初始化项目，由ModelHub XC社区提供模型

Model: QuantFactory/Llama-3-8B-OpenHermes-2.5-1M-GGUF
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.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
+Llama-3-8B-OpenHermes-2.5-1M.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-OpenHermes-2.5-1M.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-OpenHermes-2.5-1M.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-OpenHermes-2.5-1M.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-OpenHermes-2.5-1M.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-OpenHermes-2.5-1M.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-OpenHermes-2.5-1M.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-OpenHermes-2.5-1M.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-OpenHermes-2.5-1M.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-OpenHermes-2.5-1M.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-OpenHermes-2.5-1M.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-OpenHermes-2.5-1M.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-OpenHermes-2.5-1M.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+Llama-3-8B-OpenHermes-2.5-1M.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text

Llama-3-8B-OpenHermes-2.5-1M.Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9445cf146afdd175371849c34db1b9ca3e59cdf6154999f41a4bcf22f0db56bc
+size 3179131200

Llama-3-8B-OpenHermes-2.5-1M.Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:543866ffd11e0092d900095f6ce361a7feb0bfb1cf3761f0881e1a74ebabd0b5
+size 4321956160

Llama-3-8B-OpenHermes-2.5-1M.Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd7e6cc743214baeda8fffc1de2de336187ec301671b23fd33742624dc18edea
+size 4018917696

Llama-3-8B-OpenHermes-2.5-1M.Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a537928fe7af4b3f0def76073f186e54929236b1066d7b7ac28b47fa0ed1a976
+size 3664499008

Llama-3-8B-OpenHermes-2.5-1M.Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5d5078a19ba98c014bb78960b3a3da9241c221e05655baa353e15ffb74365ae1
+size 4661211456

Llama-3-8B-OpenHermes-2.5-1M.Q4_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:226ee034d5289f5875ed3632fda6d7232ee0aa3cb85ae8fe091465d8a779b667
+size 5130252608

Llama-3-8B-OpenHermes-2.5-1M.Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b30c6a019cbed9b61cf66c34e9c2eba31c861bb7522fe29f4ef78668fabb1a7
+size 4920734016

Llama-3-8B-OpenHermes-2.5-1M.Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b8db5b2aebda12a1d980845764a3f68f6874650a650390e4e4aff5eb7ce65642
+size 4692668736

Llama-3-8B-OpenHermes-2.5-1M.Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:87686cee840a579ca9e28484a008d5d03c58fd8b1f1de06c606f7508171feea7
+size 5599293760

Llama-3-8B-OpenHermes-2.5-1M.Q5_1.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cd3053d01f7be2b8fc528270eb5a244c2ed121817e63c732a2e568d4309fefd
+size 6068334912

Llama-3-8B-OpenHermes-2.5-1M.Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfee07260231d6851c1035bac1905734e087d21e81a58a162a176e9e108bdaa2
+size 5732987200

Llama-3-8B-OpenHermes-2.5-1M.Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b46ef07c635c92c0f8325387ef792816eb4fc59ac9377da187048e456de68193
+size 5599293760

Llama-3-8B-OpenHermes-2.5-1M.Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bc73e6e8c7231d40d184c8ca6e1a307d76b38c236692f6d088e92a6cd961765
+size 6596006208

Llama-3-8B-OpenHermes-2.5-1M.Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0b628ba2786ef7ce140b619fa3192193a17d9771546c6516e690f7b0d46f22f0
+size 8540770624

README.md

@@ -0,0 +1,131 @@
+---
+license: llama3
+base_model: Magpie-Align/Llama-3-8B-OpenHermes-2.5-1M
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: Llama-3-8B-OpenHermes-2.5-1M
+  results: []
+pipeline_tag: text-generation
+---
+
+# QuantFactory/Llama-3-8B-OpenHermes-2.5-1M-GGUF
+This is quantized version of [Magpie-Align/Llama-3-8B-OpenHermes-2.5-1M](https://huggingface.co/Magpie-Align/Llama-3-8B-OpenHermes-2.5-1M) created using llama.cpp
+
+# Model Description
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: meta-llama/Meta-Llama-3-8B
+model_type: LlamaForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: teknium/OpenHermes-2.5
+    type: sharegpt
+    conversation: llama3
+dataset_prepared_path: last_run_prepared
+val_set_size: 0.001
+output_dir: ./out_Llama-8B-Openhermes-2.5
+
+sequence_len: 8192
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: true
+
+wandb_project: SynDa
+wandb_entity:
+wandb_watch:
+wandb_name: Llama-3-8B-OpenHermes-2.5-1M
+wandb_log_model:
+hub_model_id: Magpie-Align/Llama-3-8B-OpenHermes-2.5-1M
+
+gradient_accumulation_steps: 8
+micro_batch_size: 1
+num_epochs: 2
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 2e-5
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: false
+
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+  use_reentrant: false
+early_stopping_patience:
+resume_from_checkpoint:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_steps: 100
+evals_per_epoch: 3
+eval_table_size:
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+  pad_token: <|end_of_text|>
+
+```
+
+</details><br>
+
+# Llama-3-8B-OpenHermes-2.5-1M
+
+This model is a fine-tuned version of [meta-llama/Meta-Llama-3-8B](https://huggingface.co/meta-llama/Meta-Llama-3-8B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.6993
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 32
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 100
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.9499        | 0.0007 | 1    | 0.9305          |
+| 0.6229        | 0.3337 | 488  | 0.7164          |
+| 0.6231        | 0.6674 | 976  | 0.7045          |
+| 0.5959        | 1.0011 | 1464 | 0.6959          |
+| 0.4997        | 1.3181 | 1952 | 0.7003          |
+| 0.529         | 1.6518 | 2440 | 0.6993          |
+
+
+### Framework versions
+
+- Transformers 4.40.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.19.1
+- Tokenizers 0.19.1

configuration.json

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