Upload folder using huggingface_hub
Browse files- .gitattributes +2 -0
- added_tokens.json +3 -0
- config.json +77 -0
- config_sentence_transformers.json +20 -0
- merges.txt +0 -0
- model.onnx +3 -0
- model.onnx_data +3 -0
- modules.json +20 -0
- special_tokens_map.json +23 -0
- tokenizer.json +3 -0
- tokenizer_config.json +22 -0
- vocab.json +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
model.onnx_data filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"<|endoftext|>": 151643
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,77 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen2ForCausalLM"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 151643,
|
| 7 |
+
"eos_token_id": 151643,
|
| 8 |
+
"hidden_act": "silu",
|
| 9 |
+
"hidden_size": 1536,
|
| 10 |
+
"initializer_range": 0.02,
|
| 11 |
+
"intermediate_size": 8960,
|
| 12 |
+
"layer_types": [
|
| 13 |
+
"full_attention",
|
| 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 |
+
"full_attention",
|
| 33 |
+
"full_attention",
|
| 34 |
+
"full_attention",
|
| 35 |
+
"full_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"full_attention",
|
| 38 |
+
"full_attention",
|
| 39 |
+
"full_attention",
|
| 40 |
+
"full_attention"
|
| 41 |
+
],
|
| 42 |
+
"matryoshka_dims": [
|
| 43 |
+
64,
|
| 44 |
+
128,
|
| 45 |
+
256,
|
| 46 |
+
512,
|
| 47 |
+
896
|
| 48 |
+
],
|
| 49 |
+
"max_position_embeddings": 32768,
|
| 50 |
+
"max_window_layers": 28,
|
| 51 |
+
"model_type": "qwen2",
|
| 52 |
+
"num_attention_heads": 12,
|
| 53 |
+
"num_hidden_layers": 28,
|
| 54 |
+
"num_key_value_heads": 2,
|
| 55 |
+
"prompt_names": [
|
| 56 |
+
"query",
|
| 57 |
+
"passage"
|
| 58 |
+
],
|
| 59 |
+
"rms_norm_eps": 1e-06,
|
| 60 |
+
"rope_scaling": null,
|
| 61 |
+
"rope_theta": 1000000.0,
|
| 62 |
+
"sliding_window": null,
|
| 63 |
+
"task_names": [
|
| 64 |
+
"nl2code",
|
| 65 |
+
"qa",
|
| 66 |
+
"code2code",
|
| 67 |
+
"code2nl",
|
| 68 |
+
"code2completion"
|
| 69 |
+
],
|
| 70 |
+
"tie_word_embeddings": true,
|
| 71 |
+
"tokenizer_class": "Qwen2TokenizerFast",
|
| 72 |
+
"torch_dtype": "bfloat16",
|
| 73 |
+
"transformers_version": "4.55.4",
|
| 74 |
+
"use_cache": true,
|
| 75 |
+
"use_sliding_window": false,
|
| 76 |
+
"vocab_size": 151936
|
| 77 |
+
}
|
config_sentence_transformers.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"prompts": {
|
| 3 |
+
"nl2code_query": "Find the most relevant code snippet given the following query:\n",
|
| 4 |
+
"nl2code_document": "Candidate code snippet:\n",
|
| 5 |
+
|
| 6 |
+
"code2code_query": "Find an equivalent code snippet given the following code snippet:\n",
|
| 7 |
+
"code2code_document": "Candidate code snippet:\n",
|
| 8 |
+
|
| 9 |
+
"code2nl_query": "Find the most relevant comment given the following code snippet:\n",
|
| 10 |
+
"code2nl_document": "Candidate comment:\n",
|
| 11 |
+
|
| 12 |
+
"code2completion_query": "Find the most relevant completion given the following start of code snippet:\n",
|
| 13 |
+
"code2completion_document": "Candidate completion:\n",
|
| 14 |
+
|
| 15 |
+
"qa_query": "Find the most relevant answer given the following question:\n",
|
| 16 |
+
"qa_document": "Candidate answer:\n"
|
| 17 |
+
},
|
| 18 |
+
"default_prompt_name": null,
|
| 19 |
+
"similarity_fn_name": "cosine"
|
| 20 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model.onnx
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8d790bd99b41a7bd15ecd5f8662d9d1f5955fc6ec15c158272a8f79c2cc6ef5
|
| 3 |
+
size 1159485
|
model.onnx_data
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b71786dfc314773864223693641f240c9a9dc47a118275743eda3dcdc3debf8
|
| 3 |
+
size 6174857472
|
modules.json
ADDED
|
@@ -0,0 +1,20 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
[
|
| 2 |
+
{
|
| 3 |
+
"idx": 0,
|
| 4 |
+
"name": "0",
|
| 5 |
+
"path": "",
|
| 6 |
+
"type": "sentence_transformers.models.Transformer"
|
| 7 |
+
},
|
| 8 |
+
{
|
| 9 |
+
"idx": 1,
|
| 10 |
+
"name": "1",
|
| 11 |
+
"path": "1_Pooling",
|
| 12 |
+
"type": "sentence_transformers.models.Pooling"
|
| 13 |
+
},
|
| 14 |
+
{
|
| 15 |
+
"idx": 2,
|
| 16 |
+
"name": "2",
|
| 17 |
+
"path": "2_Normalize",
|
| 18 |
+
"type": "sentence_transformers.models.Normalize"
|
| 19 |
+
}
|
| 20 |
+
]
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"eos_token": {
|
| 3 |
+
"content": "<|endoftext|>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"pad_token": {
|
| 10 |
+
"content": "<|endoftext|>",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"unk_token": {
|
| 17 |
+
"content": "<|endoftext|>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
}
|
| 23 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0c3c6d1699d808eea431043c5d9db4e6c191698789c69a5d35f11aeabc2304a
|
| 3 |
+
size 11417884
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,22 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"151643": {
|
| 4 |
+
"content": "<|endoftext|>",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
}
|
| 11 |
+
},
|
| 12 |
+
"bos_token": null,
|
| 13 |
+
"clean_up_tokenization_spaces": false,
|
| 14 |
+
"eos_token": "<|endoftext|>",
|
| 15 |
+
"errors": "replace",
|
| 16 |
+
"extra_special_tokens": {},
|
| 17 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 18 |
+
"pad_token": "<|endoftext|>",
|
| 19 |
+
"split_special_tokens": false,
|
| 20 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 21 |
+
"unk_token": "<|endoftext|>"
|
| 22 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|