初始化项目，由ModelHub XC社区提供模型
Model: Orion-zhen/Qwen2.5-7B-Gutenberg-KTO 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
|
||||
48
README.md
Normal file
48
README.md
Normal file
@@ -0,0 +1,48 @@
|
||||
---
|
||||
license: gpl-3.0
|
||||
datasets:
|
||||
- Orion-zhen/kto-gutenberg
|
||||
language:
|
||||
- zh
|
||||
- en
|
||||
base_model:
|
||||
- Orion-zhen/Qwen2.5-7B-Instruct-Uncensored
|
||||
pipeline_tag: text-generation
|
||||
---
|
||||
|
||||
# Qwen2.5-7B-Gutenberg-KTO
|
||||
|
||||
This model is fine tuned over gutenberg datasets using kto strategy. It's my first time to use kto strategy, and I'm not sure how the model actually performs.
|
||||
|
||||
Compared to those large companies which remove accessories such as charger and cables from packages, I have achieved **real** environment protection by **truly** reducing energy consumption, rather than shifting costs to consumers.
|
||||
|
||||
Checkout GGUF here: [Orion-zhen/Qwen2.5-7B-Gutenberg-KTO-Q6_K-GGUF](https://huggingface.co/Orion-zhen/Qwen2.5-7B-Gutenberg-KTO-Q6_K-GGUF)
|
||||
|
||||
## Details
|
||||
|
||||
### Platform
|
||||
|
||||
~~I randomly grabbed some rubbish from a second-hand market and built a PC~~
|
||||
|
||||
I carefully selected various dedicated hardwares and constructed an incomparable home server, which I entitled the **Great Server**:
|
||||
|
||||
- CPU: Intel Core i3-4160
|
||||
- Memory: 8G DDR3, single channel
|
||||
- GPU: Tesla P4, TDP 75W, boasting its **Eco friendly energy consumption**
|
||||
- Disk: 1TB M.2 NVME, PCIe 4.0
|
||||
|
||||
### Training
|
||||
|
||||
To practice the **eco-friendly training**, I utilized various methods, including adam-mini, qlora and unsloth, to minimize VRAM and energy usage, as well as accelerating training speed.
|
||||
|
||||
- dataset: [Orion-zhen/kto-gutenberg](https://huggingface.co/datasets/Orion-zhen/kto-gutenberg)
|
||||
- epoch: 2
|
||||
- gradient accumulation: 8
|
||||
- batch size: 1
|
||||
- KTO perf beta: 0.1
|
||||
|
||||
### Train log
|
||||
|
||||
|
||||
|
||||
|
||||
24
added_tokens.json
Normal file
24
added_tokens.json
Normal file
@@ -0,0 +1,24 @@
|
||||
{
|
||||
"</tool_call>": 151658,
|
||||
"<tool_call>": 151657,
|
||||
"<|box_end|>": 151649,
|
||||
"<|box_start|>": 151648,
|
||||
"<|endoftext|>": 151643,
|
||||
"<|file_sep|>": 151664,
|
||||
"<|fim_middle|>": 151660,
|
||||
"<|fim_pad|>": 151662,
|
||||
"<|fim_prefix|>": 151659,
|
||||
"<|fim_suffix|>": 151661,
|
||||
"<|im_end|>": 151645,
|
||||
"<|im_start|>": 151644,
|
||||
"<|image_pad|>": 151655,
|
||||
"<|object_ref_end|>": 151647,
|
||||
"<|object_ref_start|>": 151646,
|
||||
"<|quad_end|>": 151651,
|
||||
"<|quad_start|>": 151650,
|
||||
"<|repo_name|>": 151663,
|
||||
"<|video_pad|>": 151656,
|
||||
"<|vision_end|>": 151653,
|
||||
"<|vision_pad|>": 151654,
|
||||
"<|vision_start|>": 151652
|
||||
}
|
||||
29
config.json
Normal file
29
config.json
Normal file
@@ -0,0 +1,29 @@
|
||||
{
|
||||
"_name_or_path": "/home/orion/ai/Models/qwen2.5-7b",
|
||||
"architectures": [
|
||||
"Qwen2ForCausalLM"
|
||||
],
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 151643,
|
||||
"eos_token_id": 151645,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 3584,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 18944,
|
||||
"max_position_embeddings": 32768,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen2",
|
||||
"num_attention_heads": 28,
|
||||
"num_hidden_layers": 28,
|
||||
"num_key_value_heads": 4,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_scaling": null,
|
||||
"rope_theta": 1000000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.45.2",
|
||||
"use_cache": true,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 152064
|
||||
}
|
||||
14
generation_config.json
Normal file
14
generation_config.json
Normal file
@@ -0,0 +1,14 @@
|
||||
{
|
||||
"bos_token_id": 151643,
|
||||
"do_sample": true,
|
||||
"eos_token_id": [
|
||||
151645,
|
||||
151643
|
||||
],
|
||||
"pad_token_id": 151643,
|
||||
"repetition_penalty": 1.05,
|
||||
"temperature": 0.7,
|
||||
"top_k": 20,
|
||||
"top_p": 0.8,
|
||||
"transformers_version": "4.45.2"
|
||||
}
|
||||
151388
merges.txt
Normal file
151388
merges.txt
Normal file
File diff suppressed because it is too large
Load Diff
3
model-00001-of-00016.safetensors
Normal file
3
model-00001-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:f7750ef811855400eaf0017804c4c12081ba254debbfcf4a3235384784c5a429
|
||||
size 1089994896
|
||||
3
model-00002-of-00016.safetensors
Normal file
3
model-00002-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a7419815472cb85d05f2723eb95ad8aad916e2549c6cf653adb2af2cf8751773
|
||||
size 990964136
|
||||
3
model-00003-of-00016.safetensors
Normal file
3
model-00003-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:cf1641b1ce049be2460c0f67c0733542f8df6f445a5850448fcdce343cd74134
|
||||
size 932233880
|
||||
3
model-00004-of-00016.safetensors
Normal file
3
model-00004-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:edb3d6ddb636ed8f040e0a5525b748ddb24c15d726f2093cb6abd9e1e90d6bb6
|
||||
size 932233880
|
||||
3
model-00005-of-00016.safetensors
Normal file
3
model-00005-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b5ea9f823b1bab751ca9d31b48763743e3f4dd8c2974e3e60ee410263cd5982c
|
||||
size 932233880
|
||||
3
model-00006-of-00016.safetensors
Normal file
3
model-00006-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:aea2eb8e4028d8ae7c145483f6f17bac6f9f98a9f0403a60b43d8ca6e0821a60
|
||||
size 932233872
|
||||
3
model-00007-of-00016.safetensors
Normal file
3
model-00007-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:77f20f1747dec3eafb97db1e34cd8967461a21c5aa76fa934ece5c80a3d6cc4e
