HenryJJ/Instruct_Mistral-7B-v0.1_Dolly15K
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: HenryJJ/Instruct_Mistral-7B-v0.1_Dolly15K
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-05-08 10:38:20 +08:00
commit f59bed5505
15 changed files with 91986 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

425
README.md Normal file
View File

@@ -0,0 +1,425 @@
---
license: apache-2.0
datasets:
- databricks/databricks-dolly-15k
---
# Instruct_Mixtral-7B-v0.1_Dolly15K
Fine-tuned from Mixtral-7B-v0.1， used Dolly15k for the dataset. 90% for training, 10% validation. Trained for 2.0 epochs using Lora. Trained with 1024 context window.
# Model Details
* **Trained by**: trained by HenryJJ.
* **Model type:** **Instruct_Mixtral-7B-v0.1_Dolly15K** is an auto-regressive language model based on the Llama 2 transformer architecture.
* **Language(s)**: English
* **License for Instruct_Mixtral-7B-v0.1_Dolly15K**: apache-2.0 license
# Prompting
## Prompt Template With Context
```
Write a 10-line poem about a given topic
Input:
The topic is about racecars
Output:
```
## Prompt Template Without Context
```
Who was the was the second president of the United States?
Output:
```
# Training script:
Fully opensourced at: https://github.com/hengjiUSTC/learn-llm/blob/main/trl_finetune.py.
## Latest results
These are the [latest results from run 2024-01-04T13:27:32.660899](https://huggingface.co/datasets/open-llm-leaderboard/details_HenryJJ__Instruct_Mistral-7B-v0.1_Dolly15K/blob/main/results_2024-01-04T13-27-32.660899.json)(note that their might be results for other tasks in the repos if successive evals didn't cover the same tasks. You find each in the results and the "latest" split for each eval):
```python
{
"all": {
"acc": 0.6241143484289186,
"acc_stderr": 0.032689663124831826,
"acc_norm": 0.6299031400315822,
"acc_norm_stderr": 0.033361474961048916,
"mc1": 0.2802937576499388,
"mc1_stderr": 0.015723139524608767,
"mc2": 0.435601924823795,
"mc2_stderr": 0.014179199089974604
},
"harness|arc:challenge|25": {
"acc": 0.5571672354948806,
"acc_stderr": 0.014515573873348906,
"acc_norm": 0.5938566552901023,
"acc_norm_stderr": 0.014351656690097862
},
"harness|hellaswag|10": {
"acc": 0.6253734315873332,
"acc_stderr": 0.004830371317841054,
"acc_norm": 0.826229834694284,
"acc_norm_stderr": 0.00378137335887
},
"harness|hendrycksTest-abstract_algebra|5": {
"acc": 0.31,
"acc_stderr": 0.04648231987117316,
"acc_norm": 0.31,
"acc_norm_stderr": 0.04648231987117316
},
"harness|hendrycksTest-anatomy|5": {
"acc": 0.6148148148148148,
"acc_stderr": 0.04203921040156279,
"acc_norm": 0.6148148148148148,
"acc_norm_stderr": 0.04203921040156279
},
"harness|hendrycksTest-astronomy|5": {
"acc": 0.6513157894736842,
"acc_stderr": 0.03878139888797611,
"acc_norm": 0.6513157894736842,
"acc_norm_stderr": 0.03878139888797611
},
"harness|hendrycksTest-business_ethics|5": {
"acc": 0.57,
"acc_stderr": 0.04975698519562428,
"acc_norm": 0.57,
"acc_norm_stderr": 0.04975698519562428
},
"harness|hendrycksTest-clinical_knowledge|5": {
"acc": 0.660377358490566,
"acc_stderr": 0.029146904747798328,
"acc_norm": 0.660377358490566,
"acc_norm_stderr": 0.029146904747798328
},
"harness|hendrycksTest-college_biology|5": {
