初始化项目，由ModelHub XC社区提供模型
Model: vihangd/shearedplats-2.7b-v1 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
|
||||
12
README.md
Normal file
12
README.md
Normal file
@@ -0,0 +1,12 @@
|
||||
---
|
||||
license: llama2
|
||||
---
|
||||
<h1>Use v2 </h1>
|
||||
<p><h1> ShearedPlats-7b </h1></p>
|
||||
An experimental finetune of Sheared LLaMA 2.7b with Alpaca-QLoRA
|
||||
|
||||
<h2> Datasets </h2>
|
||||
Trained on alpca style datasets
|
||||
|
||||
<p><h2> Prompt Template </h2></p>
|
||||
Uses alpaca style prompt template
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "princeton-nlp/Sheared-LLaMA-2.7B",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2560,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 6912,
|
||||
"max_position_embeddings": 4096,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 20,
|
||||
"num_hidden_layers": 32,
|
||||
"num_key_value_heads": 20,
|
||||
"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": "4.35.0.dev0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.35.0.dev0"
|
||||
}
|
||||
3
pytorch_model-00001-of-00015.bin
Normal file
3
pytorch_model-00001-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:38cc5535ec8974e4b62da1f235dd5e38839b0a5dcaeb8b3b4933ca86b96422b1
|
||||
size 374881638
|
||||
3
pytorch_model-00002-of-00015.bin
Normal file
3
pytorch_model-00002-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d5ce3f760fd6f4235c7a74c7573e10875412c8623cdd166b0c1f96abddcfa7be
|
||||
size 388000914
|
||||
3
pytorch_model-00003-of-00015.bin
Normal file
3
pytorch_model-00003-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ffe1a726eee35c050e91d0d24e0a503f09eb94b4b538dfbef4e2975eb7f991ee
|
||||
size 391944602
|
||||
3
pytorch_model-00004-of-00015.bin
Normal file
3
pytorch_model-00004-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3257da8148082c23373c259f0e19aa0f86b5715df3b49c238f8f48cc25fbfc23
|
||||
size 365718674
|
||||
3
pytorch_model-00005-of-00015.bin
Normal file
3
pytorch_model-00005-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:e41d4526b2951183b726941ed21a0c142fb61b58a8029081c79bafc9e191157f
|
||||
size 388011830
|
||||
3
pytorch_model-00006-of-00015.bin
Normal file
3
pytorch_model-00006-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:035baa4738f00a2e44863555aca86cb9e60f70e245f3f0487dede9cb0dc46ffa
|
||||
size 369651510
|
||||
3
pytorch_model-00007-of-00015.bin
Normal file
3
pytorch_model-00007-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f98ea76719916d20d75e232b70e48713afced6ff8d58c8c483e8324ba00b7f86
|
||||
size 388000978
|
||||
3
pytorch_model-00008-of-00015.bin
Normal file
3
pytorch_model-00008-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f6245e3676ea6b8abe9de7a7e5ce212fd07afa1168136064793b1b942eaa5bfe
|
||||
size 391944602
|
||||
3
pytorch_model-00009-of-00015.bin
Normal file
3
pytorch_model-00009-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0ed72cbe77138df0ad933854e7e204760831ebb35bf821262a22c08ace12e814
|
||||
size 365718738
|
||||
3
pytorch_model-00010-of-00015.bin
Normal file
3
pytorch_model-00010-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6aa50d314efc3bd2f490b77ea599138282214f5465662408bfcad9ad3c07e6dd
|
||||
size 388011830
|
||||
3
pytorch_model-00011-of-00015.bin
Normal file
3
pytorch_model-00011-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2fa94963e09499eb435731ece953e9347983eb6f111257559a40d11f1dd41614
|
||||
size 369651510
|
||||
3
pytorch_model-00012-of-00015.bin
Normal file
3
pytorch_model-00012-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:479f701b9cd6beddb19b0a0e4bae81d4a0683a2d22a86d867c1be01f3ef24cd2
|
||||
size 388000978
|
||||
3
pytorch_model-00013-of-00015.bin
Normal file
3
pytorch_model-00013-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6982faf724fced333549915eae40765d9f1fe94453bf1b97678c6f4c620dbeab
|
||||
size 391944602
|
||||
3
pytorch_model-00014-of-00015.bin
Normal file
3
pytorch_model-00014-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:2af2b52a78ba50c5d7cec2a0218a4f4f724c1e0c614719484f1a628151163f4e
|
||||
size 277904330
|
||||
3
pytorch_model-00015-of-00015.bin
Normal file
3
pytorch_model-00015-of-00015.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0edd18c223a83ab8026c2079b9b31dc28c1cddcf135da16d684bae271e83392c
|
||||
size 163841413
|
||||
298
pytorch_model.bin.index.json
Normal file
298
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,298 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 5403120640
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.norm.weight": "pytorch_model-00014-of-00015.bin"
|
||||
}
|
||||
}
|
||||
93391
tokenizer.json
Normal file
93391
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
BIN
tokenizer.model
(Stored with Git LFS)
Normal file
Binary file not shown.
35
tokenizer_config.json
Normal file
35
tokenizer_config.json
Normal file
@@ -0,0 +1,35 @@
|
||||
{
|
||||
"add_bos_token": true,
|
||||
"add_eos_token": false,
|
||||
"bos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"legacy": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": {
|
||||
"__type": "AddedToken",
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user