|
||||
size 932233904
|
||||
3
model-00008-of-00016.safetensors
Normal file
3
model-00008-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b0766cc585b7b5b78b1b780bf755bae2f2622417ee0b003030586b815e20a5e9
|
||||
size 932233904
|
||||
3
model-00009-of-00016.safetensors
Normal file
3
model-00009-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:b75f5326d12b18a490a98d688c49da0d19d1ff1d27680d8d1c5a47785cc71a11
|
||||
size 932233904
|
||||
3
model-00010-of-00016.safetensors
Normal file
3
model-00010-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:209176ae1762be29a3e7ddf2596a7e0fd4362ae9ccbae811d4ff4dae35866cc3
|
||||
size 932233904
|
||||
3
model-00011-of-00016.safetensors
Normal file
3
model-00011-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9e417f9701f4875ea80ea02d1761c0f30a76be1f3b38afdc3118d2def8c16d2b
|
||||
size 932233904
|
||||
3
model-00012-of-00016.safetensors
Normal file
3
model-00012-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:c7284b5e252ca3c6c0b7ea9b4572f28ca23d9ff0df3747212f4e86f65627170c
|
||||
size 932233904
|
||||
3
model-00013-of-00016.safetensors
Normal file
3
model-00013-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6398e524bfe50316c282770f0bfef7ece499a8193bd2aa0e463253c6382098d5
|
||||
size 932233904
|
||||
3
model-00014-of-00016.safetensors
Normal file
3
model-00014-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:27365195d57d4325424741992b07269f8df93589ce038808f87ae2a0152c283f
|
||||
size 932233904
|
||||
3
model-00015-of-00016.safetensors
Normal file
3
model-00015-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:06006972c3be88e8a44fe21cfe2b0472b130780c781a741f8f90f1fe5ba3aae2
|
||||
size 1089994880
|
||||
3
model-00016-of-00016.safetensors
Normal file
3
model-00016-of-00016.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a077bf080912c640677d8a302387ceea083c29283ebbced2e98cec68b38cb5f7
|
||||
size 873510904
|
||||
346
model.safetensors.index.json
Normal file
346
model.safetensors.index.json
Normal file
@@ -0,0 +1,346 @@
|
||||
{
|
||||
"metadata": {
|
||||
"total_size": 15231233024
|
||||
},
|
||||
"weight_map": {
|
||||
"lm_head.weight": "model-00015-of-00016.safetensors",
|
||||
"model.embed_tokens.weight": "model-00001-of-00016.safetensors",
|
||||
"model.layers.0.input_layernorm.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.0.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.0.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.0.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.0.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
|
||||
"model.layers.0.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.1.input_layernorm.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.1.mlp.down_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.1.mlp.gate_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.1.mlp.up_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.1.post_attention_layernorm.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
|
||||
"model.layers.1.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.10.input_layernorm.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.10.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.10.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.10.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.10.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
|
||||
"model.layers.10.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.11.input_layernorm.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.11.mlp.down_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.11.mlp.gate_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.11.mlp.up_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.11.post_attention_layernorm.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
|
||||
"model.layers.11.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.12.input_layernorm.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.12.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.12.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.12.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.12.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.bias": "model-00007-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.k_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.o_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.bias": "model-00007-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.q_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.bias": "model-00007-of-00016.safetensors",
|
||||
"model.layers.12.self_attn.v_proj.weight": "model-00007-of-00016.safetensors",
|
||||
"model.layers.13.input_layernorm.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.13.mlp.down_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.13.mlp.gate_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.13.mlp.up_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.13.post_attention_layernorm.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
|
||||
"model.layers.13.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.14.input_layernorm.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.14.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.14.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.14.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.14.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.bias": "model-00008-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.k_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.o_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.bias": "model-00008-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.q_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.bias": "model-00008-of-00016.safetensors",
