SicariusSicariiStuff/Assistant_Pepe_32B_GPTQ_AR_4-bit-128
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: SicariusSicariiStuff/Assistant_Pepe_32B_GPTQ_AR_4-bit-128
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-08-07 00:51:17 +08:00
commit f562a6df4b
28 changed files with 2348 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

11
README.md Normal file
View File

@@ -0,0 +1,11 @@
---
base_model:
- SicariusSicariiStuff/Assistant_Pepe_32B
datasets:
- SicariusSicariiStuff/UBW_Tapestries
language:
- en
library_name: transformers
license: apache-2.0
quantized_by: SicariusSicariiStuff
---

4
chat_template.jinja Normal file
View File

@@ -0,0 +1,4 @@
{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
' + message['content'] + '<|im_end|>' + '
'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
' }}{% endif %}

117
config.json Normal file
View File

@@ -0,0 +1,117 @@
{
"_name_or_path": "SicariusSicariiStuff/Assistant_Pepe_32B",
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": 151643,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 25600,
"layer_types": [
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention",
"full_attention"
],
"max_position_embeddings": 40960,
"max_window_layers": 64,
"model_type": "qwen3",
"num_attention_heads": 64,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"pad_token_id": null,
"quantization_config": {
"autoround_version": "0.12.0",
"batch_size": 1,
"bits": 4,
"damp_percent": 0.01,
"data_type": "int",
"desc_act": false,
"group_size": 128,
"lm_head": false,
"nsamples": 64,
"provider": "auto-round",
"quant_method": "gptq",
"seqlen": 512,
"sym": true,
"true_sequential": false
},
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": false,
"transformers_version": "5.5.4",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 151936,
"torch_dtype": "float16"
}

13
generation_config.json Normal file
View File

@@ -0,0 +1,13 @@
{
"bos_token_id": 151643,
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "5.5.4"
}

3
model-00001-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e3006029bb322c6bcdd840c3dea360f2593c77fb1362299ea8550b3e445766ec
size 1063442776

3
model-00002-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:4403e8d6b1d3a6c2994c47748f43b5c427409e2a4abdf9c5f48e41c248035a93
size 1014316856

3
model-00003-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:03938c99e820d52197944a064c6b04bad984adb7abd3e596a70b8f195557ef64
size 1014316928

3
model-00004-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0b94360543047fdf70b780e4c81e86e41c496300c4058a211f87e495232bdc45
size 1014316984

3
model-00005-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:0148c31f507068819b03ec39b16eb85c94069dc2222b1220ab42e097229925fb
size 1014316984

3
model-00006-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f3d0d87cb5cd9f990fad8f66fceddd3402d5dc165da6184f9084e38cc86e5fee
size 1014316984

3
model-00007-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:bf6d59f9f89863cb35b3e6c2fa7433da3a442c1e6a687869874954ec9000ca86
size 1014316984

3
model-00008-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:97d97f81840686fae22148d7f50ec680db82976112d9f8192902b11a3b4a72d1
size 1014316984

3
model-00009-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:948b7851525c1edba51e93ceeef4905c6b2f24a4d444d6dc0c522d9ffd9537c9
size 1014316984

3
model-00010-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a840abf1713ab552afbc33088636f951fda3603724494fbccff017bfef7b4a6b
size 1014316984

3
model-00011-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:14cf31ebcc8d64dd463e0edecc4235d3fcc92ef11981d4501dedfc5f69981837
size 1014316984

3
model-00012-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:669a71aa4ba66f12b402a0551f2877d9a7fc97d047587c023520bc3688734fcd
size 1014316984

3
model-00013-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:03e44a9a0177147057c7739a1c86ad3471762a25b2f11d9714baec2af701c334
size 1014316984

3
model-00014-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:94fa23688b69c62a79a8086882383db1959c12dad05b40cd5012ad8bf10ac8bd
size 1014316984

3
model-00015-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c8273e12cabddd870c1c71f8be515cac3332991df40df0626e400a1e729cdb96
size 1014316984

3
model-00016-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:e5c5d98f9081cc1b6a6c0d3d4389cd0f2b2f4eec5aed34eddf7f9069a46266a2
size 965191096

3
model-00017-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:a0915e898a17f315355f430e1aa7f5bbc9a713ba15f7d718b8e7625e2a7b440e
size 1555824752

3
model-00018-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:718dae4f5267d656754195edb97a1335b75a75337a90de8e6edc6bf19f9b75cb
size 10328

3
model-00019-of-00019.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:f3ae0cf6041aefde6d263aea4ef51f54f66033078349dd394852beb663f41c0a
size 1555824736

2061
model.safetensors.index.json Normal file
View File

File diff suppressed because it is too large Load Diff

16
quantization_config.json Normal file
View File

@@ -0,0 +1,16 @@
{
"bits": 4,
"data_type": "int",
"group_size": 128,
"sym": true,
"batch_size": 1,
"nsamples": 64,
"seqlen": 512,
"autoround_version": "0.12.0",
"lm_head": false,
"provider": "auto-round",
"quant_method": "gptq",
"desc_act": false,
"true_sequential": false,
"damp_percent": 0.01
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b064181fd20c7d19d5613f061552279d7dcbb8210ffde80386e2a9a6ddf996e7
size 11422748

30
tokenizer_config.json Normal file
View File

@@ -0,0 +1,30 @@
{
"add_prefix_space": false,
"backend": "tokenizers",
"bos_token": null,
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"is_local": true,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}