LLM-Research/WizardHermes-2-Pro-Llama-3-8b
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: LLM-Research/WizardHermes-2-Pro-Llama-3-8b
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-19 12:37:12 +08:00
commit b2d1635f0b
14 changed files with 205 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

43
.gitattributes vendored Normal file
View File

@@ -0,0 +1,43 @@
*.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
WizardHermes-2-Pro-Llama-3-8b.f16.gguf filter=lfs diff=lfs merge=lfs -text
WizardHermes-2-Pro-Llama-3-8b.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
WizardHermes-2-Pro-Llama-3-8b.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
WizardHermes-2-Pro-Llama-3-8b.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
WizardHermes-2-Pro-Llama-3-8b.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
WizardHermes-2-Pro-Llama-3-8b.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
adapter_model.safetensors filter=lfs diff=lfs merge=lfs -text
optimizer.pt filter=lfs diff=lfs merge=lfs -text

100
README.md Normal file
View File

@@ -0,0 +1,100 @@
---
license: llama3
language:
- en
library_name: transformers
pipeline_tag: text-generation
datasets:
- cognitivecomputations/WizardLM_alpaca_evol_instruct_70k_unfiltered
tags:
- finetune
- llama
---
# WizardHermes-2-Pro-Llama-3-8b
Finetuned from Meta-Llama-3-8b, 0.55 epoches
Merged with Hermes-2-Pro-Llama-3-8b
Eval (0.0 temp) ([https://inflection.ai/assets/MMLU-Examples.pdf](https://inflection.ai/assets/MMLU-Examples.pdf), 0-shot):
```
Hermes 2 Pro LoRA (merged) (checkpoint 1): 7/12
Hermes 2 Pro LoRA (merged) (checkpoint 2): 9/12
Hermes 2 Pro Llama 3 8b: 8/12
```
TruthfulQA (0-shot):
```
Hermes 2 Pro LoRA (merged) (checkpoint 2): 9/15
Hermes 2 Pro Llama 3 8b: 7/15
```
**Trained using MonsterAPI**
LoRA training parameters:
```
{
"deployment_name": "wizardlm-llama-3-8b",
"pretrainedmodel_config": {
"model_path": "meta-llama/Meta-Llama-3-8B",
"other_model_info": null,
"resume_checkpoint_path": "",
"use_lora": true,
"lora_r": 8,
"lora_alpha": 16,
"lora_dropout": 0,
"lora_bias": "none",
"use_quantization": false,
"use_gradient_checkpointing": false,
"parallelization": "nmp"
},
"data_config": {
"data_path": "cognitivecomputations/WizardLM_alpaca_evol_instruct_70k_unfiltered",
"data_subset": "default",
"data_source_type": "hub_link",
"cutoff_len": 4096,
"data_split_config": {
"train": 0.9,
"validation": 0.1
},
"prevalidated": true,
"concat_config": {
"0": {
"text": "Below is an instruction that describes a task. Write a response that appropriately completes the request. \n\n\n###Instruction:",
"column": false
},
"1": {
"text": "instruction",
"column": true
},
"2": {
"text": "\n\n\n###Response:",
"column": false
},
"3": {
"text": "output",
"column": true
}
}
},
"training_config": {
"early_stopping_patience": 5,
"num_train_epochs": 5,
"gradient_accumulation_steps": 1,
"warmup_steps": 300,
"learning_rate": 0.0005,
"lr_scheduler_type": "reduce_lr_on_plateau",
"group_by_length": false,
"use_hugging_face": false
},
"logging_config": {
"use_wandb": false,
"wandb_username": "",
"wandb_login_key": "",
"wandb_project": "",
"wandb_run_name": ""
},
"accessorytasks_config": {
"run_eval_report": false,
"run_quantize_merge": false
}
}
```

3
WizardHermes-2-Pro-Llama-3-8b.Q2_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:accf2d8ea02d744279ae3266f25ab0562306016325b5f593501c61672b14fa38
size 3179282752

3
WizardHermes-2-Pro-Llama-3-8b.Q3_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:ef6703d1e04daecbd5e4f4cdd58f1f5c28b4f87995ab4cb2c3b34b72309e280e
size 4019082560

3
WizardHermes-2-Pro-Llama-3-8b.Q4_K_M.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7d1b6e4f6c0ee305364a7beefc5f36dc01f93e94e63b73a3664bcdfa46aa7107
size 4920916288

3
WizardHermes-2-Pro-Llama-3-8b.Q6_K.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1c8641c510025c60f111596390846b0c20da9c31a9bf3cb45130ce5b5016dbe6
size 6596222272

3
WizardHermes-2-Pro-Llama-3-8b.Q8_0.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9d52436ba89e4aa5463436ef728e37f2ef060b93bbea849fe30150db4ca94449
size 8541050176

3
WizardHermes-2-Pro-Llama-3-8b.f16.gguf Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:41a7d34e10b91ce47502e4364eea5c018e857bba05d4acbb6a2d232c020c848f
size 16069416224

31
adapter_config.json Normal file
View File

@@ -0,0 +1,31 @@
{
"alpha_pattern": {},
"auto_mapping": null,
"base_model_name_or_path": "meta-llama/Meta-Llama-3-8B",
"bias": "none",
"fan_in_fan_out": false,
"inference_mode": true,
"init_lora_weights": true,
"layer_replication": null,
"layers_pattern": null,
"layers_to_transform": null,
"loftq_config": {},
"lora_alpha": 16,
"lora_dropout": 0.0,
"megatron_config": null,
"megatron_core": "megatron.core",
"modules_to_save": null,
"peft_type": "LORA",
"r": 8,
"rank_pattern": {},
"revision": null,
"target_modules": [
"o_proj",
"q_proj",
"k_proj",
"v_proj"
],
"task_type": "CAUSAL_LM",
"use_dora": false,
"use_rslora": false
}

3
adapter_model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e8893875c67009a9fdec4cb04020bee9bb7d6d6c9f85f2bae32e557bb37ea76a
size 13665592

1
configuration.json Normal file
View File

@@ -0,0 +1 @@
{"framework": "pytorch", "task": "text-generation", "allow_remote": true}

3
optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9d192666a7cfd4b8a8c408088a73ffc25bd2141adef43863a9ab9176f24b8758
size 27414330

3
rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:48ee9b73399c28d7e668360bf1d5a4d11095c4738bf96c13f7bb6fbff59f8ccb
size 14244

3
scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:2b6ba104e682d8207a8019fb0461a3618f62771d258f986e3ebd6619216e8b39
size 1192