|
||||
"model.layers.14.self_attn.v_proj.weight": "model-00008-of-00016.safetensors",
|
||||
"model.layers.15.input_layernorm.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.15.mlp.down_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.15.mlp.gate_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.15.mlp.up_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.15.post_attention_layernorm.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
|
||||
"model.layers.15.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.16.input_layernorm.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.16.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.16.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.16.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.16.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.bias": "model-00009-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.k_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.o_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.bias": "model-00009-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.q_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.bias": "model-00009-of-00016.safetensors",
|
||||
"model.layers.16.self_attn.v_proj.weight": "model-00009-of-00016.safetensors",
|
||||
"model.layers.17.input_layernorm.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.17.mlp.down_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.17.mlp.gate_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.17.mlp.up_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.17.post_attention_layernorm.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
|
||||
"model.layers.17.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.18.input_layernorm.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.18.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.18.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.18.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.18.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.bias": "model-00010-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.k_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.o_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.bias": "model-00010-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.q_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.bias": "model-00010-of-00016.safetensors",
|
||||
"model.layers.18.self_attn.v_proj.weight": "model-00010-of-00016.safetensors",
|
||||
"model.layers.19.input_layernorm.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.19.mlp.down_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.19.mlp.gate_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.19.mlp.up_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.19.post_attention_layernorm.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
|
||||
"model.layers.19.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.2.input_layernorm.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.2.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.2.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.2.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.2.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.bias": "model-00002-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.k_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.o_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.bias": "model-00002-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.q_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.bias": "model-00002-of-00016.safetensors",
|
||||
"model.layers.2.self_attn.v_proj.weight": "model-00002-of-00016.safetensors",
|
||||
"model.layers.20.input_layernorm.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.20.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.20.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.20.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.20.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.bias": "model-00011-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.k_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.o_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.bias": "model-00011-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.q_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.bias": "model-00011-of-00016.safetensors",
|
||||
"model.layers.20.self_attn.v_proj.weight": "model-00011-of-00016.safetensors",
|
||||
"model.layers.21.input_layernorm.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.21.mlp.down_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.21.mlp.gate_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.21.mlp.up_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.21.post_attention_layernorm.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
|
||||
"model.layers.21.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.22.input_layernorm.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.22.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.22.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.22.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.22.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.bias": "model-00012-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.k_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.o_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.bias": "model-00012-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.q_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.bias": "model-00012-of-00016.safetensors",
