初始化项目，由ModelHub XC社区提供模型
Model: migtissera/Tess-M-v1.3 Source: Original Platform
This commit is contained in:
ModelHub XC
65
.gitattributes
vendored
Normal file
65
.gitattributes
vendored
Normal file
@@ -0,0 +1,65 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
|
||||
*.bz2 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
|
||||
|
||||
*.msgpack 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
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
pytorch_model-00012-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00007-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00003-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00004-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00002-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00008-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00001-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00010-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00009-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00015-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00013-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00011-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00014-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00005-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.model filter=lfs diff=lfs merge=lfs -text
|
||||
pytorch_model-00006-of-00015.bin filter=lfs diff=lfs merge=lfs -text
|
||||
31
README.md
Normal file
31
README.md
Normal file
@@ -0,0 +1,31 @@
|
||||
---
|
||||
license: other
|
||||
license_name: yi-34b
|
||||
license_link: https://huggingface.co/01-ai/Yi-34B/blob/main/LICENSE
|
||||
---
|
||||
|
||||
# Note:
|
||||
This version is the stable release. The issues that were present in versions 1.0, 1.1 and 1.2 all have been rectified. Thank you for your patience while R&D was conducted. Enjoy!
|
||||
|
||||
This model have been tested on very long context length. Model produced slight repetition, but it was very minor. I recommend testing the model to your usecase and limiting the context length. Here's my conversation: https://migel.substack.com/p/testing-tess-m-v13
|
||||
|
||||
As can be seen, "USER:" and "SYSTEM: Answer the question thoughtfully and intelligently. Always answer without hesitation." was presented by the model in the latter part of the conversation.
|
||||
|
||||
# Learnings:
|
||||
Here's my learnings going from Tess-v1.0 to Tess-v1.3: https://migel.substack.com/p/learnings-from-training-tess
|
||||
|
||||
# Tess
|
||||
|
||||
|
||||
|
||||
Tess, short for Tesoro (Treasure in Italian), is a general purpose Large Language Model series. Tess-M-v1.3 was trained on the Yi-34B-200K base.
|
||||
|
||||
|
||||
# Prompt Format:
|
||||
|
||||
```
|
||||
SYSTEM: <ANY SYSTEM CONTEXT>
|
||||
USER:
|
||||
ASSISTANT:
|
||||
```
|
||||
|
||||
4
added_tokens.json
Normal file
4
added_tokens.json
Normal file
@@ -0,0 +1,4 @@
|
||||
{
|
||||
"</s>": 64001,
|
||||
"<s>": 64000
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "/home/migel/Yi-34B-200K-Llama",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"bos_token_id": 64000,
|
||||
"eos_token_id": 64001,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 7168,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 20480,
|
||||
"max_position_embeddings": 200000,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 56,
|
||||
"num_hidden_layers": 60,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 5000000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.35.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 64002
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
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": "4.35.1"
|
||||
}
|
||||
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:ba4dc3bfe5e10fc44af91d132efc91f91922fa7a01b3b9c55ed4d57f0a256105
|
||||
size 4793167065
|
||||
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:c6cc5faf1392cdf988708b4ee6ede4a96e1b921c1712432c494726c5ce7d3716
|
||||
size 4756468297
|
||||
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:a40021bba5e2967d5551fa09d23514918110aeb06696ee3edad8ab7a41f791e4
|
||||
size 4991380097
|
||||
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 sha256:8514d0a303cd89536580132e5a66f1459227d3e81d801c00ba4c4dd4b3fa6766
|
||||
size 4756468333
|
||||
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:d78269745c56b670bef0f4176eea2b76755e30819e3674c48011c04fd3b18d2d
|
||||
size 4756468297
|
||||
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:cbcbf827d377569e19b6c8d5b6e69813fe683c593869d02950f20848188ce0ba
|
||||
size 4991380161
|
||||
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 sha256:8c457633bd6f29a9666c482fc89ed4a4dab15c4c27975852e688a265c363324a
|
||||
size 4756468333
|
||||
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:d8d498352725090b4d0eb022cd40c4c850ac2a49f1c3798f2cedc1c9c28bc267
|
||||
size 4756468297
|
||||
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 sha256:97604052b73e7bcb4cbbe99b115c53dd9e25fd40c2d22a78a0701142ee26c35d
|
||||
size 4991380161
|
||||
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:bc90c26c8a8aa1534d5e48956d91c9072fd472639253322a0d6c07ff6cb0554d
|
||||
size 4756468333
|
||||
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 sha256:2453b8c7aa33c0a1ca43f0757202c62fd78c3e98738be5cd544226d2abb358ce
|
||||
size 4756468297
|
||||
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:ea7c716792eb141fbba02bcbd34ca7ca1986ff69bf421ba8162c2392a35fe713
|
||||
size 4991380161
|
||||
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 sha256:02fd56b84515be08714b060d82302a918f76215e28ff815c5424a2fba97616eb
|
||||
size 4756468333
|
||||
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 sha256:93e1bd1b369bb624890f7a21d86bce7d8b962df2687885274375e9a65fd41171
|
||||
size 4756468297
|
||||
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:d5fc0d38de1fd5389978c0b01a0c6d0535a4db2b3d7f7eab1058b4ba82082a3a
|
||||
size 1211179118
|
||||
550
pytorch_model.bin.index.json
Normal file
550
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,550 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 68777891840
|
||||
},
|
||||
"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-00001-of-00015.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-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-00003-of-00015.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-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-00002-of-00015.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.40.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.41.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.42.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
|
||||
"model.layers.43.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.44.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.45.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.46.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
|
||||
"model.layers.47.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.48.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.49.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.50.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.51.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
|
||||
"model.layers.52.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.53.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.54.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.55.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
|
||||
"model.layers.56.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.57.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.58.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.59.input_layernorm.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00015-of-00015.bin",
|
||||
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
|
||||
"model.norm.weight": "pytorch_model-00015-of-00015.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": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8d22a896da936284f97462519cc81e1a0d0ab761ff2a2535f3d44cd0d84268f3
|
||||
size 3561399
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
||||
size 1033105
|
||||
57
tokenizer_config.json
Normal file
57
tokenizer_config.json
Normal file
@@ -0,0 +1,57 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<|startoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"64000": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"64001": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": false,
|
||||
"model_max_length": 200000,
|
||||
"pad_token": "<unk>",
|
||||
"padding_side": "right",
|
||||
"sp_model_kwargs": {},
|
||||
"spaces_between_special_tokens": false,
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"truncation_side": "right",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user