Update tiny models for Starcoder2Model
Browse files- config.json +32 -0
- model.safetensors +3 -0
- tokenizer.json +0 -0
- tokenizer_config.json +55 -0
config.json
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Starcoder2Model"
|
| 4 |
+
],
|
| 5 |
+
"attention_dropout": 0.0,
|
| 6 |
+
"bos_token_id": 0,
|
| 7 |
+
"dtype": "float32",
|
| 8 |
+
"embedding_dropout": 0.0,
|
| 9 |
+
"eos_token_id": 0,
|
| 10 |
+
"hidden_act": "gelu",
|
| 11 |
+
"hidden_size": 32,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 32,
|
| 14 |
+
"max_position_embeddings": 512,
|
| 15 |
+
"model_type": "starcoder2",
|
| 16 |
+
"norm_epsilon": 1e-05,
|
| 17 |
+
"num_attention_heads": 2,
|
| 18 |
+
"num_hidden_layers": 2,
|
| 19 |
+
"num_key_value_heads": 2,
|
| 20 |
+
"pad_token_id": 0,
|
| 21 |
+
"residual_dropout": 0.0,
|
| 22 |
+
"rope_parameters": {
|
| 23 |
+
"rope_theta": 10000.0,
|
| 24 |
+
"rope_type": "default"
|
| 25 |
+
},
|
| 26 |
+
"sliding_window": null,
|
| 27 |
+
"tie_word_embeddings": false,
|
| 28 |
+
"transformers_version": "5.16.0.dev0",
|
| 29 |
+
"use_bias": true,
|
| 30 |
+
"use_cache": true,
|
| 31 |
+
"vocab_size": 49152
|
| 32 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6db918cb812f2d3a2c53e21e124c325383ddb30548a8d45b45696b378fb39b4
|
| 3 |
+
size 6346784
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,55 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
| 4 |
+
"bos_token": "<|endoftext|>",
|
| 5 |
+
"clean_up_tokenization_spaces": true,
|
| 6 |
+
"eos_token": "<|endoftext|>",
|
| 7 |
+
"errors": "replace",
|
| 8 |
+
"extra_special_tokens": [
|
| 9 |
+
"<|endoftext|>",
|
| 10 |
+
"<fim_prefix>",
|
| 11 |
+
"<fim_middle>",
|
| 12 |
+
"<fim_suffix>",
|
| 13 |
+
"<fim_pad>",
|
| 14 |
+
"<repo_name>",
|
| 15 |
+
"<file_sep>",
|
| 16 |
+
"<issue_start>",
|
| 17 |
+
"<issue_comment>",
|
| 18 |
+
"<issue_closed>",
|
| 19 |
+
"<jupyter_start>",
|
| 20 |
+
"<jupyter_text>",
|
| 21 |
+
"<jupyter_code>",
|
| 22 |
+
"<jupyter_output>",
|
| 23 |
+
"<jupyter_script>",
|
| 24 |
+
"<empty_output>",
|
| 25 |
+
"<code_to_intermediate>",
|
| 26 |
+
"<intermediate_to_code>",
|
| 27 |
+
"<pr>",
|
| 28 |
+
"<pr_status>",
|
| 29 |
+
"<pr_is_merged>",
|
| 30 |
+
"<pr_base>",
|
| 31 |
+
"<pr_file>",
|
| 32 |
+
"<pr_base_code>",
|
| 33 |
+
"<pr_diff>",
|
| 34 |
+
"<pr_diff_hunk>",
|
| 35 |
+
"<pr_comment>",
|
| 36 |
+
"<pr_event_id>",
|
| 37 |
+
"<pr_review>",
|
| 38 |
+
"<pr_review_state>",
|
| 39 |
+
"<pr_review_comment>",
|
| 40 |
+
"<pr_in_reply_to_review_id>",
|
| 41 |
+
"<pr_in_reply_to_comment_id>",
|
| 42 |
+
"<pr_diff_hunk_comment_line>",
|
| 43 |
+
"<NAME>",
|
| 44 |
+
"<EMAIL>",
|
| 45 |
+
"<KEY>",
|
| 46 |
+
"<PASSWORD>"
|
| 47 |
+
],
|
| 48 |
+
"is_local": true,
|
| 49 |
+
"local_files_only": false,
|
| 50 |
+
"model_max_length": 512,
|
| 51 |
+
"pad_token": null,
|
| 52 |
+
"tokenizer_class": "GPT2Tokenizer",
|
| 53 |
+
"unk_token": "<|endoftext|>",
|
| 54 |
+
"vocab_size": 49152
|
| 55 |
+
}
|