|
||||
"model.layers.22.self_attn.v_proj.weight": "model-00012-of-00016.safetensors",
|
||||
"model.layers.23.input_layernorm.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.23.mlp.down_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.23.mlp.gate_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.23.mlp.up_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.23.post_attention_layernorm.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
|
||||
"model.layers.23.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.24.input_layernorm.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.24.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.24.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.24.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.24.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.bias": "model-00013-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.k_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.o_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.bias": "model-00013-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.q_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.bias": "model-00013-of-00016.safetensors",
|
||||
"model.layers.24.self_attn.v_proj.weight": "model-00013-of-00016.safetensors",
|
||||
"model.layers.25.input_layernorm.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.25.mlp.down_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.25.mlp.gate_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.25.mlp.up_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.25.post_attention_layernorm.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
|
||||
"model.layers.25.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.26.input_layernorm.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.mlp.down_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.mlp.gate_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.mlp.up_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.post_attention_layernorm.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.bias": "model-00014-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.k_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.o_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.bias": "model-00014-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.q_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.bias": "model-00014-of-00016.safetensors",
|
||||
"model.layers.26.self_attn.v_proj.weight": "model-00014-of-00016.safetensors",
|
||||
"model.layers.27.input_layernorm.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.mlp.down_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.mlp.gate_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.mlp.up_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.post_attention_layernorm.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.bias": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.k_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.o_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.bias": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.q_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.bias": "model-00016-of-00016.safetensors",
|
||||
"model.layers.27.self_attn.v_proj.weight": "model-00016-of-00016.safetensors",
|
||||
"model.layers.3.input_layernorm.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.3.mlp.down_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.3.mlp.gate_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.3.mlp.up_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.3.post_attention_layernorm.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
|
||||
"model.layers.3.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.4.input_layernorm.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.4.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.4.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.4.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.4.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.bias": "model-00003-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.k_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.o_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.bias": "model-00003-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.q_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.bias": "model-00003-of-00016.safetensors",
|
||||
"model.layers.4.self_attn.v_proj.weight": "model-00003-of-00016.safetensors",
|
||||
"model.layers.5.input_layernorm.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.5.mlp.down_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.5.mlp.gate_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.5.mlp.up_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.5.post_attention_layernorm.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
|
||||
"model.layers.5.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.6.input_layernorm.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.6.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.6.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.6.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.6.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.bias": "model-00004-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.k_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.o_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.bias": "model-00004-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.q_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.bias": "model-00004-of-00016.safetensors",
|
||||
