初始化项目,由ModelHub XC社区提供模型
Model: joseph-ai/Aris-293M Source: Original Platform
This commit is contained in:
4
last-checkpoint/chat_template.jinja
Normal file
4
last-checkpoint/chat_template.jinja
Normal file
@@ -0,0 +1,4 @@
|
||||
{% for message in messages %}{{'<|im_start|>' + message['role'] + '
|
||||
' + message['content'] + '<|im_end|>' + '
|
||||
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
||||
' }}{% endif %}
|
||||
32
last-checkpoint/config.json
Normal file
32
last-checkpoint/config.json
Normal file
@@ -0,0 +1,32 @@
|
||||
{
|
||||
"architectures": [
|
||||
"LlamaForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 0,
|
||||
"dtype": "float32",
|
||||
"eos_token_id": 0,
|
||||
"head_dim": 64,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1024,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 4096,
|
||||
"max_position_embeddings": 4096,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 16,
|
||||
"num_hidden_layers": 16,
|
||||
"num_key_value_heads": 4,
|
||||
"pad_token_id": 0,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 500000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.12.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 49152
|
||||
}
|
||||
12
last-checkpoint/generation_config.json
Normal file
12
last-checkpoint/generation_config.json
Normal file
@@ -0,0 +1,12 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": [
|
||||
0
|
||||
],
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"pad_token_id": 0,
|
||||
"transformers_version": "5.12.1",
|
||||
"use_cache": false
|
||||
}
|
||||
3
last-checkpoint/model.safetensors
Normal file
3
last-checkpoint/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:9605f6354cfacffddb46324f74e0235e4e575f89cc7653a04c421b60d2c55f78
|
||||
size 1174556784
|
||||
3
last-checkpoint/optimizer.pt
Normal file
3
last-checkpoint/optimizer.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:730f4003104d127284239b0673d877f9c25190bcef12f16cd4e9a2f2000ef2fb
|
||||
size 2349203770
|
||||
3
last-checkpoint/rng_state_0.pth
Normal file
3
last-checkpoint/rng_state_0.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d5ba29f46557a47121b6d958c73709c883f68518d01cd68a767a082520b91b9f
|
||||
size 14512
|
||||
3
last-checkpoint/rng_state_1.pth
Normal file
3
last-checkpoint/rng_state_1.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:0a408fa3a85250385243240a3c4f6e6dc4513da1d97421e8faae4c8d880e7d1a
|
||||
size 14512
|
||||
3
last-checkpoint/scheduler.pt
Normal file
3
last-checkpoint/scheduler.pt
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:d61683177ee3717ed38f8d3006bf1a4424a670de6da8cc1e910e864aae34242e
|
||||
size 1064
|
||||
244965
last-checkpoint/tokenizer.json
Normal file
244965
last-checkpoint/tokenizer.json
Normal file
File diff suppressed because it is too large
Load Diff
34
last-checkpoint/tokenizer_config.json
Normal file
34
last-checkpoint/tokenizer_config.json
Normal file
@@ -0,0 +1,34 @@
|
||||
{
|
||||
"add_prefix_space": false,
|
||||
"backend": "tokenizers",
|
||||
"bos_token": "<|endoftext|>",
|
||||
"clean_up_tokenization_spaces": false,
|
||||
"eos_token": "<|endoftext|>",
|
||||
"errors": "replace",
|
||||
"extra_special_tokens": [
|
||||
"<|endoftext|>",
|
||||
"<|im_start|>",
|
||||
"<|im_end|>",
|
||||
"<repo_name>",
|
||||
"<reponame>",
|
||||
"<file_sep>",
|
||||
"<filename>",
|
||||
"<gh_stars>",
|
||||
"<issue_start>",
|
||||
"<issue_comment>",
|
||||
"<issue_closed>",
|
||||
"<jupyter_start>",
|
||||
"<jupyter_text>",
|
||||
"<jupyter_code>",
|
||||
"<jupyter_output>",
|
||||
"<jupyter_script>",
|
||||
"<empty_output>"
|
||||
],
|
||||
"is_local": false,
|
||||
"local_files_only": false,
|
||||
"model_max_length": 1000000000000000019884624838656,
|
||||
"pad_token": "<|endoftext|>",
|
||||
"tokenizer_class": "GPT2Tokenizer",
|
||||
"unk_token": "<|endoftext|>",
|
||||
"vocab_size": 49152
|
||||
}
|
||||
5503
last-checkpoint/trainer_state.json
Normal file
5503
last-checkpoint/trainer_state.json
Normal file
File diff suppressed because it is too large
Load Diff
3
last-checkpoint/training_args.bin
Normal file
3
last-checkpoint/training_args.bin
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:1ab1cc1b837b107318eb1fb70965ee9da7284e9a0034311a2b0f8c297b7b7c98
|
||||
size 4792
|
||||
Reference in New Issue
Block a user