初始化项目，由ModelHub XC社区提供模型

Model: kikiyaa/Mistral-7B-dpo-full-tuned Source: Original Platform
2026-06-13 17:10:39 +08:00
commit 62faa781b4
41 changed files with 1084752 additions and 0 deletions
--- a/.gitattributes
+++ b/.gitattributes
@@ -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
--- a/README.md
+++ b/README.md
@@ -0,0 +1,69 @@
+---
+base_model: mistralai/Mistral-7B-v0.1
+library_name: transformers
+model_name: app/output/Mistral-7B-full-tunned
+tags:
+- generated_from_trainer
+- dpo
+- trl
+licence: license
+---
+
+# Model Card for app/output/Mistral-7B-full-tunned
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.1](https://huggingface.co/mistralai/Mistral-7B-v0.1).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+ 
+
+
+
+This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
+
+### Framework versions
+
+- TRL: 0.29.0
+- Transformers: 5.5.0
+- Pytorch: 2.9.1+cu128
+- Datasets: 4.5.0
+- Tokenizers: 0.22.2
+
+## Citations
+
+Cite DPO as:
+
+```bibtex
+@inproceedings{rafailov2023direct,
+    title        = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
+    author       = {Rafael Rafailov and Archit Sharma and Eric Mitchell and Christopher D. Manning and Stefano Ermon and Chelsea Finn},
+    year         = 2023,
+    booktitle    = {Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, NeurIPS 2023, New Orleans, LA, USA, December 10 - 16, 2023},
+    url          = {http://papers.nips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract-Conference.html},
+    editor       = {Alice Oh and Tristan Naumann and Amir Globerson and Kate Saenko and Moritz Hardt and Sergey Levine},
+}
+```
+
+Cite TRL as:
+    
+```bibtex
+@software{vonwerra2020trl,
+  title   = {{TRL: Transformers Reinforcement Learning}},
+  author  = {von Werra, Leandro and Belkada, Younes and Tunstall, Lewis and Beeching, Edward and Thrush, Tristan and Lambert, Nathan and Huang, Shengyi and Rasul, Kashif and Gallouédec, Quentin},
+  license = {Apache-2.0},
+  url     = {https://github.com/huggingface/trl},
+  year    = {2020}
+}
+```
--- a/checkpoint-1800/config.json
+++ b/checkpoint-1800/config.json
@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}
--- a/checkpoint-1800/generation_config.json
+++ b/checkpoint-1800/generation_config.json
@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "5.5.0"
+}
--- a/checkpoint-1800/model.safetensors
+++ b/checkpoint-1800/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4040f2d06a5ab630252793f70cab6d293108427c389f25a6f1d01ff73d26f618
+size 14483498224
--- a/checkpoint-1800/optimizer.pt
+++ b/checkpoint-1800/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29d7132c64c3613f42b2b157e707eff3674db7fc533c7e0cb154f325068e393e
+size 15492459239
--- a/checkpoint-1800/rng_state_0.pth
+++ b/checkpoint-1800/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22fd48de94f8794152ebf150819976a79ffce6c6db91d8d8f7f19252d8a88706
+size 14917
--- a/checkpoint-1800/rng_state_1.pth
+++ b/checkpoint-1800/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6002b151733147d2dfb26db4f758a47a2e84aaee49b3f2ab08cf3644b17f14ea
+size 14917
--- a/checkpoint-1800/scheduler.pt
+++ b/checkpoint-1800/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a892ab591f4c57e475ad6e4dc16ac86e611bd646fba96798637aead5aa2ce865
+size 1465
--- a/checkpoint-1800/tokenizer.json
+++ b/checkpoint-1800/tokenizer.json
--- a/checkpoint-1800/tokenizer_config.json
+++ b/checkpoint-1800/tokenizer_config.json
@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}
--- a/checkpoint-1800/trainer_state.json
+++ b/checkpoint-1800/trainer_state.json
--- a/checkpoint-1800/training_args.bin
+++ b/checkpoint-1800/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614aa8e2dd443314ad7e68fa2f4dbaa35bb5733286b3c5fcb81187eee69d303a
+size 7249
--- a/checkpoint-2000/config.json
+++ b/checkpoint-2000/config.json
@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}
--- a/checkpoint-2000/generation_config.json
+++ b/checkpoint-2000/generation_config.json
@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "5.5.0"
+}
--- a/checkpoint-2000/model.safetensors
+++ b/checkpoint-2000/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1d0722dd0e4fa4502904f11eca14f692e310853b284fd7a80d11199744a68e6