"model.layers.6.self_attn.v_proj.weight": "model-00004-of-00016.safetensors",
|
||||
"model.layers.7.input_layernorm.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.7.mlp.down_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.7.mlp.gate_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.7.mlp.up_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.7.post_attention_layernorm.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
|
||||
"model.layers.7.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.8.input_layernorm.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.8.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.8.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.8.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.8.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.bias": "model-00005-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.k_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.o_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.bias": "model-00005-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.q_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.bias": "model-00005-of-00016.safetensors",
|
||||
"model.layers.8.self_attn.v_proj.weight": "model-00005-of-00016.safetensors",
|
||||
"model.layers.9.input_layernorm.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.9.mlp.down_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.9.mlp.gate_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.9.mlp.up_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.9.post_attention_layernorm.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.bias": "model-00006-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.k_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.o_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.bias": "model-00006-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.q_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.bias": "model-00006-of-00016.safetensors",
|
||||
"model.layers.9.self_attn.v_proj.weight": "model-00006-of-00016.safetensors",
|
||||
"model.norm.weight": "model-00016-of-00016.safetensors"
|
||||
}
|
||||
}
|
||||
31
special_tokens_map.json
Normal file
31
special_tokens_map.json
Normal file
@@ -0,0 +1,31 @@
|
||||
{
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"eos_token": {
|
||||
"content": "<|im_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|endoftext|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
303283
tokenizer.json
Normal file
303283
tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
207
tokenizer_config.json
Normal file
207
tokenizer_config.json
Normal file
@@ -0,0 +1,207 @@
|
||||
{
|
||||
"add_bos_token": false,
|
||||
"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
|
||||
},
|
||||
"151646": {
|
||||
"content": "<|object_ref_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151647": {
|
||||
"content": "<|object_ref_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151648": {
|
||||
"content": "<|box_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151649": {
|
||||
"content": "<|box_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151650": {
|
||||
"content": "<|quad_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151651": {
|
||||
"content": "<|quad_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151652": {
|
||||
"content": "<|vision_start|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151653": {
|
||||
"content": "<|vision_end|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151654": {
|
||||
"content": "<|vision_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151655": {
|
||||
"content": "<|image_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151656": {
|
||||
"content": "<|video_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": true
|
||||
},
|
||||
"151657": {
|
||||
"content": "<tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151658": {
|
||||
"content": "</tool_call>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151659": {
|
||||
"content": "<|fim_prefix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151660": {
|
||||
"content": "<|fim_middle|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151661": {
|
||||
"content": "<|fim_suffix|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151662": {
|
||||
"content": "<|fim_pad|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151663": {
|
||||
"content": "<|repo_name|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
},
|
||||
"151664": {
|
||||
"content": "<|file_sep|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false,
|
||||
"special": false
|
||||
}
|
||||
},
|
||||
"additional_special_tokens": [
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<|object_ref_start|>",
|
||||
"<|object_ref_end|>",
|
||||
"<|box_start|>",
|
||||
"<|box_end|>",
|
||||
"<|quad_start|>",
|
||||
"<|quad_end|>",
|
||||
"<|vision_start|>",
|
||||
"<|vision_end|>",
|
||||
"<|vision_pad|>",
|
||||
"<|image_pad|>",
|
||||
"<|video_pad|>"
|
||||
],
|
||||
"bos_token": null,
|
||||
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|im_end|>",
|
||||
"errors": "replace",
|
||||
"model_max_length": 131072,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"split_special_tokens": false,
|
||||
"tokenizer_class": "Qwen2Tokenizer",
|
||||
"unk_token": null
|
||||
}
|
||||
BIN
training_eval_loss.png
Normal file
BIN
training_eval_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 34 KiB |
BIN
training_loss.png
Normal file
BIN
training_loss.png
Normal file
Binary file not shown.
|
After Width: | Height: | Size: 58 KiB |
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