Dampfinchen
commited on
Commit
•
92fbf9e
1
Parent(s):
c40ef52
Upload 5 files
Browse files- config.json +1 -2
- generation_config.json +9 -0
- special_tokens_map.json +2 -14
- tokenizer.json +1 -0
- tokenizer_config.json +2 -1
config.json
CHANGED
@@ -1,5 +1,4 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "NousResearch/Meta-Llama-3-8B",
|
3 |
"architectures": [
|
4 |
"LlamaForCausalLM"
|
5 |
],
|
@@ -22,7 +21,7 @@
|
|
22 |
"rope_theta": 500000.0,
|
23 |
"tie_word_embeddings": false,
|
24 |
"torch_dtype": "bfloat16",
|
25 |
-
"transformers_version": "4.
|
26 |
"use_cache": true,
|
27 |
"vocab_size": 128256
|
28 |
}
|
|
|
1 |
{
|
|
|
2 |
"architectures": [
|
3 |
"LlamaForCausalLM"
|
4 |
],
|
|
|
21 |
"rope_theta": 500000.0,
|
22 |
"tie_word_embeddings": false,
|
23 |
"torch_dtype": "bfloat16",
|
24 |
+
"transformers_version": "4.40.0.dev0",
|
25 |
"use_cache": true,
|
26 |
"vocab_size": 128256
|
27 |
}
|
generation_config.json
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"bos_token_id": 128000,
|
3 |
+
"eos_token_id": [128001, 128009],
|
4 |
+
"do_sample": true,
|
5 |
+
"temperature": 0.6,
|
6 |
+
"max_length": 4096,
|
7 |
+
"top_p": 0.9,
|
8 |
+
"transformers_version": "4.40.0.dev0"
|
9 |
+
}
|
special_tokens_map.json
CHANGED
@@ -1,16 +1,4 @@
|
|
1 |
{
|
2 |
-
"bos_token":
|
3 |
-
|
4 |
-
"lstrip": false,
|
5 |
-
"normalized": false,
|
6 |
-
"rstrip": false,
|
7 |
-
"single_word": false
|
8 |
-
},
|
9 |
-
"eos_token": {
|
10 |
-
"content": "<|end_of_text|>",
|
11 |
-
"lstrip": false,
|
12 |
-
"normalized": false,
|
13 |
-
"rstrip": false,
|
14 |
-
"single_word": false
|
15 |
-
}
|
16 |
}
|
|
|
1 |
{
|
2 |
+
"bos_token": "<|begin_of_text|>",
|
3 |
+
"eos_token": "<|end_of_text|>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
4 |
}
|
tokenizer.json
CHANGED
@@ -2407,6 +2407,7 @@
|
|
2407 |
"end_of_word_suffix": null,
|
2408 |
"fuse_unk": false,
|
2409 |
"byte_fallback": false,
|
|
|
2410 |
"vocab": {
|
2411 |
"!": 0,
|
2412 |
"\"": 1,
|
|
|
2407 |
"end_of_word_suffix": null,
|
2408 |
"fuse_unk": false,
|
2409 |
"byte_fallback": false,
|
2410 |
+
"ignore_merges": true,
|
2411 |
"vocab": {
|
2412 |
"!": 0,
|
2413 |
"\"": 1,
|
tokenizer_config.json
CHANGED
@@ -2050,8 +2050,9 @@
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
|
|
2053 |
"clean_up_tokenization_spaces": true,
|
2054 |
-
"eos_token": "<|
|
2055 |
"model_input_names": [
|
2056 |
"input_ids",
|
2057 |
"attention_mask"
|
|
|
2050 |
}
|
2051 |
},
|
2052 |
"bos_token": "<|begin_of_text|>",
|
2053 |
+
"chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
|
2054 |
"clean_up_tokenization_spaces": true,
|
2055 |
+
"eos_token": "<|eot_id|>",
|
2056 |
"model_input_names": [
|
2057 |
"input_ids",
|
2058 |
"attention_mask"
|