初始化项目,由ModelHub XC社区提供模型

Model: FinaPolat/phi-4_1K_induced_thinking_dpo_openED
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-04 15:26:53 +08:00
commit 72227796b8
16 changed files with 602573 additions and 0 deletions

35
.gitattributes vendored Normal file
View 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

21
README.md Normal file
View File

@@ -0,0 +1,21 @@
---
base_model: FinaPolat/phi-4_1K_induce_thinking_openED
tags:
- text-generation-inference
- transformers
- unsloth
- llama
license: apache-2.0
language:
- en
---
# Uploaded finetuned model
- **Developed by:** FinaPolat
- **License:** apache-2.0
- **Finetuned from model :** FinaPolat/phi-4_1K_induce_thinking_openED
This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)

1
chat_template.jinja Normal file
View File

@@ -0,0 +1 @@
{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}

32
config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 100257,
"torch_dtype": "bfloat16",
"eos_token_id": 100265,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 17920,
"max_position_embeddings": 16384,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 40,
"num_hidden_layers": 40,
"num_key_value_heads": 10,
"original_max_position_embeddings": 16384,
"pad_token_id": 100351,
"pretraining_tp": 1,
"rms_norm_eps": 1e-05,
"rope_scaling": null,
"rope_theta": 250000,
"tie_word_embeddings": false,
"unsloth_fixed": true,
"unsloth_version": "2026.3.10",
"use_cache": false,
"vocab_size": 100352
}

100001
merges.txt Normal file

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9a17de2123176b28d2a8f4bcf26ae4b37ab5264cea1ec31ce9817bc0109c1bb7
size 4933658528

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:938ddaadf3ba51e80b8e046e760fcded638d3a2015fe320bb10298cbd2fd3b93
size 4954693112

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:44f05322c582d0df588e85f648b3b010bdaf81cf94448e3eb70818f4ca388e7d
size 4902243992

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e81c63cd1af1c0be15a87ac63dae574c14aa42da5f05c5d0e79370306ef8b3b2
size 4954672440

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:8a1a9c171afa44a6ecec90c6a53c8b3aec135d822bcd8536773a33af65c9b956
size 4954672432

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ef3587d311a207a24d21d143a47ec73a541e2b3d8b5a8fc007a2b9f92083dd05
size 4619116224

View File

@@ -0,0 +1,370 @@
{
"metadata": {
"total_size": 29319014400
},
"weight_map": {
"lm_head.weight": "model-00006-of-00006.safetensors",
"model.embed_tokens.weight": "model-00001-of-00006.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.13.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.20.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.21.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.27.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.28.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.30.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.34.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.35.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.36.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.36.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.36.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.37.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.37.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.37.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.38.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.38.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.38.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.39.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.39.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.39.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00006.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00006.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00006.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00006.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00006.safetensors",
"model.norm.weight": "model-00006-of-00006.safetensors"
}
}

30
special_tokens_map.json Normal file
View File

@@ -0,0 +1,30 @@
{
"bos_token": {
"content": "<|endoftext|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false
},
"eos_token": {
"content": "<|im_end|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false
},
"pad_token": {
"content": "<|dummy_87|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false
},
"unk_token": {
"content": "�",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