"acc": 0.7291666666666666,
"acc_stderr": 0.03716177437566017,
"acc_norm": 0.7291666666666666,
"acc_norm_stderr": 0.03716177437566017
},
"harness|hendrycksTest-college_chemistry|5": {
"acc": 0.46,
"acc_stderr": 0.05009082659620332,
"acc_norm": 0.46,
"acc_norm_stderr": 0.05009082659620332
},
"harness|hendrycksTest-college_computer_science|5": {
"acc": 0.54,
"acc_stderr": 0.05009082659620333,
"acc_norm": 0.54,
"acc_norm_stderr": 0.05009082659620333
},
"harness|hendrycksTest-college_mathematics|5": {
"acc": 0.38,
"acc_stderr": 0.04878317312145632,
"acc_norm": 0.38,
"acc_norm_stderr": 0.04878317312145632
},
"harness|hendrycksTest-college_medicine|5": {
"acc": 0.5838150289017341,
"acc_stderr": 0.03758517775404947,
"acc_norm": 0.5838150289017341,
"acc_norm_stderr": 0.03758517775404947
},
"harness|hendrycksTest-college_physics|5": {
"acc": 0.35294117647058826,
"acc_stderr": 0.04755129616062946,
"acc_norm": 0.35294117647058826,
"acc_norm_stderr": 0.04755129616062946
},
"harness|hendrycksTest-computer_security|5": {
"acc": 0.77,
"acc_stderr": 0.04229525846816505,
"acc_norm": 0.77,
"acc_norm_stderr": 0.04229525846816505
},
"harness|hendrycksTest-conceptual_physics|5": {
"acc": 0.5574468085106383,
"acc_stderr": 0.032469569197899575,
"acc_norm": 0.5574468085106383,
"acc_norm_stderr": 0.032469569197899575
},
"harness|hendrycksTest-econometrics|5": {
"acc": 0.5,
"acc_stderr": 0.047036043419179864,
"acc_norm": 0.5,
"acc_norm_stderr": 0.047036043419179864
},
"harness|hendrycksTest-electrical_engineering|5": {
"acc": 0.5724137931034483,
"acc_stderr": 0.041227371113703316,
"acc_norm": 0.5724137931034483,
"acc_norm_stderr": 0.041227371113703316
},
"harness|hendrycksTest-elementary_mathematics|5": {
"acc": 0.3994708994708995,
"acc_stderr": 0.02522545028406788,
"acc_norm": 0.3994708994708995,
"acc_norm_stderr": 0.02522545028406788
},
"harness|hendrycksTest-formal_logic|5": {
"acc": 0.3968253968253968,
"acc_stderr": 0.04375888492727061,
"acc_norm": 0.3968253968253968,
"acc_norm_stderr": 0.04375888492727061
},
"harness|hendrycksTest-global_facts|5": {
"acc": 0.35,
"acc_stderr": 0.0479372485441102,
"acc_norm": 0.35,
"acc_norm_stderr": 0.0479372485441102
},
"harness|hendrycksTest-high_school_biology|5": {
"acc": 0.7483870967741936,
"acc_stderr": 0.024685979286239956,
"acc_norm": 0.7483870967741936,
"acc_norm_stderr": 0.024685979286239956
},
"harness|hendrycksTest-high_school_chemistry|5": {
"acc": 0.5221674876847291,
"acc_stderr": 0.03514528562175008,
"acc_norm": 0.5221674876847291,
"acc_norm_stderr": 0.03514528562175008
},
"harness|hendrycksTest-high_school_computer_science|5": {
"acc": 0.67,
"acc_stderr": 0.04725815626252607,
"acc_norm": 0.67,
"acc_norm_stderr": 0.04725815626252607
},
"harness|hendrycksTest-high_school_european_history|5": {
"acc": 0.7636363636363637,
"acc_stderr": 0.03317505930009182,
"acc_norm": 0.7636363636363637,
"acc_norm_stderr": 0.03317505930009182
},
"harness|hendrycksTest-high_school_geography|5": {
"acc": 0.7525252525252525,
"acc_stderr": 0.030746300742124498,
"acc_norm": 0.7525252525252525,
"acc_norm_stderr": 0.030746300742124498
},
"harness|hendrycksTest-high_school_government_and_politics|5": {
"acc": 0.844559585492228,
