初始化项目，由ModelHub XC社区提供模型
Model: M4-ai/Hercules-Qwen1.5-14B 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
|
||||
163
README.md
Normal file
163
README.md
Normal file
@@ -0,0 +1,163 @@
|
||||
---
|
||||
library_name: transformers
|
||||
license: other
|
||||
datasets:
|
||||
- Locutusque/hercules-v4.0
|
||||
language:
|
||||
- en
|
||||
---
|
||||
|
||||
<style>
|
||||
body {
|
||||
font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
|
||||
line-height: 1.6;
|
||||
color: #f5f5f5;
|
||||
background-color: #1e2a36;
|
||||
margin: 0;
|
||||
padding: 0;
|
||||
}
|
||||
|
||||
.container {
|
||||
max-width: 1200px;
|
||||
margin: 20px auto;
|
||||
padding: 20px;
|
||||
background-color: #2a3f54;
|
||||
border-radius: 8px;
|
||||
box-shadow: 0 4px 8px rgba(0, 0, 0, 0.1);
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
justify-content: space-between;
|
||||
}
|
||||
|
||||
h1 {
|
||||
font-size: 2.5rem;
|
||||
color: #51a3d3;
|
||||
text-align: center;
|
||||
margin-bottom: 30px;
|
||||
width: 100%;
|
||||
}
|
||||
|
||||
h2 {
|
||||
font-size: 1.75rem;
|
||||
margin: 20px 0;
|
||||
color: #63b8ea;
|
||||
padding-bottom: 10px;
|
||||
}
|
||||
|
||||
h3 {
|
||||
font-size: 1.25rem;
|
||||
color: #80c8f4;
|
||||
}
|
||||
|
||||
p, a {
|
||||
font-size: 1rem;
|
||||
}
|
||||
|
||||
p {
|
||||
color: #b0c2ce;
|
||||
margin-bottom: 20px;
|
||||
}
|
||||
|
||||
ul {
|
||||
list-style-type: none;
|
||||
padding: 0;
|
||||
display: flex;
|
||||
flex-wrap: wrap;
|
||||
justify-content: space-between;
|
||||
width: 100%;
|
||||
}
|
||||
|
||||
li {
|
||||
background-color: #34495e;
|
||||
padding: 20px;
|
||||
margin-bottom: 10px;
|
||||
border-radius: 4px;
|
||||
cursor: pointer;
|
||||
transition: background-color 0.3s ease, color 0.3s ease;
|
||||
overflow: hidden;
|
||||
color: #b0c2ce;
|
||||
width: calc(50% - 10px);
|
||||
box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
|
||||
}
|
||||
|
||||
li:hover {
|
||||
background-color: #4e6a81;
|
||||
color: #dfe8f1;
|
||||
}
|
||||
|
||||
.section-content {
|
||||
margin-top: 15px;
|
||||
border-top: 1px solid #4e6a81;
|
||||
padding-top: 10px;
|
||||
}
|
||||
|
||||
a {
|
||||
color: #a4c8e1;
|
||||
text-decoration: none;
|
||||
}
|
||||
|
||||
a:hover {
|
||||
text-decoration: underline;
|
||||
}
|
||||
|
||||
pre {
|
||||
background-color: #2c3e50;
|
||||
padding: 10px;
|
||||
border-radius: 5px;
|
||||
overflow-x: auto;
|
||||
color: #b0c2ce;
|
||||
}
|
||||
</style>
|
||||
<div class="container">
|
||||
<h1>Hercules-Qwen1.5-14B</h1>
|
||||
</div>
|
||||
|
||||
<ul>
|
||||
<li>
|
||||
<h2>Model Details</h2>
|
||||
<div class="section-content">
|
||||
<h3>Model Description</h3>
|
||||
<p>This model has capabilities in math, coding, function calling, roleplay, and more. We fine-tuned it using 700,000 examples of Hercules-v4.</p>
|
||||
<p><strong>Developed by:</strong> M4-ai</p>
|
||||
<p><strong>Language(s) (NLP):</strong> English and maybe Chinese</p>
|
||||
<p><strong>License:</strong> tongyi-qianwen license</p>
|
||||
<p><strong>Finetuned from model:</strong> <a href="https://huggingface.co/Qwen/Qwen1.5-14B">Qwen1.5-14B</a></p>
|
||||
</div>
|
||||
</li>
|
||||
<li>
|
||||
<h2>Uses</h2>
|
||||
<div class="section-content">
|
||||
<p>General purpose assistant, question answering, chain-of-thought, etc..</p>
|
||||
<h3>Recommendations</h3>
|
||||
<p>Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.</p>
|
||||
</div>
|
||||
</li>
|
||||
<li>
|
||||
<h2>Evaluation</h2>
|
||||
<div class="section-content">
|
||||
<p>Coming soon</p>
|
||||
</div>
|
||||
</li>
|
||||
<li>
|
||||
<h2>Training Details</h2>
|
||||
<div class="section-content">
|
||||
<h3>Training Data</h3>
|
||||
<p><a href="https://huggingface.co/datasets/Locutusque/hercules-v4.0">https://huggingface.co/datasets/Locutusque/hercules-v4.0</a></p>
|
||||
<h4>Training Hyperparameters</h4>
|
||||
<p><strong>Training regime:</strong> bf16 non-mixed precision</p>
|
||||
</div>
|
||||
</li>
|
||||
<li>
|
||||
<h2>Technical Specifications</h2>
|
||||
<div class="section-content">
|
||||
<h4>Hardware</h4>
|
||||
<p>We used 8 Kaggle TPUs, and we trained at a global batch size of 128 and sequence length of 1024</p>
|
||||
</div>
|
||||
</li>
|
||||
<li>
|
||||
<h2>Contributions</h2>
|
||||
<div class="section-content">
|
||||
<p>Thanks to @Tonic, @aloobun, @fhai50032, and @Locutusque for their contributions to this model.</p>
|
||||
</div>
|
||||
</li>
|
||||
</ul>
|
||||
5
added_tokens.json
Normal file
5
added_tokens.json
Normal file
@@ -0,0 +1,5 @@
|
||||
{
|
||||
"<|endoftext|>": 151643,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644
|
||||
}
|
||||
28
config.json
Normal file
28
config.json
Normal file
@@ -0,0 +1,28 @@
|
||||
{
|
||||
"_name_or_path": "Qwen/Qwen1.5-14B",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 5120,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 13696,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 35,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 40,
|
||||
"num_hidden_layers": 40,
|
||||
"num_key_value_heads": 40,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": 32768,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.39.2",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
6
generation_config.json
Normal file
6
generation_config.json
Normal file
@@ -0,0 +1,6 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151643,
|
||||
"max_new_tokens": 2048,
|
||||
"transformers_version": "4.39.2"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
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:fbe1978ae36f254b7e4b0e444ff239db1e2ff8bec9a77da59e0d3300349bfb3f
|
||||
size 1907129376
|
||||
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 sha256:7ee58d7e927f853cd30155f7e07a0fb6d936e972969a72ee5e647ca79a3829e5
|
||||
size 1891526672
|
||||
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:f47625dff4c7a04d5f5481c5c46307d29a764cd7c6fc95e33b7b394eb52efff8
