初始化项目，由ModelHub XC社区提供模型
Model: dsvv-cair/alpaca-cleaned-llama-30b-bf16 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
|
||||||
31
README.md
Normal file
31
README.md
Normal file
@@ -0,0 +1,31 @@
|
|||||||
|
---
|
||||||
|
# For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1
|
||||||
|
# Doc / guide: https://huggingface.co/docs/hub/model-cards
|
||||||
|
{}
|
||||||
|
---
|
||||||
|
|
||||||
|
**Method** : QLORA
|
||||||
|
|
||||||
|
**Dataset** : yahma/alpaca-cleaned
|
||||||
|
|
||||||
|
**Base model** : huggyllama/llama-30b
|
||||||
|
|
||||||
|
**Compute dtype** : bfloat16
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
|
||||||
|
# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
|
||||||
|
Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_dsvv-cair__alpaca-cleaned-llama-30b-bf16)
|
||||||
|
|
||||||
|
| Metric | Value |
|
||||||
|
|-----------------------|---------------------------|
|
||||||
|
| Avg. | 50.12 |
|
||||||
|
| ARC (25-shot) | 61.77 |
|
||||||
|
| HellaSwag (10-shot) | 85.06 |
|
||||||
|
| MMLU (5-shot) | 57.52 |
|
||||||
|
| TruthfulQA (0-shot) | 51.49 |
|
||||||
|
| Winogrande (5-shot) | 77.35 |
|
||||||
|
| GSM8K (5-shot) | 7.73 |
|
||||||
|
| DROP (3-shot) | 9.91 |
|
||||||
24
config.json
Normal file
24
config.json
Normal file
@@ -0,0 +1,24 @@
|
|||||||
|
{
|
||||||
|
"_name_or_path": "/home/mohit/text-generation-webui/models_ununsed/huggyllama_llama-30b_bkp/",
|
||||||
|
"architectures": [
|
||||||
|
"LlamaForCausalLM"
|
||||||
|
],
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"hidden_act": "silu",
|
||||||
|
"hidden_size": 6656,
|
||||||
|
"initializer_range": 0.02,
|
||||||
|
"intermediate_size": 17920,
|
||||||
|
"max_position_embeddings": 2048,
|
||||||
|
"max_sequence_length": 2048,
|
||||||
|
"model_type": "llama",
|
||||||
|
"num_attention_heads": 52,
|
||||||
|
"num_hidden_layers": 60,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"rms_norm_eps": 1e-06,
|
||||||
|
"tie_word_embeddings": false,
|
||||||
|
"torch_dtype": "float16",
|
||||||
|
"transformers_version": "4.29.2",
|
||||||
|
"use_cache": true,
|
||||||
|
"vocab_size": 32000
|
||||||
|
}
|
||||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
|||||||
|
{
|
||||||
|
"_from_model_config": true,
|
||||||
|
"bos_token_id": 1,
|
||||||
|
"eos_token_id": 2,
|
||||||
|
"pad_token_id": 0,
|
||||||
|
"transformers_version": "4.29.2"
|
||||||
|
}
|
||||||
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 sha256:8169a5a2185b35cd4f34e59fae1f56d96241eb5890994f51a344ce954d42161c
|
||||||
|
size 9818324627
|
||||||
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 sha256:4f0c5abfc47f34fa7585177818a92c479975c3596f4d60d98a48159c6d420571
|
||||||
|
size 9958102743
|
||||||
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:a09fd353dcd72bfed798171cb85d3372511738ece0f21aef86c59c140b33e7ac
|
||||||
|
size 9896734715
|
||||||
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 sha256:4ecdb29fd337e96e28f883cc49574ae35e18e98d85a07ee8a4945d6cf70ce938
|
||||||
|
size 9869470481
|
||||||
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 sha256:8386438db49cf51211f4beb7607f3d1152ff85d8578047f7cd9c3de4a54ae8ba
|
||||||
|
size 9869470445
|
||||||
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 sha256:8f7e2d2bd2176ed945377b6d99e4ee6fdbb4613ac7434f76ad0758db274de2ac
|
||||||
|
size 9958102743
|
||||||
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 sha256:10c267a37fcc715784c5bdf392ba73810bd9a583d56e27cfe3beb362007ef64e
|
||||||
|
size 5687903281
|
||||||
610
pytorch_model.bin.index.json
Normal file
610
pytorch_model.bin.index.json
Normal file
@@ -0,0 +1,610 @@
|
|||||||
|
{
|
||||||
|
"metadata": {
|
||||||
|
"total_size": 65057902592
|
||||||
|
},
|
||||||
|
"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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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-00002-of-00007.bin",
|
||||||
|
"model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-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-00002-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.rotary_emb.inv_freq": "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-00002-of-00007.bin",
|
||||||
|
"model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.14.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.15.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.16.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.17.self_attn.rotary_emb.inv_freq": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-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-00002-of-00007.bin",
|
||||||
|
"model.layers.18.self_attn.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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.rotary_emb.inv_freq": "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-00003-of-00007.bin",
|
||||||
|
"model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-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-00003-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.rotary_emb.inv_freq": "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-00003-of-00007.bin",
|
||||||
|
"model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.21.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.22.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.23.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.24.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.25.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.26.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-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-00004-of-00007.bin",
|
||||||
|
"model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.27.self_attn.rotary_emb.inv_freq": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00007.bin",
|
||||||
|
"model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.28.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.29.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-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.rotary_emb.inv_freq": "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-00004-of-00007.bin",
|
||||||
|
"model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.30.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.31.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.31.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.32.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.32.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.32.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.32.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.32.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.32.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.32.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.32.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.32.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.32.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.33.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.33.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.33.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.33.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.33.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.33.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.33.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.33.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.33.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.33.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.34.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.34.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.34.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.34.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.34.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.34.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.34.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.34.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.34.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.34.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.35.input_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.35.mlp.down_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.35.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.35.mlp.up_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.35.post_attention_layernorm.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.35.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.35.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.35.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.35.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.35.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.36.mlp.gate_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.36.self_attn.k_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.36.self_attn.o_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.36.self_attn.q_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.36.self_attn.rotary_emb.inv_freq": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.36.self_attn.v_proj.weight": "pytorch_model-00004-of-00007.bin",
|
||||||
|
"model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.37.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.38.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.39.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.39.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.39.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.39.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.39.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-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.rotary_emb.inv_freq": "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-00005-of-00007.bin",
|
||||||
|
"model.layers.40.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.40.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.40.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.40.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.40.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.40.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.40.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.40.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.40.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.41.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.41.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.41.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.41.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.41.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.41.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.41.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.41.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.41.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.41.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.42.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.42.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.42.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.42.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.42.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.42.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.42.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.42.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.42.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.42.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.43.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.43.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.43.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.43.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.43.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.43.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.43.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.43.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.43.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.43.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.44.input_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.44.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.44.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.44.mlp.up_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.44.post_attention_layernorm.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.44.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.44.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.44.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.44.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.44.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.45.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.45.mlp.down_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.45.mlp.gate_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.45.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.45.self_attn.k_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.45.self_attn.o_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.45.self_attn.q_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.45.self_attn.rotary_emb.inv_freq": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.45.self_attn.v_proj.weight": "pytorch_model-00005-of-00007.bin",