"acc_stderr": 0.026148483469153314,
"acc_norm": 0.844559585492228,
"acc_norm_stderr": 0.026148483469153314
},
"harness|hendrycksTest-high_school_macroeconomics|5": {
"acc": 0.6205128205128205,
"acc_stderr": 0.024603626924097417,
"acc_norm": 0.6205128205128205,
"acc_norm_stderr": 0.024603626924097417
},
"harness|hendrycksTest-high_school_mathematics|5": {
"acc": 0.337037037037037,
"acc_stderr": 0.028820884666253252,
"acc_norm": 0.337037037037037,
"acc_norm_stderr": 0.028820884666253252
},
"harness|hendrycksTest-high_school_microeconomics|5": {
"acc": 0.6260504201680672,
"acc_stderr": 0.031429466378837076,
"acc_norm": 0.6260504201680672,
"acc_norm_stderr": 0.031429466378837076
},
"harness|hendrycksTest-high_school_physics|5": {
"acc": 0.33774834437086093,
"acc_stderr": 0.03861557546255169,
"acc_norm": 0.33774834437086093,
"acc_norm_stderr": 0.03861557546255169
},
"harness|hendrycksTest-high_school_psychology|5": {
"acc": 0.7944954128440367,
"acc_stderr": 0.01732435232501601,
"acc_norm": 0.7944954128440367,
"acc_norm_stderr": 0.01732435232501601
},
"harness|hendrycksTest-high_school_statistics|5": {
"acc": 0.5046296296296297,
"acc_stderr": 0.03409825519163572,
"acc_norm": 0.5046296296296297,
"acc_norm_stderr": 0.03409825519163572
},
"harness|hendrycksTest-high_school_us_history|5": {
"acc": 0.8137254901960784,
"acc_stderr": 0.027325470966716312,
"acc_norm": 0.8137254901960784,
"acc_norm_stderr": 0.027325470966716312
},
"harness|hendrycksTest-high_school_world_history|5": {
"acc": 0.7763713080168776,
"acc_stderr": 0.027123298205229966,
"acc_norm": 0.7763713080168776,
"acc_norm_stderr": 0.027123298205229966
},
"harness|hendrycksTest-human_aging|5": {
"acc": 0.6860986547085202,
"acc_stderr": 0.031146796482972465,
"acc_norm": 0.6860986547085202,
"acc_norm_stderr": 0.031146796482972465
},
"harness|hendrycksTest-human_sexuality|5": {
"acc": 0.7557251908396947,
"acc_stderr": 0.037683359597287434,
"acc_norm": 0.7557251908396947,
"acc_norm_stderr": 0.037683359597287434
},
"harness|hendrycksTest-international_law|5": {
"acc": 0.7851239669421488,
"acc_stderr": 0.037494924487096966,
"acc_norm": 0.7851239669421488,
"acc_norm_stderr": 0.037494924487096966
},
"harness|hendrycksTest-jurisprudence|5": {
"acc": 0.75,
"acc_stderr": 0.04186091791394607,
"acc_norm": 0.75,
"acc_norm_stderr": 0.04186091791394607
},
"harness|hendrycksTest-logical_fallacies|5": {
"acc": 0.7791411042944786,
"acc_stderr": 0.03259177392742178,
"acc_norm": 0.7791411042944786,
"acc_norm_stderr": 0.03259177392742178
},
"harness|hendrycksTest-machine_learning|5": {
"acc": 0.41964285714285715,
"acc_stderr": 0.04684099321077106,
"acc_norm": 0.41964285714285715,
"acc_norm_stderr": 0.04684099321077106
},
"harness|hendrycksTest-management|5": {
"acc": 0.7961165048543689,
"acc_stderr": 0.039891398595317706,
"acc_norm": 0.7961165048543689,
"acc_norm_stderr": 0.039891398595317706
},
"harness|hendrycksTest-marketing|5": {
"acc": 0.8589743589743589,
"acc_stderr": 0.022801382534597528,
"acc_norm": 0.8589743589743589,
"acc_norm_stderr": 0.022801382534597528
},
"harness|hendrycksTest-medical_genetics|5": {
"acc": 0.73,
"acc_stderr": 0.044619604333847394,
"acc_norm": 0.73,
"acc_norm_stderr": 0.044619604333847394
},