+size 14483498224
--- a/checkpoint-2000/optimizer.pt
+++ b/checkpoint-2000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03ee70f7cd16ea787f86c514669d309862da3ae1b7a8f1736bef2bf3f3fc64a4
+size 15492459239
--- a/checkpoint-2000/rng_state_0.pth
+++ b/checkpoint-2000/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0422ee5c141001d3aedb3fdd5436a57c7d09eccddd5d897a8c15e78796a2bcaa
+size 14917
--- a/checkpoint-2000/rng_state_1.pth
+++ b/checkpoint-2000/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c0ba5c76bb547c32dd4db22c3757d37b3e1ec1077e8c11a48c9288a7025d3ec5
+size 14917
--- a/checkpoint-2000/scheduler.pt
+++ b/checkpoint-2000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94dc5f32e487a6c1db3b1c60813696a8e15ca67606b6de3d7e3df2d3a2b93025
+size 1465
--- a/checkpoint-2000/tokenizer.json
+++ b/checkpoint-2000/tokenizer.json
--- a/checkpoint-2000/tokenizer_config.json
+++ b/checkpoint-2000/tokenizer_config.json
@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}
--- a/checkpoint-2000/trainer_state.json
+++ b/checkpoint-2000/trainer_state.json
--- a/checkpoint-2000/training_args.bin
+++ b/checkpoint-2000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614aa8e2dd443314ad7e68fa2f4dbaa35bb5733286b3c5fcb81187eee69d303a
+size 7249
--- a/checkpoint-2181/config.json
+++ b/checkpoint-2181/config.json
@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}
--- a/checkpoint-2181/generation_config.json
+++ b/checkpoint-2181/generation_config.json
@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "5.5.0"
+}
--- a/checkpoint-2181/model.safetensors
+++ b/checkpoint-2181/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc9814c34fe85aa0e259075f524bcddca37b9717e0821d64b0a220d55c90545
+size 14483498224
--- a/checkpoint-2181/optimizer.pt
+++ b/checkpoint-2181/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13648ac5d4a33dcc9d84ac55c3925e9acf7aa794b7ea98ad572492b31558d3f0
+size 15492459239
--- a/checkpoint-2181/rng_state_0.pth
+++ b/checkpoint-2181/rng_state_0.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62a7f220058b2a83cb865138b418559197d934c38ad4cb37de2fa90a20738473
+size 14917
--- a/checkpoint-2181/rng_state_1.pth
+++ b/checkpoint-2181/rng_state_1.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfe523d92e0bf393b8e0943f6455e87bf27d55a9040e1080407956bfc34dadc1
+size 14917
--- a/checkpoint-2181/scheduler.pt
+++ b/checkpoint-2181/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc33e320769f228522a5b027ce213c5aab90adca9d580a46b128d53567e2546c
+size 1465
--- a/checkpoint-2181/tokenizer.json
+++ b/checkpoint-2181/tokenizer.json
--- a/checkpoint-2181/tokenizer_config.json
+++ b/checkpoint-2181/tokenizer_config.json
@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}
--- a/checkpoint-2181/trainer_state.json
+++ b/checkpoint-2181/trainer_state.json
--- a/checkpoint-2181/training_args.bin
+++ b/checkpoint-2181/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:614aa8e2dd443314ad7e68fa2f4dbaa35bb5733286b3c5fcb81187eee69d303a
+size 7249
--- a/config.json
+++ b/config.json
@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "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,
+  "pad_token_id": 2,
+  "rms_norm_eps": 1e-05,
+  "rope_parameters": {
+    "rope_theta": 10000.0,
+    "rope_type": "default"
+  },
+  "sliding_window": 4096,
+  "tie_word_embeddings": false,
+  "transformers_version": "5.5.0",
+  "use_cache": false,
+  "vocab_size": 32000
+}
--- a/debug.log
+++ b/debug.log
--- a/generation_config.json
+++ b/generation_config.json
@@ -0,0 +1,10 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": [
+    2
+  ],
+  "pad_token_id": 2,
+  "transformers_version": "5.5.0"
+}
--- a/model.safetensors
+++ b/model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9bc9814c34fe85aa0e259075f524bcddca37b9717e0821d64b0a220d55c90545
+size 14483498224
--- a/tokenizer.json
+++ b/tokenizer.json
--- a/tokenizer_config.json
+++ b/tokenizer_config.json
@@ -0,0 +1,17 @@
+{
+  "add_prefix_space": null,
+  "backend": "tokenizers",
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "extra_special_tokens": [],
+  "is_local": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}