501273
tokenizer.json Normal file

File diff suppressed because it is too large Load Diff

791
tokenizer_config.json Normal file
View File

@@ -0,0 +1,791 @@
{
"add_prefix_space": false,
"added_tokens_decoder": {
"5809": {
"content": "�",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"100256": {
"content": "<|dummy_0|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100257": {
"content": "<|endoftext|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100258": {
"content": "<|fim_prefix|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100259": {
"content": "<|fim_middle|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100260": {
"content": "<|fim_suffix|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100261": {
"content": "<|dummy_1|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100262": {
"content": "<|dummy_2|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100263": {
"content": "<|dummy_3|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100264": {
"content": "<|im_start|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100265": {
"content": "<|im_end|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100266": {
"content": "<|im_sep|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100267": {
"content": "<|dummy_4|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100268": {
"content": "<|dummy_5|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100269": {
"content": "<|dummy_6|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100270": {
"content": "<|dummy_7|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100271": {
"content": "<|dummy_8|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100272": {
"content": "<|dummy_9|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100273": {
"content": "<|dummy_10|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100274": {
"content": "<|dummy_11|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100275": {
"content": "<|dummy_12|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100276": {
"content": "<|endofprompt|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100277": {
"content": "<|dummy_13|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100278": {
"content": "<|dummy_14|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100279": {
"content": "<|dummy_15|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100280": {
"content": "<|dummy_16|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100281": {
"content": "<|dummy_17|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100282": {
"content": "<|dummy_18|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100283": {
"content": "<|dummy_19|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100284": {
"content": "<|dummy_20|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100285": {
"content": "<|dummy_21|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100286": {
"content": "<|dummy_22|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100287": {
"content": "<|dummy_23|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100288": {
"content": "<|dummy_24|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100289": {
"content": "<|dummy_25|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100290": {
"content": "<|dummy_26|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100291": {
"content": "<|dummy_27|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100292": {
"content": "<|dummy_28|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100293": {
"content": "<|dummy_29|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100294": {
"content": "<|dummy_30|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100295": {
"content": "<|dummy_31|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100296": {
"content": "<|dummy_32|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100297": {
"content": "<|dummy_33|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100298": {
"content": "<|dummy_34|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100299": {
"content": "<|dummy_35|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100300": {
"content": "<|dummy_36|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100301": {
"content": "<|dummy_37|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100302": {
"content": "<|dummy_38|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100303": {
"content": "<|dummy_39|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100304": {
"content": "<|dummy_40|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100305": {
"content": "<|dummy_41|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100306": {
"content": "<|dummy_42|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100307": {
"content": "<|dummy_43|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100308": {
"content": "<|dummy_44|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100309": {
"content": "<|dummy_45|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100310": {
"content": "<|dummy_46|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100311": {
"content": "<|dummy_47|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100312": {
"content": "<|dummy_48|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100313": {
"content": "<|dummy_49|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100314": {
"content": "<|dummy_50|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100315": {
"content": "<|dummy_51|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100316": {
"content": "<|dummy_52|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100317": {
"content": "<|dummy_53|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100318": {
"content": "<|dummy_54|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100319": {
"content": "<|dummy_55|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100320": {
"content": "<|dummy_56|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100321": {
"content": "<|dummy_57|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100322": {
"content": "<|dummy_58|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100323": {
"content": "<|dummy_59|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100324": {
"content": "<|dummy_60|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100325": {
"content": "<|dummy_61|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100326": {
"content": "<|dummy_62|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100327": {
"content": "<|dummy_63|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100328": {
"content": "<|dummy_64|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100329": {
"content": "<|dummy_65|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100330": {
"content": "<|dummy_66|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100331": {
"content": "<|dummy_67|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100332": {
"content": "<|dummy_68|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100333": {
"content": "<|dummy_69|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100334": {
"content": "<|dummy_70|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100335": {
"content": "<|dummy_71|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100336": {
"content": "<|dummy_72|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100337": {
"content": "<|dummy_73|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100338": {
"content": "<|dummy_74|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100339": {
"content": "<|dummy_75|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100340": {
"content": "<|dummy_76|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100341": {
"content": "<|dummy_77|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100342": {
"content": "<|dummy_78|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100343": {
"content": "<|dummy_79|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100344": {
"content": "<|dummy_80|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100345": {
"content": "<|dummy_81|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100346": {
"content": "<|dummy_82|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100347": {
"content": "<|dummy_83|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100348": {
"content": "<|dummy_84|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100349": {
"content": "<|dummy_85|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100350": {
"content": "<|dummy_86|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
},
"100351": {
"content": "<|dummy_87|>",
"lstrip": true,
"normalized": false,
"rstrip": true,
"single_word": false,
"special": true
}
},
"bos_token": "<|endoftext|>",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"extra_special_tokens": {},
"model_max_length": 16384,
"pad_token": "<|dummy_87|>",
"padding_side": "left",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "�",
"chat_template": "{% for message in messages %}{% if (message['role'] == 'system') %}{{'<|im_start|>system<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'user') %}{{'<|im_start|>user<|im_sep|>' + message['content'] + '<|im_end|>'}}{% elif (message['role'] == 'assistant') %}{{'<|im_start|>assistant<|im_sep|>' + message['content'] + '<|im_end|>'}}{% endif %}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant<|im_sep|>' }}{% endif %}"
}

1
vocab.json Normal file

File diff suppressed because one or more lines are too long