_token": "[PAD]",
|
||||
"padding_side": "left",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"trust_remote_code": false,
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false,
|
||||
"use_fast": true
|
||||
}
|
||||
Reference in New Issue
Block a user