初始化项目,由ModelHub XC社区提供模型
Model: donoway/ARC-Easy_Llama-3.2-1B-oqrx1b71 Source: Original Platform
This commit is contained in:
36
checkpoint-21/config.json
Normal file
36
checkpoint-21/config.json
Normal file
@@ -0,0 +1,36 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"eos_token_id": 128001,
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 131072,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 16,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 128004,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 32.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"tie_word_embeddings": true,
|
||||
"torch_dtype": "bfloat16",
|
||||
"transformers_version": "4.51.3",
|
||||
"use_cache": true,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
9
checkpoint-21/generation_config.json
Normal file
9
checkpoint-21/generation_config.json
Normal file
@@ -0,0 +1,9 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 128000,
|
||||
"do_sample": true,
|
||||
"eos_token_id": 128001,
|
||||
"temperature": 0.6,
|
||||
"top_p": 0.9,
|
||||
"transformers_version": "4.51.3"
|
||||
}
|
||||
3
checkpoint-21/model.safetensors
Normal file
3
checkpoint-21/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:adb8d0cd79d7d8e1a9a997977ba53da9160ece736a92782a441115fced4ef446
|
||||
size 2471645608
|
||||
3
checkpoint-21/optimizer.pt
Normal file
3
checkpoint-21/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:6c90d21cd1e048399239d8e35c308b3c9bdd52d83bde5e380fa277bb0adef273
|
||||
size 4943382114
|
||||
3
checkpoint-21/rng_state.pth
Normal file
3
checkpoint-21/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:bdc6b9e266079af4905e788266ab5911a661673579466ce5a178ea07f97617a8
|
||||
size 14244
|
||||
3
checkpoint-21/scheduler.pt
Normal file
3
checkpoint-21/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d84bfb48e0636c1b417b109cff164d10bcd741414d8fb3a1492190b54d573f8c
|
||||
size 1064
|
||||
23
checkpoint-21/special_tokens_map.json
Normal file
23
checkpoint-21/special_tokens_map.json
Normal file
@@ -0,0 +1,23 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|end_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": {
|
||||
"content": "<|finetune_right_pad_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
}
|
||||
}
|
||||
BIN
checkpoint-21/tokenizer.json
(Stored with Git LFS)
Normal file
BIN
checkpoint-21/tokenizer.json
(Stored with Git LFS)
Normal file
Binary file not shown.
2063
checkpoint-21/tokenizer_config.json
Normal file
2063
checkpoint-21/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
1092
checkpoint-21/trainer_state.json
Normal file
1092
checkpoint-21/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
checkpoint-21/training_args.bin
Normal file
3
checkpoint-21/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:8f9cc115c0a2df7f95373e88d223e7fe0c5fe2b1804d07650e45c90766f827c8
|
||||
size 5432
|
||||
Reference in New Issue
Block a user