Upload folder using huggingface_hub
Browse files- .ipynb_checkpoints/added_tokens-checkpoint.json +5 -0
- .ipynb_checkpoints/mergekit_moe_config-checkpoint.yml +71 -0
- config.json +5 -5
- mergekit_moe_config.yml +63 -14
- model-00001-of-00005.safetensors +2 -2
- model-00002-of-00005.safetensors +1 -1
- model-00003-of-00005.safetensors +1 -1
- model-00004-of-00005.safetensors +1 -1
- model-00005-of-00005.safetensors +1 -1
- model.safetensors.index.json +0 -0
- special_tokens_map.json +1 -6
- tokenizer.json +0 -27
- tokenizer_config.json +5 -33
.ipynb_checkpoints/added_tokens-checkpoint.json
ADDED
@@ -0,0 +1,5 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"<sep>": 32002,
|
3 |
+
"<|end_of_turn|>": 32000,
|
4 |
+
"<|pad_0|>": 32001
|
5 |
+
}
|
.ipynb_checkpoints/mergekit_moe_config-checkpoint.yml
ADDED
@@ -0,0 +1,71 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model: chihoonlee10/T3Q-EN-DPO-Mistral-7B
|
2 |
+
gate_mode: cheap_embed # one of "hidden", "cheap_embed", or "random"
|
3 |
+
dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
|
4 |
+
## (optional)
|
5 |
+
experts_per_token: 2
|
6 |
+
experts:
|
7 |
+
- source_model: Kukedlc/Jupiter-k-7B-slerp
|
8 |
+
positive_prompts:
|
9 |
+
- "This puzzle involves identifying a repeating pattern. Can you analyze the examples and complete the missing element?"
|
10 |
+
- "These grids seem to follow a specific visual pattern. Can you analyze the examples and apply the pattern to solve the puzzle?"
|
11 |
+
- "Look for a consistent rule in how the elements are arranged. Can you use that rule to predict the missing element?"
|
12 |
+
- "This task requires applying logical deduction. Can you analyze the information and choose the answer that follows logically?"
|
13 |
+
- "Reason through the cause-and-effect relationships in the examples. Can you use that logic to solve the puzzle?"
|
14 |
+
- "Analyze the relationship between the input and output in the examples. Can you apply that relationship to solve the new problem?"
|
15 |
+
- "This puzzle requires modifying the image based on a specific rule. Can you analyze the changes in the examples and apply them to solve the puzzle?"
|
16 |
+
- "Focus on the visual changes demonstrated in the training examples. Can you replicate those changes to solve the new problem?"
|
17 |
+
- "This task involves manipulating shapes or colors based on a pattern. Can you analyze the examples and apply the pattern to the new image?"
|
18 |
+
- "These puzzles involve manipulating numbers according to a specific rule. Can you analyze the pattern and solve the missing number?"
|
19 |
+
- "Focus on the mathematical operations demonstrated in the examples. Can you apply those operations to solve the new equation?"
|
20 |
+
- "Look for relationships between the numbers in the training examples. Can you use that relationship to predict the missing number?"
|
21 |
+
- "This task requires understanding the arrangement of objects in space. Can you analyze the movement patterns in the examples and predict the next step?"
|
22 |
+
- "Focus on the spatial relationships between elements in the grids. Can you replicate those relationships to solve the new puzzle?"
|
23 |
+
- "Analyze the rotation, reflection, or translation demonstrated in the examples. Can you apply that manipulation to solve the new problem?"
|
24 |
+
- source_model: InferenceIllusionist/Excalibur-7b-DPO
|
25 |
+
positive_prompts:
|
26 |
+
- "This passage contains factual information. Can you summarize the key details about [topic]?"
|
27 |
+
- "Based on the information provided, what can you tell me about [entity]?"
|
28 |
+
- "Is the following statement true or false according to the passage: [statement]?"
|
29 |
+
- "What caused [event] to happen in the passage?"
|
30 |
+
- "Why did [character] take the action of [action]?"
|
31 |
+
- "If [condition] were true, what would likely happen next?"
|
32 |
+
- "How are [entity A] and [entity B] similar/different?"
|
33 |
+
- "Which option, [A] or [B], is more likely based on the information provided?"
|
34 |
+
- "Rank the following options ([list]) based on [criteria] according to the passage."
|
35 |
+
- "Does the following statement logically follow from the information provided: [statement]?"
|
36 |
+
- "Identify any inconsistencies or contradictions in the passage."
|
37 |
+
- "Can you draw a logical conclusion based on the evidence presented?"
|
38 |
+
- "What can be inferred about [concept] based on the information provided?"
|
39 |
+
- "What is the underlying meaning or implication of the author's statement?"
|
40 |
+
- "Can you fill in the blanks with the most likely word(s) based on the context?"
|
41 |
+
- "What are some potential consequences of [event]?"
|
42 |
+
- "Can you generate creative solutions to the problem presented in the passage?"
