Upload 7 files
Browse files- chat_template.jinja +4 -0
- config.json +51 -0
- generation_config.json +9 -0
- model.safetensors +3 -0
- special_tokens_map.json +9 -0
- tokenizer.json +0 -0
- tokenizer_config.json +12 -0
chat_template.jinja
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{% for message in messages %}{{ '<|im_start|>' + message['role'] + '
|
| 2 |
+
' + message['content'] + '<|im_end|>
|
| 3 |
+
' }}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
|
| 4 |
+
' }}{% endif %}
|
config.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": null,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"eos_token_id": 3,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 1152,
|
| 11 |
+
"initializer_range": 0.02,
|
| 12 |
+
"intermediate_size": 3072,
|
| 13 |
+
"layer_types": [
|
| 14 |
+
"full_attention",
|
| 15 |
+
"full_attention",
|
| 16 |
+
"full_attention",
|
| 17 |
+
"full_attention",
|
| 18 |
+
"full_attention",
|
| 19 |
+
"full_attention",
|
| 20 |
+
"full_attention",
|
| 21 |
+
"full_attention",
|
| 22 |
+
"full_attention",
|
| 23 |
+
"full_attention",
|
| 24 |
+
"full_attention",
|
| 25 |
+
"full_attention",
|
| 26 |
+
"full_attention",
|
| 27 |
+
"full_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"full_attention",
|
| 30 |
+
"full_attention",
|
| 31 |
+
"full_attention"
|
| 32 |
+
],
|
| 33 |
+
"max_position_embeddings": 4096,
|
| 34 |
+
"max_window_layers": 28,
|
| 35 |
+
"model_type": "qwen2",
|
| 36 |
+
"num_attention_heads": 16,
|
| 37 |
+
"num_hidden_layers": 18,
|
| 38 |
+
"num_key_value_heads": 8,
|
| 39 |
+
"pad_token_id": 0,
|
| 40 |
+
"rms_norm_eps": 1e-06,
|
| 41 |
+
"rope_parameters": {
|
| 42 |
+
"rope_theta": 10000.0,
|
| 43 |
+
"rope_type": "default"
|
| 44 |
+
},
|
| 45 |
+
"sliding_window": null,
|
| 46 |
+
"tie_word_embeddings": true,
|
| 47 |
+
"transformers_version": "5.14.1",
|
| 48 |
+
"use_cache": false,
|
| 49 |
+
"use_sliding_window": false,
|
| 50 |
+
"vocab_size": 16384
|
| 51 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": 3,
|
| 4 |
+
"output_attentions": false,
|
| 5 |
+
"output_hidden_states": false,
|
| 6 |
+
"pad_token_id": 0,
|
| 7 |
+
"transformers_version": "5.14.1",
|
| 8 |
+
"use_cache": true
|
| 9 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a08eb32d21c83ad1f0d0ab0cb8f1313c4555197f5ea01b20952fd074b3f07351
|
| 3 |
+
size 1126924520
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": "<|im_end|>",
|
| 3 |
+
"pad_token": "<pad>",
|
| 4 |
+
"unk_token": "<unk>",
|
| 5 |
+
"additional_special_tokens": [
|
| 6 |
+
"<|im_start|>",
|
| 7 |
+
"<|im_end|>"
|
| 8 |
+
]
|
| 9 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"backend": "tokenizers",
|
| 3 |
+
"eos_token": "<|im_end|>",
|
| 4 |
+
"pad_token": "<pad>",
|
| 5 |
+
"unk_token": "<unk>",
|
| 6 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
| 7 |
+
"model_max_length": 4096,
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|im_start|>",
|
| 10 |
+
"<|im_end|>"
|
| 11 |
+
]
|
| 12 |
+
}
|