初始化项目，由ModelHub XC社区提供模型
Model: mzbac/CodeLlama-34b-guanaco 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
|
||||
10
README.md
Normal file
10
README.md
Normal file
@@ -0,0 +1,10 @@
|
||||
---
|
||||
license: mit
|
||||
---
|
||||
Codellama 34b base model fine-tuned on the text chunk from the OpenAssistant-Guanaco dataset instead of Q&A pair, so it struggles to determine the end of the answer. recommend using a stop string like "### Human:" to prevent the model from talking to itself.
|
||||
|
||||
Prompt template:
|
||||
```
|
||||
### Human: {prompt}
|
||||
### Assistant:
|
||||
```
|
||||
9
added_tokens.json
Normal file
9
added_tokens.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"</s>": 2,
|
||||
"<s>": 1,
|
||||
"<unk>": 0,
|
||||
"▁<EOT>": 32003,
|
||||
"▁<MID>": 32001,
|
||||
"▁<PRE>": 32000,
|
||||
"▁<SUF>": 32002
|
||||
}
|
||||
27
config.json
Normal file
27
config.json
Normal file
@@ -0,0 +1,27 @@
|
||||
{
|
||||
"_name_or_path": "codellama/CodeLlama-34b-guanaco",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 8192,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 22016,
|
||||
"max_position_embeddings": 16384,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 64,
|
||||
"num_hidden_layers": 48,
|
||||
"num_key_value_heads": 8,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.34.0",
|
||||
"use_cache": true,
|
||||
"vocab_size": 32000
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"transformers_version": "4.34.0"
|
||||
}
|
||||
3
pytorch_model-00001-of-00007.bin
Normal file
3
pytorch_model-00001-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:065a570c9a7efbbc34c35d7c339bc410fa19b77f2667847d4311c748a77c9aef
|
||||
size 9852637497
|
||||
3
pytorch_model-00002-of-00007.bin
Normal file
3
pytorch_model-00002-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:46a99875186fc21cc7edd1011f9dbdf966a486b5e507bb94fafb49428e882c3f
|
||||
size 9689093137
|
||||
3
pytorch_model-00003-of-00007.bin
Normal file
3
pytorch_model-00003-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:ab8455bfbbf4427878c4368c049dc0450d0f18d51b8866d18625b41a2b9c0bd8
|
||||
size 9689093137
|
||||
3
pytorch_model-00004-of-00007.bin
Normal file
3
pytorch_model-00004-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c5d5e8e3024e137ddb37bc183ebcfd88a86ff76d724ccc90a46fb26b941e4690
|
||||
size 9689093137
|
||||
3
pytorch_model-00005-of-00007.bin
Normal file
3
pytorch_model-00005-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:238f8ddbc4300d6e79cf3ed40fc67d7900167ab2846d58ca4169bbe93895cf8c
|
||||
size 9689093137
|
||||
3
pytorch_model-00006-of-00007.bin
Normal file
3
pytorch_model-00006-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:32cbd8feb4c8e96ec54b5a17e4123ae33d8fa5f74b5ef6eda3285da4b6a2e5a2
|
||||
size 9689093137
|
||||
3
pytorch_model-00007-of-00007.bin
Normal file
3
pytorch_model-00007-of-00007.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1c34522844f3b30fc31051e2542205dcccd552802cb80939252ec34b125be970
|
||||
size 9189985945
|
||||
442
pytorch_model.bin.index.json
Normal file
442
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,442 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 67487940608
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.embed_tokens.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||
"model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||
"model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||
"model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.36.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.37.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.41.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||
"model.layers.42.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.43.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.44.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.45.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.46.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||
"model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||
"model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||
"model.norm.weight": "pytorch_model-00007-of-00007.bin"
|
||||
}
|
||||
}
|
||||
11
special_tokens_map.json
Normal file
11
special_tokens_map.json
Normal file
@@ -0,0 +1,11 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"▁<PRE>",
|
||||
"▁<MID>",
|
||||
"▁<SUF>",
|
||||
"▁<EOT>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"eos_token": "</s>",
|
||||
"unk_token": "<unk>"
|
||||
}
|
||||
93427
tokenizer.json
Normal file
93427
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.
81
tokenizer_config.json
Normal file
81
tokenizer_config.json
Normal file
@@ -0,0 +1,81 @@
|
||||
{
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": true,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32000": {
|
||||
"content": "▁<PRE>",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32001": {
|
||||
"content": "▁<MID>",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32002": {
|
||||
"content": "▁<SUF>",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"32003": {
|
||||
"content": "▁<EOT>",
|
||||
"lstrip": true,
|
||||
"normalized": false,
|
||||
"rstrip": true,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"▁<PRE>",
|
||||
"▁<MID>",
|
||||
"▁<SUF>",
|
||||
"▁<EOT>"
|
||||
],
|
||||
"bos_token": "<s>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"eot_token": "▁<EOT>",
|
||||
"fill_token": "<FILL_ME>",
|
||||
"legacy": null,
|
||||
"middle_token": "▁<MID>",
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": null,
|
||||
"prefix_token": "▁<PRE>",
|
||||
"sp_model_kwargs": {},
|
||||
"suffix_token": "▁<SUF>",
|
||||
"tokenizer_class": "CodeLlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user