|
||||
size 1891526672
|
||||
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 sha256:2426eff3954f34f2ec41f17619015050471533c790e118163094f35b67b101df
|
||||
size 1891526672
|
||||
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 sha256:6079fed40ae8d25ffcc01e994eb8dd93183be9362272a0b20696179a5d716ea5
|
||||
size 1891526704
|
||||
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:a407752c9bf47caf53552b080ae95d7d9d4c8b564d66c64cfc9fc72a2b78dbcc
|
||||
size 1891526704
|
||||
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 sha256:668151b1a050427ac2fa201b1a897e61a075a32ca4b89db94f44b11cac5a228b
|
||||
size 1891526704
|
||||
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 sha256:2e66b51e171c764e0ffacb512947ebe578cf48fa2f8152a0b57393bf2ea68778
|
||||
size 1891526704
|
||||
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 sha256:2660bfbd9305c38061f52e3ed5c5c6751348452bb2a21bcdf168bae183f67994
|
||||
size 1891526704
|
||||
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:da69370401ca892c252286478703615c1c173a0e7bbd6e355c70cc66aeea2695
|
||||
size 1891526704
|
||||
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:d1278d03912736b6bd21d5c542b77ecbdafef49409c380782c6022a734676f2b
|
||||
size 1891526704
|
||||
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 sha256:5507bcc8fa585a9f514c82829e01d9ab751387710690a234858c378f3ec03065
|
||||
size 1891526704
|
||||
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 sha256:3f07dee79b3d433ad7aa23300b0f7312126462434dd257684c949d2c20b81921
|
||||
size 1891526704
|
||||
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 sha256:890ee14f7f8b66b2608a28e4755ccef71489002afa2fb22c220d1881458b65bc
|
||||
size 1891526704
|
||||
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 sha256:56231220b9b2ea8d63b19373d570f0b117f01e4c977f3a43a6be21ea3a7ff861
|
||||
size 1837660840
|
||||
490
model.safetensors.index.json
Normal file
490
model.safetensors.index.json
Normal file
@@ -0,0 +1,490 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 28334581760
|
||||
},
|
||||
"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-00002-of-00015.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00015.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "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.bias": "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.bias": "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-00002-of-00015.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00005-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00005-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00005-of-00015.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00006-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00006-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00006-of-00015.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00006-of-00015.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00007-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00007-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00007-of-00015.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00007-of-00015.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00008-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00008-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00008-of-00015.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00008-of-00015.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00009-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00009-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00009-of-00015.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00009-of-00015.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00010-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00010-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00010-of-00015.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00010-of-00015.safetensors",
|
||||
"model.layers.28.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.28.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.28.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.28.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.28.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
|
||||
"model.layers.28.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.29.input_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.29.mlp.down_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.29.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.29.mlp.up_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.29.post_attention_layernorm.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
|
||||
"model.layers.29.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00002-of-00015.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00002-of-00015.safetensors",
|
||||
"model.layers.30.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.30.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.30.mlp.gate_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.30.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.30.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.bias": "model-00011-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.k_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.o_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.bias": "model-00011-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.q_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.bias": "model-00011-of-00015.safetensors",
|
||||
"model.layers.30.self_attn.v_proj.weight": "model-00011-of-00015.safetensors",
|
||||
"model.layers.31.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.31.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.31.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.31.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.31.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
