cs-552-2026-the-transformers/general_knowledge_model
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: cs-552-2026-the-transformers/general_knowledge_model
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-20 05:53:10 +08:00
commit e7f998cf6d
98 changed files with 32335 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
checkpoint-7136/chat_template.jinja Normal file
View File

@@ -0,0 +1,13 @@
{%- if messages[0]['role'] == 'system' %}
{%- set loop_messages = messages[1:] %}
{{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
{%- else %}
{%- set loop_messages = messages %}
{{- '<|im_start|>system\n' + "You are a knowledgeable assistant. For multiple-choice questions, write ONLY the letter of the correct answer inside \\boxed{}." + '<|im_end|>\n' }}
{%- endif %}
{%- for message in loop_messages %}
{{- '<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>\n' }}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- endif %}

63
checkpoint-7136/config.json Normal file
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
}

12
checkpoint-7136/generation_config.json Normal file
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"
}

3
checkpoint-7136/model.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:530f552bb2a5eaf1eaa4ff6ca6f9e4197c9f515754ef8fe0e7c6526fedd160d6
size 3441185608

3
checkpoint-7136/optimizer.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:6a2433f98e74e6c0a46cff3df29cb206fbe0d750801ef640c8d3379f56c20316
size 6882572207

3
checkpoint-7136/rng_state.pth Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:61c19bab1174704a4a4441475683bf1270277af15d2e2c95e964789128e482c4
size 14645

3
checkpoint-7136/scheduler.pt Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:77b2bcd6a6fe7f9904d15dd735af201ee67fe2aaf90996e4ebb4a9c178aacf7d
size 1465

3
checkpoint-7136/tokenizer.json Normal file
View File

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

30
checkpoint-7136/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": false,
"local_files_only": false,
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

7164
checkpoint-7136/trainer_state.json Normal file
View File

File diff suppressed because it is too large Load Diff

3
checkpoint-7136/training_args.bin Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3c570d44b5dfac423532e77f40f4b5a1be2f35231009d8aad93eb07d41a9a26c
size 5713