初始化项目,由ModelHub XC社区提供模型
Model: cooler8/ZeliDesk-sLM-1B Source: Original Platform
This commit is contained in:
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": 2048,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 8192,
|
||||
"max_position_embeddings": 2048,
|
||||
"mlp_bias": false,
|
||||
"model_type": "llama",
|
||||
"num_attention_heads": 32,
|
||||
"num_hidden_layers": 16,
|
||||
"num_key_value_heads": 8,
|
||||
"pad_token_id": 1,
|
||||
"pretraining_tp": 1,
|
||||
"rms_norm_eps": 1e-06,
|
||||
"rope_parameters": {
|
||||
"rope_theta": 500000.0,
|
||||
"rope_type": "default"
|
||||
},
|
||||
"tie_word_embeddings": true,
|
||||
"transformers_version": "5.13.1",
|
||||
"use_cache": false,
|
||||
"vocab_size": 32768
|
||||
}
|
||||
10
last-checkpoint/generation_config.json
Normal file
10
last-checkpoint/generation_config.json
Normal file
@@ -0,0 +1,10 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"bos_token_id": 0,
|
||||
"eos_token_id": 0,
|
||||
"output_attentions": false,
|
||||
"output_hidden_states": false,
|
||||
"pad_token_id": 1,
|
||||
"transformers_version": "5.13.1",
|
||||
"use_cache": true
|
||||
}
|
||||
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 sha256:6670b37483d0b5e29b58d245c1746e00c887e871eef5a5a8ed2d9ed4bfd10e18
|
||||
size 4161036576
|
||||
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 sha256:31345cd76893333263772b127f09ab37bf24cd3f03ce84e09357b5270590937d
|
||||
size 8322168787
|
||||
3
last-checkpoint/rng_state.pth
Normal file
3
last-checkpoint/rng_state.pth
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:77ca98ed10a20c7ebf9c36ba9d30a165fa497f9abd0ea9c9b3aaf71be5943d05
|
||||
size 14645
|
||||
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 sha256:5d09db64044541a35294764f5d948f0482d36f836a748cc1119f3bcfe9d7f22b
|
||||
size 1465
|
||||
6370
last-checkpoint/trainer_state.json
Normal file
6370
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:e846a7d292f68b8582d5f303f02a1adce0cf5998bfbdccfe6132a58a5bb0f3a4
|
||||
size 5201
|
||||
Reference in New Issue
Block a user