spaceguardian/AutismWenLLM
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: spaceguardian/AutismWenLLM
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-05 13:19:17 +08:00
commit d39d0cc660
11 changed files with 363 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

36
.gitattributes vendored Normal file
View File

@@ -0,0 +1,36 @@
*.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
tokenizer.json filter=lfs diff=lfs merge=lfs -text

29
config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"_name_or_path": "ura-hcmut/GemSUra-2B",
"architectures": [
"GemmaForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 2,
"eos_token_id": 1,
"head_dim": 256,
"hidden_act": "gelu",
"hidden_activation": "gelu_pytorch_tanh",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 16384,
"max_position_embeddings": 8192,
"model_type": "gemma",
"num_attention_heads": 8,
"num_hidden_layers": 18,
"num_key_value_heads": 1,
"pad_token_id": 0,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 10000.0,
"torch_dtype": "bfloat16",
"transformers_version": "4.42.4",
"use_cache": true,
"vocab_size": 256000
}

7
generation_config.json Normal file
View File

@@ -0,0 +1,7 @@
{
"_from_model_config": true,
"bos_token_id": 2,
"eos_token_id": 1,
"pad_token_id": 0,
"transformers_version": "4.42.4"
}

3
model-00001-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:dc4394d17488ddae5372f8dce325614948166b4be1e003a6fba5a36fde5011c7
size 1948291744

3
model-00002-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:75aeb6ad39543e853da6099a606239d0ac7fb72f03cfcd54054b67da28c3816c
size 1981891704

3
model-00003-of-00003.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:67bfe3e113ce26145d31db9b3aaa1f10852650bbc7ffbd81ca0ed278d97fffe4
size 1082180304

171
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,171 @@
{
"metadata": {
"total_size": 5012344832
},
"weight_map": {
"model.embed_tokens.weight": "model-00001-of-00003.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.14.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.15.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.16.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.17.input_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
"model.layers.5.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.6.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.7.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.8.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
"model.norm.weight": "model-00003-of-00003.safetensors"
}
}

34
special_tokens_map.json Normal file
View File

@@ -0,0 +1,34 @@
{
"additional_special_tokens": [
"<start_of_turn>",
"<end_of_turn>"
],
"bos_token": {
"content": "<bos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"eos_token": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"unk_token": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:17a91ce4908a747435938ec27fe0f811551fdc89a64222b539f8de528b7fd81b
size 17477957

3
tokenizer.model Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:61a7b147390c64585d6c3543dd6fc636906c9af3865a5548f27f31aee1d4c8e2
size 4241003

71
tokenizer_config.json Normal file
View File

@@ -0,0 +1,71 @@
{
"add_bos_token": true,
"add_eos_token": false,
"added_tokens_decoder": {
"0": {
"content": "<pad>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "<eos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "<bos>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "<unk>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"106": {
"content": "<start_of_turn>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"107": {
"content": "<end_of_turn>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"additional_special_tokens": [
"<start_of_turn>",
"<end_of_turn>"
],
"bos_token": "<bos>",
"clean_up_tokenization_spaces": false,
"eos_token": "<eos>",
"legacy": null,
"model_max_length": 1000000000000000019884624838656,
"pad_token": "<pad>",
"padding_side": "right",
"sp_model_kwargs": {},
"spaces_between_special_tokens": false,
"split_special_tokens": false,
"tokenizer_class": "GemmaTokenizer",
"unk_token": "<unk>",
"use_default_system_prompt": false
}