|
||||||
|
"model.layers.46.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.46.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.46.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.46.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.46.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.46.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.46.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.46.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.46.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.46.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.47.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.47.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.47.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.47.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.47.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.47.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.47.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.47.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.47.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.47.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.48.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.48.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.48.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.48.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.48.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.48.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.48.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.48.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.48.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.48.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.49.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.49.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.49.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.49.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.49.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.49.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.49.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.49.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.49.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.49.self_attn.v_proj.weight": "pytorch_model-00006-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.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.50.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.50.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.50.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.50.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.50.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.50.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.50.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.50.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.50.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.50.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.51.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.51.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.51.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.51.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.51.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.51.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.51.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.51.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.51.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.51.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.52.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.52.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.52.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.52.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.52.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.52.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.52.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.52.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.52.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.52.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.53.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.53.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.53.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.53.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.53.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.53.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.53.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.53.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.53.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.53.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.54.input_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.54.mlp.down_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.54.mlp.gate_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.54.mlp.up_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.54.post_attention_layernorm.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.54.self_attn.k_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.54.self_attn.o_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.54.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.54.self_attn.rotary_emb.inv_freq": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.54.self_attn.v_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.55.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.55.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.55.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.55.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.55.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.55.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.55.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.55.self_attn.q_proj.weight": "pytorch_model-00006-of-00007.bin",
|
||||||
|
"model.layers.55.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.55.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.56.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.56.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.56.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.56.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.56.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.56.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.56.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.56.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.56.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.56.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.57.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.57.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.57.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.57.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.57.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.57.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.57.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.57.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.57.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.57.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.58.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.58.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.58.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.58.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.58.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.58.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.58.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.58.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.58.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.58.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.59.input_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.59.mlp.down_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.59.mlp.gate_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.59.mlp.up_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.59.post_attention_layernorm.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.59.self_attn.k_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.59.self_attn.o_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.59.self_attn.q_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.59.self_attn.rotary_emb.inv_freq": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.59.self_attn.v_proj.weight": "pytorch_model-00007-of-00007.bin",
|
||||||
|
"model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-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-00001-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.rotary_emb.inv_freq": "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-00001-of-00007.bin",
|
||||||
|
"model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.7.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00007.bin",
|
||||||
|
"model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-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-00001-of-00007.bin",
|
||||||
|
"model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.8.self_attn.rotary_emb.inv_freq": "pytorch_model-00001-of-00007.bin",
|
||||||
|
"model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-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.rotary_emb.inv_freq": "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"
|
||||||
|
}
|
||||||
|
}
|
||||||
23
special_tokens_map.json
Normal file
23
special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
|||||||
|
{
|
||||||
|
"bos_token": {
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"eos_token": {
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"unk_token": {
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
93385
tokenizer.json
Normal file
93385
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.
33
tokenizer_config.json
Normal file
33
tokenizer_config.json
Normal file
@@ -0,0 +1,33 @@
|
|||||||
|
{
|
||||||
|
"add_bos_token": true,
|
||||||
|
"add_eos_token": false,
|
||||||
|
"bos_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "<s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"clean_up_tokenization_spaces": false,
|
||||||
|
"eos_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "</s>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
},
|
||||||
|
"model_max_length": 2048,
|
||||||
|
"pad_token": null,
|
||||||
|
"sp_model_kwargs": {},
|
||||||
|
"tokenizer_class": "LlamaTokenizer",
|
||||||
|
"unk_token": {
|
||||||
|
"__type": "AddedToken",
|
||||||
|
"content": "<unk>",
|
||||||
|
"lstrip": false,
|
||||||
|
"normalized": true,
|
||||||
|
"rstrip": false,
|
||||||
|
"single_word": false
|
||||||
|
}
|
||||||
|
}
|
||||||
Reference in New Issue
Block a user