初始化项目，由ModelHub XC社区提供模型
Model: BlueNipples/TimeCrystal-l2-13B 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
|
||||
26
README.md
Normal file
26
README.md
Normal file
@@ -0,0 +1,26 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
tags:
|
||||
- llama-2
|
||||
- roleplaying
|
||||
---
|
||||
This 13B model, TimeCrystal-l2-13B is built to maximize logic and instruct following, whilst also increasing the vividness of prose found in Chronos based models like Mythomax, over the more romantic prose, hopefully without losing the elegent narrative structure touch of newer models like synthia and xwin. TLDR: Attempt at more clever, better prose.
|
||||
|
||||
Tentative test results: I'm not certain if logic/instruct was improved or not (haven't tested much), but the prose infusion seems to have worked really well.
|
||||
|
||||
It is built so:
|
||||
|
||||
SLERPS:
|
||||
Amethyst + Openchat Super = OpenStone
|
||||
|
||||
MythoMax + Chronos = ChronoMax
|
||||
|
||||
ChronoMax + Amethyst = TimeStone
|
||||
|
||||
Gradient Merge:
|
||||
|
||||
TimeStone + OpenStone (0.9,0,0) = TimeCrystal
|
||||
|
||||
Props to all the mergers, fine tuners!
|
||||
|
||||
All models in Merge: Many, lol.
|
||||
3
added_tokens.json
Normal file
3
added_tokens.json
Normal file
@@ -0,0 +1,3 @@
|
||||
{
|
||||
"<pad>": 32000
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": ".\\TimeStone",
|
||||
"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": 40,
|
||||
"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": "4.34.0",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
3
pytorch_model-00001-of-00013.bin
Normal file
3
pytorch_model-00001-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:021c5cd1c130fda08bd7cbbac623beffb1df40d7851ab01bceec4d99908389e3
|
||||
size 2089337516
|
||||
3
pytorch_model-00002-of-00013.bin
Normal file
3
pytorch_model-00002-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e65b773db54420ede974c5d93c54ffd7e02251acca2a261474c81c797da1d70a
|
||||
size 2044815558
|
||||
3
pytorch_model-00003-of-00013.bin
Normal file
3
pytorch_model-00003-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:82ef7972f4363cb7e37acaeaa04c91992ed5a595f743b9b832bd0f439bcab424
|
||||
size 2060523782
|
||||
3
pytorch_model-00004-of-00013.bin
Normal file
3
pytorch_model-00004-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:218e0189271086b0502126990e913dd7ec1e34e9b3b499c34b161f2e67c7577b
|
||||
size 1955665570
|
||||
3
pytorch_model-00005-of-00013.bin
Normal file
3
pytorch_model-00005-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a44e286f817bce8c04cd5f99ad03f449fbcf0fdb86ed711d5e175414d943321d
|
||||
size 2044794530
|
||||
3
pytorch_model-00006-of-00013.bin
Normal file
3
pytorch_model-00006-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cb5922fdecd7b4890381971a43fd3238538b2886d0f686d834d090a2adee6e3a
|
||||
size 2044794530
|
||||
3
pytorch_model-00007-of-00013.bin
Normal file
3
pytorch_model-00007-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:500e23ce4211e74ce0dd0ec2472eaf7f1ceedcbfd93212ceaa0c910c3730ce4f
|
||||
size 2044815622
|
||||
3
pytorch_model-00008-of-00013.bin
Normal file
3
pytorch_model-00008-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c57e5bba1bca3226955e9d75ee1c9fbdc70eba8d156e2f1799c0e815d1039a9f
|
||||
size 2060523782
|
||||
3
pytorch_model-00009-of-00013.bin
Normal file
3
pytorch_model-00009-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2edaf8ba5506e25fad457d43c0fed58f4aca0062941b3eeb5575d57c23deab52
|
||||
size 1955665570
|
||||
3
pytorch_model-00010-of-00013.bin
Normal file
3
pytorch_model-00010-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d3d7241db7cabd9fd246f0586eb46b638a286b470503ff5d72311fc7140a6030
|
||||
size 2044794530
|
||||
3
pytorch_model-00011-of-00013.bin
Normal file
3
pytorch_model-00011-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d5d91dcf229472b8055b9f8120048910f26f8b79443da41dbe7983360ea5f680
|
||||
size 2044794530
|
||||
3
pytorch_model-00012-of-00013.bin
Normal file
3
pytorch_model-00012-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f0ffe0ee92269894eeb6d8f22274683627e1586a103ba0ff3a670ddf3358d156
|
||||
size 2044815622
|
||||
3
pytorch_model-00013-of-00013.bin
Normal file
3
pytorch_model-00013-of-00013.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3a595a577f8424db11c6920868c44dffeac0d959b79d470242c268fc1385491f
|
||||
size 1596515474
|
||||
370
pytorch_model.bin.index.json
Normal file
370
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,370 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 26031728640
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00005-of-00013.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00006-of-00013.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00013.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00007-of-00013.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00008-of-00013.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00009-of-00013.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00010-of-00013.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00011-of-00013.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00012-of-00013.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00013-of-00013.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00013.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00004-of-00013.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00013.bin",
|
||||
"model.norm.weight": "pytorch_model-00013-of-00013.bin"
|
||||
}
|
||||
}
|
||||
24
special_tokens_map.json
Normal file
24
special_tokens_map.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"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
|
||||
},
|
||||
"pad_token": "<unk>",
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
|
||||
size 499723
|
||||
Reference in New Issue
Block a user