初始化项目,由ModelHub XC社区提供模型

Model: cs-552-2026-theattentionseekers/general_knowledge_model
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-06-13 10:12:38 +08:00
commit bca1f29769
31 changed files with 153764 additions and 0 deletions

View File

@@ -0,0 +1,6 @@
{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}<|im_start|>system
You are solving a general knowledge multiple-choice benchmark. Choose the single best option from the listed options. If the question requires logic or calculation, you may think step-by-step before answering, with the reasoning wrapped in <think>...</think> tags, but keep your reasoning strictly concise (max 4000 tokens). Your final answer must ALWAYS be wrapped in exactly one LaTeX box, like \boxed{A}.<|im_end|>
{% endif %}<|im_start|>{{ message['role'] }}
{{ message['content'] }}<|im_end|>
{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant
{% endif %}

View File

@@ -0,0 +1,63 @@
{
"architectures": [
"Qwen3ForCausalLM"
],
"attention_bias": false,
"attention_dropout": 0.0,
"bos_token_id": null,
"dtype": "bfloat16",
"eos_token_id": 151645,
"head_dim": 128,
"hidden_act": "silu",
"hidden_size": 2048,
"initializer_range": 0.02,
"intermediate_size": 6144,
"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"
],
"max_position_embeddings": 40960,
"max_window_layers": 28,
"model_type": "qwen3",
"num_attention_heads": 16,
"num_hidden_layers": 28,
"num_key_value_heads": 8,
"pad_token_id": 151643,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"rope_theta": 1000000,
"rope_type": "default"
},
"sliding_window": null,
"tie_word_embeddings": true,
"transformers_version": "5.7.0",
"use_cache": false,
"use_sliding_window": false,
"vocab_size": 151936
}

View File

@@ -0,0 +1,12 @@
{
"do_sample": true,
"eos_token_id": [
151645,
151643
],
"pad_token_id": 151643,
"temperature": 0.6,
"top_k": 20,
"top_p": 0.95,
"transformers_version": "5.7.0"
}

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:657e0330141404bd24497f59371ac4c26a5c17060ed936305c7e9b6105467f06
size 14645

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:94945cd9e703c68a467d55ede62dcc6b791170b2da980d03b8779fe8333c731c
size 1465

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:be75606093db2094d7cd20f3c2f385c212750648bd6ea4fb2bf507a6a4c55506
size 11422650

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,
"local_files_only": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

File diff suppressed because it is too large Load Diff

View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:de9e0fa52b52fd893dc9365789e6afe10494029178f185a645e456c0d5ecf70e
size 7185