|
||||
"model.layers.31.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.32.input_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.32.mlp.down_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.32.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.32.mlp.up_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.32.post_attention_layernorm.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
|
||||
"model.layers.32.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.33.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.33.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.33.mlp.gate_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.33.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.33.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.bias": "model-00012-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.k_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.o_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.bias": "model-00012-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.q_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.bias": "model-00012-of-00015.safetensors",
|
||||
"model.layers.33.self_attn.v_proj.weight": "model-00012-of-00015.safetensors",
|
||||
"model.layers.34.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.34.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.34.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.34.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.34.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
|
||||
"model.layers.34.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.35.input_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.35.mlp.down_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.35.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.35.mlp.up_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.35.post_attention_layernorm.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
|
||||
"model.layers.35.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.36.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.36.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.36.mlp.gate_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.36.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.36.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.bias": "model-00013-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.k_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.o_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.bias": "model-00013-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.q_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.bias": "model-00013-of-00015.safetensors",
|
||||
"model.layers.36.self_attn.v_proj.weight": "model-00013-of-00015.safetensors",
|
||||
"model.layers.37.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.37.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.37.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.37.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.37.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
|
||||
"model.layers.37.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.38.input_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.38.mlp.down_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.38.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.38.mlp.up_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.38.post_attention_layernorm.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
|
||||
"model.layers.38.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.39.input_layernorm.weight": "model-00015-of-00015.safetensors",
|
||||
"model.layers.39.mlp.down_proj.weight": "model-00015-of-00015.safetensors",
|
||||
"model.layers.39.mlp.gate_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.39.mlp.up_proj.weight": "model-00015-of-00015.safetensors",
|
||||
"model.layers.39.post_attention_layernorm.weight": "model-00015-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.bias": "model-00014-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.k_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.o_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.bias": "model-00014-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.q_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.bias": "model-00014-of-00015.safetensors",
|
||||
"model.layers.39.self_attn.v_proj.weight": "model-00014-of-00015.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00003-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00003-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00003-of-00015.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00003-of-00015.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00005-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00004-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00004-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00004-of-00015.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00004-of-00015.safetensors",
|
||||
"model.norm.weight": "model-00015-of-00015.safetensors"
|
||||
}
|
||||
}
|
||||
14
special_tokens_map.json
Normal file
14
special_tokens_map.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|endoftext|>"
|
||||
}
|
||||
303125
tokenizer.json
Normal file
303125
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
43
tokenizer_config.json
Normal file
43
tokenizer_config.json
Normal file
@@ -0,0 +1,43 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"added_tokens_decoder": {
|
||||
"151643": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151644": {
|
||||
"content": "<|im_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151645": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 32768,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
1
vocab.json
Normal file
1
vocab.json
Normal file
File diff suppressed because one or more lines are too long
Reference in New Issue
Block a user