"harness|hendrycksTest-miscellaneous|5": {
"acc": 0.8135376756066411,
"acc_stderr": 0.013927751372001501,
"acc_norm": 0.8135376756066411,
"acc_norm_stderr": 0.013927751372001501
},
"harness|hendrycksTest-moral_disputes|5": {
"acc": 0.6994219653179191,
"acc_stderr": 0.0246853168672578,
"acc_norm": 0.6994219653179191,
"acc_norm_stderr": 0.0246853168672578
},
"harness|hendrycksTest-moral_scenarios|5": {
"acc": 0.4033519553072626,
"acc_stderr": 0.01640712303219525,
"acc_norm": 0.4033519553072626,
"acc_norm_stderr": 0.01640712303219525
},
"harness|hendrycksTest-nutrition|5": {
"acc": 0.7320261437908496,
"acc_stderr": 0.02536060379624255,
"acc_norm": 0.7320261437908496,
"acc_norm_stderr": 0.02536060379624255
},
"harness|hendrycksTest-philosophy|5": {
"acc": 0.7009646302250804,
"acc_stderr": 0.02600330111788514,
"acc_norm": 0.7009646302250804,
"acc_norm_stderr": 0.02600330111788514
},
"harness|hendrycksTest-prehistory|5": {
"acc": 0.7067901234567902,
"acc_stderr": 0.025329888171900926,
"acc_norm": 0.7067901234567902,
"acc_norm_stderr": 0.025329888171900926
},
"harness|hendrycksTest-professional_accounting|5": {
"acc": 0.49645390070921985,
"acc_stderr": 0.02982674915328092,
"acc_norm": 0.49645390070921985,
"acc_norm_stderr": 0.02982674915328092
},
"harness|hendrycksTest-professional_law|5": {
"acc": 0.44784876140808344,
"acc_stderr": 0.01270058240476822,
"acc_norm": 0.44784876140808344,
"acc_norm_stderr": 0.01270058240476822
},
"harness|hendrycksTest-professional_medicine|5": {
"acc": 0.6397058823529411,
"acc_stderr": 0.029163128570670733,
"acc_norm": 0.6397058823529411,
"acc_norm_stderr": 0.029163128570670733
},
"harness|hendrycksTest-professional_psychology|5": {
"acc": 0.6666666666666666,
"acc_stderr": 0.019070985589687495,
"acc_norm": 0.6666666666666666,
"acc_norm_stderr": 0.019070985589687495
},
"harness|hendrycksTest-public_relations|5": {
"acc": 0.6727272727272727,
"acc_stderr": 0.0449429086625209,
"acc_norm": 0.6727272727272727,
"acc_norm_stderr": 0.0449429086625209
},
"harness|hendrycksTest-security_studies|5": {
"acc": 0.7020408163265306,
"acc_stderr": 0.029279567411065677,
"acc_norm": 0.7020408163265306,
"acc_norm_stderr": 0.029279567411065677
},
"harness|hendrycksTest-sociology|5": {
"acc": 0.7960199004975125,
"acc_stderr": 0.02849317624532607,
"acc_norm": 0.7960199004975125,
"acc_norm_stderr": 0.02849317624532607
},
"harness|hendrycksTest-us_foreign_policy|5": {
"acc": 0.84,
"acc_stderr": 0.03684529491774709,
"acc_norm": 0.84,
"acc_norm_stderr": 0.03684529491774709
},
"harness|hendrycksTest-virology|5": {
"acc": 0.5542168674698795,
"acc_stderr": 0.03869543323472101,
"acc_norm": 0.5542168674698795,
"acc_norm_stderr": 0.03869543323472101
},
"harness|hendrycksTest-world_religions|5": {
"acc": 0.8011695906432749,
"acc_stderr": 0.03061111655743253,
"acc_norm": 0.8011695906432749,
"acc_norm_stderr": 0.03061111655743253
},
"harness|truthfulqa:mc|0": {
"mc1": 0.2802937576499388,
"mc1_stderr": 0.015723139524608767,
"mc2": 0.435601924823795,
"mc2_stderr": 0.014179199089974604
},
"harness|winogrande|5": {
"acc": 0.7932123125493291,
"acc_stderr": 0.011382566829235805
},
"harness|gsm8k|5": {
"acc": 0.3510235026535254,
"acc_stderr": 0.01314694594139722
}
}
```

