初始化项目，由ModelHub XC社区提供模型
Model: abacusai/MM-Orc-Vic-bagel-34b-c1000 Source: Original Platform
This commit is contained in:
ModelHub XC
65
.gitattributes
vendored
Normal file
65
.gitattributes
vendored
Normal file
@@ -0,0 +1,65 @@
|
||||
*.7z filter=lfs diff=lfs merge=lfs -text
|
||||
*.arrow filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin filter=lfs diff=lfs merge=lfs -text
|
||||
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.ftz filter=lfs diff=lfs merge=lfs -text
|
||||
*.gz filter=lfs diff=lfs merge=lfs -text
|
||||
*.h5 filter=lfs diff=lfs merge=lfs -text
|
||||
*.joblib filter=lfs diff=lfs merge=lfs -text
|
||||
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
||||
*.onnx filter=lfs diff=lfs merge=lfs -text
|
||||
*.ot filter=lfs diff=lfs merge=lfs -text
|
||||
*.parquet filter=lfs diff=lfs merge=lfs -text
|
||||
*.pb filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt filter=lfs diff=lfs merge=lfs -text
|
||||
*.pth filter=lfs diff=lfs merge=lfs -text
|
||||
*.rar filter=lfs diff=lfs merge=lfs -text
|
||||
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
||||
*.tflite filter=lfs diff=lfs merge=lfs -text
|
||||
*.tgz filter=lfs diff=lfs merge=lfs -text
|
||||
*.xz filter=lfs diff=lfs merge=lfs -text
|
||||
*.zip filter=lfs diff=lfs merge=lfs -text
|
||||
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
||||
*.tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
*.db* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ark* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
|
||||
**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
||||
*.gguf* filter=lfs diff=lfs merge=lfs -text
|
||||
*.ggml filter=lfs diff=lfs merge=lfs -text
|
||||
*.llamafile* filter=lfs diff=lfs merge=lfs -text
|
||||
*.pt2 filter=lfs diff=lfs merge=lfs -text
|
||||
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
||||
*.npy filter=lfs diff=lfs merge=lfs -text
|
||||
*.npz filter=lfs diff=lfs merge=lfs -text
|
||||
*.pickle filter=lfs diff=lfs merge=lfs -text
|
||||
*.pkl filter=lfs diff=lfs merge=lfs -text
|
||||
*.tar filter=lfs diff=lfs merge=lfs -text
|
||||
*.wasm filter=lfs diff=lfs merge=lfs -text
|
||||
*.zst filter=lfs diff=lfs merge=lfs -text
|
||||
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
||||
|
||||
model-00015-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00002-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.model filter=lfs diff=lfs merge=lfs -text
|
||||
model-00007-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00003-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00004-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
||||
model-00008-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00001-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00010-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00014-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00005-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00009-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00013-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00011-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00006-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
model-00012-of-00015.safetensors filter=lfs diff=lfs merge=lfs -text
|
||||
15
README.md
Normal file
15
README.md
Normal file
@@ -0,0 +1,15 @@
|
||||
---
|
||||
license: apache-2.0
|
||||
datasets:
|
||||
- abacusai/MetaMathFewshot
|
||||
---
|
||||
|
||||
Finetune of the DPO Bagel model (https://huggingface.co/jondurbin/nontoxic-bagel-34b-v0.2) on the MetamathFewshot (https://huggingface.co/datasets/abacusai/MetaMathFewshot) dataset
|
||||
|
||||
### Evaluation Results
|
||||
|
||||
| Average | ARC | HellaSwag | MMLU | TruthfulQA | Winogrande | GSM8K |
|
||||
| --- | --- | --- | --- | --- | --- | --- |
|
||||
| | | | | | | |
|
||||
|
||||
For comparison the GSM8K score for the original `nontoxic-bagel-34b-v0.2` model was 58.45 and average score was 74.69
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "/data/models/nontoxic-bagel-34b-v0.2/",
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 7168,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 20480,
|
||||
"max_position_embeddings": 200000,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 56,
|
||||
"num_hidden_layers": 60,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 5000000.0,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "float16",
|
||||
"transformers_version": "4.36.2",
|
||||
"use_cache": true,
|
||||
"vocab_size": 64000
|
||||
}
|
||||
1
configuration.json
Normal file
1
configuration.json
Normal file
@@ -0,0 +1 @@
|
||||
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}
|
||||
7
generation_config.json
Normal file
7
generation_config.json
Normal file
@@ -0,0 +1,7 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 1,
|
||||
"eos_token_id": 2,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "4.36.2"
|
||||
}
|
||||
3
model-00001-of-00015.safetensors
Normal file
3
model-00001-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:3c0b9c18ad0f43b45b66cfc6d79976f0ba308434bce522ebe64e9501e3813965
|
||||
size 4793130720
|
||||
3
model-00002-of-00015.safetensors
Normal file
3
model-00002-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6ecbd27c23b883559bccb5577c0cd0be85c878452d3d61662d47ccec357a6258
|
||||
size 4756459680
|
||||
3
model-00003-of-00015.safetensors
Normal file
3
model-00003-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5859f6d9dacb942203b9c02781d3be583d87d1eef605dd7fd3a0f7171aa67a38
|
||||
size 4991370096
|
||||
3
model-00004-of-00015.safetensors
Normal file
3
model-00004-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1b9182c89645a8bdc609c2779a11c7e4c016b4b51e8db607f08975102b8d8402
|
||||
size 4756459720
|
||||
3
model-00005-of-00015.safetensors
Normal file
3
model-00005-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:dbbedcdcb11d46a11a405b6fd1436ac558258268201c8301fc309f95649eb8a9
|
||||
size 4756459720
|
||||
3
model-00006-of-00015.safetensors
Normal file
3
model-00006-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cfb9c8c0e3a4478f3853039cd355794f7d034b908d89b9d25474db0ed2a8d00b
|
||||
size 4991370120
|
||||
3
model-00007-of-00015.safetensors
Normal file
3
model-00007-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0eb62a8d94abf0663d4be930155003ae4163527cffc22318d9ad964eb2a0a853
|
||||
size 4756459720
|
||||
3
model-00008-of-00015.safetensors
