初始化项目,由ModelHub XC社区提供模型
Model: kikiyaa/Mistral-7B-dpo-full-tuned Source: Original Platform
This commit is contained in:
30
checkpoint-1800/config.json
Normal file
30
checkpoint-1800/config.json
Normal file
@@ -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
|
||||
}
|
||||
10
checkpoint-1800/generation_config.json
Normal file
10
checkpoint-1800/generation_config.json
Normal file
@@ -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"
|
||||
}
|
||||
3
checkpoint-1800/model.safetensors
Normal file
3
checkpoint-1800/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:4040f2d06a5ab630252793f70cab6d293108427c389f25a6f1d01ff73d26f618
|
||||
size 14483498224
|
||||
3
checkpoint-1800/optimizer.pt
Normal file
3
checkpoint-1800/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:29d7132c64c3613f42b2b157e707eff3674db7fc533c7e0cb154f325068e393e
|
||||
size 15492459239
|
||||
3
checkpoint-1800/rng_state_0.pth
Normal file
3
checkpoint-1800/rng_state_0.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:22fd48de94f8794152ebf150819976a79ffce6c6db91d8d8f7f19252d8a88706
|
||||
size 14917
|
||||
3
checkpoint-1800/rng_state_1.pth
Normal file
3
checkpoint-1800/rng_state_1.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6002b151733147d2dfb26db4f758a47a2e84aaee49b3f2ab08cf3644b17f14ea
|
||||
size 14917
|
||||
3
checkpoint-1800/scheduler.pt
Normal file
3
checkpoint-1800/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a892ab591f4c57e475ad6e4dc16ac86e611bd646fba96798637aead5aa2ce865
|
||||
size 1465
|
||||
268053
checkpoint-1800/tokenizer.json
Normal file
268053
checkpoint-1800/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
17
checkpoint-1800/tokenizer_config.json
Normal file
17
checkpoint-1800/tokenizer_config.json
Normal file
@@ -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
|
||||
}
|
||||
3653
checkpoint-1800/trainer_state.json
Normal file
3653
checkpoint-1800/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-1800/training_args.bin
Normal file
3
checkpoint-1800/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:614aa8e2dd443314ad7e68fa2f4dbaa35bb5733286b3c5fcb81187eee69d303a
|
||||
size 7249
|
||||
Reference in New Issue
Block a user