VehaanS/hackathon-250m-precise-edge
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: VehaanS/hackathon-250m-precise-edge
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-31 14:14:19 +08:00
commit 639549834b
19 changed files with 502216 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

35
.gitattributes vendored Normal file
View File

@@ -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

32
config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "float32",
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2560,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 12,
"num_key_value_heads": 16,
"pad_token_id": 50256,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"tie_word_embeddings": false,
"transformers_version": "5.0.0",
"use_cache": false,
"vocab_size": 50257
}

10
generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 50256,
"transformers_version": "5.0.0",
"use_cache": true
}

32
last-checkpoint/config.json Normal file
View File

@@ -0,0 +1,32 @@
{
"architectures": [
"LlamaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 1,
"dtype": "float32",
"eos_token_id": 2,
"head_dim": 64,
"hidden_act": "silu",
"hidden_size": 1024,
"initializer_range": 0.02,
"intermediate_size": 2560,
"max_position_embeddings": 2048,
"mlp_bias": false,
"model_type": "llama",
"num_attention_heads": 16,
"num_hidden_layers": 12,
"num_key_value_heads": 16,
"pad_token_id": 50256,
"pretraining_tp": 1,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 10000.0,
"rope_type": "default"
},
"tie_word_embeddings": false,
"transformers_version": "5.0.0",
"use_cache": false,
"vocab_size": 50257
}

10
last-checkpoint/generation_config.json Normal file
View File

@@ -0,0 +1,10 @@
{
"_from_model_config": true,
"bos_token_id": 1,
"eos_token_id": 2,
"output_attentions": false,
"output_hidden_states": false,
"pad_token_id": 50256,
"transformers_version": "5.0.0",
"use_cache": true
}

3
last-checkpoint/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ef92379012a0eb4a1bbc1485a2dba1518618280ae738776b978db072ecd5c7d
size 990634176

3
last-checkpoint/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:73e4f05b688e55441d50f5fd6c2ea453f4f7bac5f232422530fe7bf65fea401a
size 810494987

3
last-checkpoint/rng_state_0.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:61e957b4cd785256be4cb26eb03060ef689e1d58f1766d7f26ca36a62bec4994
size 14917

3
last-checkpoint/rng_state_1.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:550c54d430b44b77b0abe44c6e3ceba90a155305315c081b7616b35e2c18d1ce
size 14917

3
last-checkpoint/scaler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f4aa03f6e0cd07cf67ce1fbe3101d545f5771ef9148b9debf02b11cf6948da5c
size 1383

3
last-checkpoint/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:7357b0acae3f133fb878c2c29157a12a3493879da935946a3c06d00de62b70c7
size 1465

250306
last-checkpoint/tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

12
last-checkpoint/tokenizer_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"errors": "replace",
"is_local": false,
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

1434
last-checkpoint/trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
last-checkpoint/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6f3b50b355ca385d3ebbe350c2d26ad0b4fc857a1d1eab815c13a2c78cdb0b90
size 5201

3
model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:1ef92379012a0eb4a1bbc1485a2dba1518618280ae738776b978db072ecd5c7d
size 990634176

250306
tokenizer.json Normal file
View File

File diff suppressed because it is too large Load Diff

12
tokenizer_config.json Normal file
View File

@@ -0,0 +1,12 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": "<|endoftext|>",
"eos_token": "<|endoftext|>",
"errors": "replace",
"is_local": false,
"model_max_length": 1024,
"pad_token": "<|endoftext|>",
"tokenizer_class": "GPT2Tokenizer",
"unk_token": "<|endoftext|>"
}

3
training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6f3b50b355ca385d3ebbe350c2d26ad0b4fc857a1d1eab815c13a2c78cdb0b90
size 5201