26
config.json Normal file
View File

@@ -0,0 +1,26 @@
{
"_name_or_path": "mistralai/Mistral-7B-v0.1",
"architectures": [
"MistralForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 1,
"eos_token_id": 2,
"hidden_act": "silu",
"hidden_size": 4096,
"initializer_range": 0.02,
"intermediate_size": 14336,
"max_position_embeddings": 32768,
"model_type": "mistral",
"num_attention_heads": 32,
"num_hidden_layers": 32,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-05,
"rope_theta": 10000.0,
"sliding_window": 4096,
"tie_word_embeddings": false,
"torch_dtype": "float32",
"transformers_version": "4.37.0.dev0",
"use_cache": true,
"vocab_size": 32000
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"transformers_version": "4.37.0.dev0"
}

3
model-00001-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7f57b9812c7c2c6aea81c93ff7929431b8c352d715771925ff2168ebba98a888
size 4987196936

3
model-00002-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:348cce763cf843ecfbcb88839585a9546721f6a3ad6ec6d4b4e5a070bc7c4292
size 4899116440

3
model-00003-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:aa019f370c5ddea32862cae980cdfe6f0105e4dce119b8b3373fdb5dac391ce2
size 4999813120

3
model-00004-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:35b6a171a68b5ef93e7906a1936194990370a22b4743e4338b284f91628b2495
size 4999813128

3
model-00005-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:791b37bd849b826f7c9ccd7cc03a0b8a4e1f25185d38cdebb5b971eb465cecca
size 4832007496

3
model-00006-of-00006.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a1ddc57580afdc2ac7c70d482195e15c71e941d2216f0c24b94f6bdd49718bb2
size 4249014896

298
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,298 @@
{
"metadata": {
"total_size": 28966928384
},
"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-00003-of-00006.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00003-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-00003-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-00003-of-00006.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.12.input_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00003-of-00006.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00003-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-00004-of-00006.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00006.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00004-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-00004-of-00006.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.18.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.19.input_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00004-of-00006.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00004-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-00004-of-00006.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00004-of-00006.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00004-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-00005-of-00006.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00005-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-00005-of-00006.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.24.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.25.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.26.input_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00005-of-00006.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00005-of-00006.safetensors",
"model.layers.28.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.29.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00006-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-00006-of-00006.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.31.input_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00006-of-00006.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00006-of-00006.safetensors",
"model.layers.31.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-00002-of-00006.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00002-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-00002-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": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

91099
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

BIN
tokenizer.model (Stored with Git LFS) Normal file
View File

Binary file not shown.

46
tokenizer_config.json Normal file
View File

@@ -0,0 +1,46 @@
{
"add_bos_token": false,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "</s>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [],
"bos_token": "<s>",
"clean_up_tokenization_spaces": false,
"eos_token": "</s>",
"legacy": true,
"max_length": 1024,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<unk>",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"stride": 0,
"tokenizer_class": "LlamaTokenizer",
"truncation_side": "right",
"truncation_strategy": "longest_first",
"unk_token": "<unk>",
"use_default_system_prompt": false
}