Normal file
3
model-00008-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:5853f9a056701563af88bcb13ae932202fbeb57e12e1537311f65b8495d4c091
|
||||
size 4756459720
|
||||
3
model-00009-of-00015.safetensors
Normal file
3
model-00009-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0c3f8d2cfbf3922dc265bdcd05f9ac9babdf063602be7ad0596dc04962366290
|
||||
size 4991370120
|
||||
3
model-00010-of-00015.safetensors
Normal file
3
model-00010-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1c8fd78412c589b226617c9cab56e125548f94e3b4d6030cceb5908bd887f69d
|
||||
size 4756459720
|
||||
3
model-00011-of-00015.safetensors
Normal file
3
model-00011-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:073c40a8fa288d17dbec66feb8eec3c0abb64e9ef994574367849b900ba48734
|
||||
size 4756459720
|
||||
3
model-00012-of-00015.safetensors
Normal file
3
model-00012-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a519d2c17639289bbf9748d12594aca455774daef3b7451a98247ffebc74160d
|
||||
size 4991370120
|
||||
3
model-00013-of-00015.safetensors
Normal file
3
model-00013-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8dc19f0fd46a735344aff6cc8b804baa428f91b51144ebd0b8b0fce3fc15c081
|
||||
size 4756459720
|
||||
3
model-00014-of-00015.safetensors
Normal file
3
model-00014-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bfb751fe4371a5de335c07c70abeda84d98b9b7b4e71f086bfb0d7851b4d78b3
|
||||
size 4756459720
|
||||
3
model-00015-of-00015.safetensors
Normal file
3
model-00015-of-00015.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:156bfbb84593ef1aa96e1f5724f55f2d8f45c5a8d31c77bee5389c6bff026328
|
||||
size 1211148848
|
||||
550
model.safetensors.index.json
Normal file
550
model.safetensors.index.json
Normal file
@@ -0,0 +1,550 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 68777834496
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00015-of-00015.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.40.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.40.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.41.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.42.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.42.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.42.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.42.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.42.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.42.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.43.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.43.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.44.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.45.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.46.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.46.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.46.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.46.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.46.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.46.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.47.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.47.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.48.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.49.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.50.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.50.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.51.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.51.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.51.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.51.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.51.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.51.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.52.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.52.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.53.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.54.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.55.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.55.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.55.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.55.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.55.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.55.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.56.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.56.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.57.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.58.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.59.input_layernorm.weight": "model-00015-of-00015.safetensors",
|
||||
"model.layers.59.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
|
||||
"model.layers.59.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.59.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.59.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.59.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.norm.weight": "model-00015-of-00015.safetensors"
|
||||
}
|
||||
}
|
||||
30
special_tokens_map.json
Normal file
30
special_tokens_map.json
Normal file
@@ -0,0 +1,30 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"unk_token": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
3
tokenizer.json
Normal file
3
tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a9e5fa30ef0a3e3ddea94d7e16d0ef8dfa97cc31d869732c62a432a84e321fbd
|
||||
size 3560825
|
||||
3
tokenizer.model
Normal file
3
tokenizer.model
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:386c49cf943d71aa110361135338c50e38beeff0a66593480421f37b319e1a39
|
||||
size 1033105
|
||||
41
tokenizer_config.json
Normal file
41
tokenizer_config.json
Normal file
@@ -0,0 +1,41 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"add_eos_token": false,
|
||||
"added_tokens_decoder": {
|
||||
"0": {
|
||||
"content": "<unk>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"1": {
|
||||
"content": "<s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"2": {
|
||||
"content": "</s>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"bos_token": "<s>",
|
||||
"chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' ' + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "</s>",
|
||||
"legacy": true,
|
||||
"model_max_length": 200000,
|
||||
"pad_token": "<unk>",
|
||||
"sp_model_kwargs": {},
|
||||
"tokenizer_class": "LlamaTokenizer",
|
||||
"unk_token": "<unk>",
|
||||
"use_default_system_prompt": false
|
||||
}
|
||||
Reference in New Issue
Block a user