初始化项目,由ModelHub XC社区提供模型
Model: laion/delphi-9e19-p33m67-coldstart-magpie_lr5e6 Source: Original Platform
This commit is contained in:
7
checkpoint-S24107/chat_template.jinja
Normal file
7
checkpoint-S24107/chat_template.jinja
Normal file
@@ -0,0 +1,7 @@
|
||||
{{ '<|begin_of_text|>' }}{% if messages[0]['role'] == 'system' %}{% set loop_messages = messages[1:] %}{% set system_message = messages[0]['content'] %}{% else %}{% set loop_messages = messages %}{% endif %}{% if system_message is defined %}{{ '<|start_header_id|>system<|end_header_id|>
|
||||
|
||||
' + system_message + '<|eot_id|>' }}{% endif %}{% for message in loop_messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ '<|start_header_id|>user<|end_header_id|>
|
||||
|
||||
' + content + '<|eot_id|><|start_header_id|>assistant<|end_header_id|>
|
||||
|
||||
' }}{% elif message['role'] == 'assistant' %}{{ content + '<|eot_id|>' }}{% endif %}{% endfor %}
|
||||
59
checkpoint-S24107/config.json
Normal file
59
checkpoint-S24107/config.json
Normal file
@@ -0,0 +1,59 @@
|
||||
{
|
||||
"architectures": [
|
||||
"Qwen3ForCausalLM"
|
||||
],
|
||||
"attention_bias": false,
|
||||
"attention_dropout": 0.0,
|
||||
"bos_token_id": 128000,
|
||||
"decoder_start_token_id": 128000,
|
||||
"dtype": "bfloat16",
|
||||
"eos_token_id": 128009,
|
||||
"head_dim": 128,
|
||||
"hidden_act": "silu",
|
||||
"hidden_size": 1792,
|
||||
"initializer_range": 0.02,
|
||||
"intermediate_size": 7168,
|
||||
"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"
|
||||
],
|
||||
"max_position_embeddings": 4096,
|
||||
"max_window_layers": 28,
|
||||
"model_type": "qwen3",
|
||||
"no_bias": true,
|
||||
"num_attention_heads": 14,
|
||||
"num_hidden_layers": 18,
|
||||
"num_key_value_heads": 14,
|
||||
"pad_token_id": 128009,
|
||||
"rms_norm_eps": 1e-05,
|
||||
"rope_scaling": {
|
||||
"factor": 8.0,
|
||||
"high_freq_factor": 4.0,
|
||||
"low_freq_factor": 1.0,
|
||||
"original_max_position_embeddings": 8192,
|
||||
"rope_type": "llama3"
|
||||
},
|
||||
"rope_theta": 500000.0,
|
||||
"sliding_window": null,
|
||||
"tie_word_embeddings": false,
|
||||
"transformers_version": "4.57.6",
|
||||
"use_cache": false,
|
||||
"use_sliding_window": false,
|
||||
"vocab_size": 128256
|
||||
}
|
||||
15
checkpoint-S24107/generation_config.json
Normal file
15
checkpoint-S24107/generation_config.json
Normal file
@@ -0,0 +1,15 @@
|
||||
{
|
||||
"_from_model_config": true,
|
||||
"begin_suppress_tokens": [
|
||||
128000,
|
||||
128001
|
||||
],
|
||||
"bos_token_id": 128000,
|
||||
"decoder_start_token_id": 128000,
|
||||
"eos_token_id": [
|
||||
128009,
|
||||
128001
|
||||
],
|
||||
"pad_token_id": 128009,
|
||||
"transformers_version": "4.57.6"
|
||||
}
|
||||
3
checkpoint-S24107/model.safetensors
Normal file
3
checkpoint-S24107/model.safetensors
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:71506d17f6087092295a012136f843c37c62b3d50cd27f0e06eb1c62a433d315
|
||||
size 2769191992
|
||||
17
checkpoint-S24107/special_tokens_map.json
Normal file
17
checkpoint-S24107/special_tokens_map.json
Normal file
@@ -0,0 +1,17 @@
|
||||
{
|
||||
"bos_token": {
|
||||
"content": "<|begin_of_text|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"eos_token": {
|
||||
"content": "<|eot_id|>",
|
||||
"lstrip": false,
|
||||
"normalized": false,
|
||||
"rstrip": false,
|
||||
"single_word": false
|
||||
},
|
||||
"pad_token": "<|eot_id|>"
|
||||
}
|
||||
3
checkpoint-S24107/tokenizer.json
Normal file
3
checkpoint-S24107/tokenizer.json
Normal file
@@ -0,0 +1,3 @@
|
||||
version https://git-lfs.github.com/spec/v1
|
||||
oid sha256:a4badeeda359a84c6d9efca84271f5bb44396cb95e215b1864b763c35cc6f6c9
|
||||
size 17209844
|
||||
2065
checkpoint-S24107/tokenizer_config.json
Normal file
2065
checkpoint-S24107/tokenizer_config.json
Normal file
File diff suppressed because it is too large
Load Diff
Reference in New Issue
Block a user