|
43 |
+
- "Based on the information provided, propose a course of action for [character]."
|
44 |
+
- source_model: yam-peleg/Experiment21-7B
|
45 |
+
positive_prompts:
|
46 |
+
- "Be truthful and objective in your response. Avoid speculation or making claims that cannot be verified."
|
47 |
+
- "Focus on providing factual information based on the evidence presented in the source material."
|
48 |
+
- "If you are unsure about something, it's okay to say 'I don't know' or 'I can't find information to support that claim'."
|
49 |
+
- "Be aware of potential biases in the source material and strive to present a neutral perspective."
|
50 |
+
- "If a source seems biased, identify the bias and consider alternative viewpoints."
|
51 |
+
- "Avoid using language that promotes stereotypes or prejudices."
|
52 |
+
- "Cite your sources when referencing information from external materials."
|
53 |
+
- "Acknowledge the limitations of your knowledge and the potential for different interpretations."
|
54 |
+
- "Be transparent about your confidence level in your answer."
|
55 |
+
- "Explain your reasoning process and how you arrived at your answer."
|
56 |
+
- "Provide evidence to support your claims whenever possible."
|
57 |
+
- "If there are multiple perspectives on an issue, present them fairly and objectively."
|
58 |
+
- source_model: senseable/WestLake-7B-v2
|
59 |
+
positive_prompts:
|
60 |
+
- "This sentence contains a pronoun ('he' or 'she'). Pay close attention to the context to determine who the pronoun refers to."
|
61 |
+
- "Identify the two potential referents for the pronoun ('he' or 'she') in this sentence. Analyze the context to choose the correct one."
|
62 |
+
- "This scenario describes two individuals. Use the information provided to understand who the pronoun refers to in the sentence."
|
63 |
+
- "Focus on the actions described in the sentence and the roles of the individuals involved. This will help determine the pronoun referent."
|
64 |
+
- "Analyze the relationship between the individuals mentioned in the sentence. The pronoun likely refers to the one performing the action."
|
65 |
+
- "Consider the animacy of the potential referents. Pronouns typically refer to animate beings (people or animals) in the context."
|
66 |
+
- "Don't rely solely on the pronoun itself. Utilize the entire sentence and surrounding context to understand its meaning."
|
67 |
+
- "Look for clues in the sentence that indicate who the pronoun refers to. This could include gender, possession, or actions described."
|
68 |
+
- "Imagine the scenario described in the sentence. Visualizing the situation can help you identify the intended referent."
|
69 |
+
- "Evaluate the plausibility of each potential referent for the pronoun. Choose the one that makes the most logical sense in the context."
|
70 |
+
- "Think about the actions described and the roles of the individuals involved. Does it make more sense for one or the other to perform the action?"
|
71 |
+
- "Consider the world knowledge you possess. Does the sentence describe a situation where one referent is more likely than the other?"
|
config.json
CHANGED
@@ -1,19 +1,19 @@
|
|
1 |
{
|
2 |
-
"_name_or_path": "
|
3 |
"architectures": [
|
4 |
"MixtralForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 1,
|
8 |
-
"eos_token_id":
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 4096,
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 14336,
|
13 |
-
"max_position_embeddings":
|
14 |
"model_type": "mixtral",
|
15 |
"num_attention_heads": 32,
|
16 |
-
"num_experts_per_tok":
|
17 |
"num_hidden_layers": 32,
|
18 |
"num_key_value_heads": 8,
|
19 |
"num_local_experts": 4,
|
@@ -26,5 +26,5 @@
|
|
26 |
"torch_dtype": "bfloat16",
|
27 |
"transformers_version": "4.39.3",
|
28 |
"use_cache": true,
|
29 |
-
"vocab_size":
|
30 |
}
|
|
|
1 |
{
|
2 |
+
"_name_or_path": "chihoonlee10/T3Q-EN-DPO-Mistral-7B",
|
3 |
"architectures": [
|
4 |
"MixtralForCausalLM"
|
5 |
],
|
6 |
"attention_dropout": 0.0,
|
7 |
"bos_token_id": 1,
|
8 |
+
"eos_token_id": 2,
|
9 |
"hidden_act": "silu",
|
10 |
"hidden_size": 4096,
|
11 |
"initializer_range": 0.02,
|
12 |
"intermediate_size": 14336,
|
13 |
+
"max_position_embeddings": 32768,
|
14 |
"model_type": "mixtral",
|
15 |
"num_attention_heads": 32,
|
16 |
+
"num_experts_per_tok": 2,
|
17 |
"num_hidden_layers": 32,
|
18 |
"num_key_value_heads": 8,
|
19 |
"num_local_experts": 4,
|
|
|
26 |
"torch_dtype": "bfloat16",
|
27 |
"transformers_version": "4.39.3",
|
28 |
"use_cache": true,
|
29 |
+
"vocab_size": 32000
|
30 |
}
|
mergekit_moe_config.yml
CHANGED
@@ -1,22 +1,71 @@
|
|
1 |
-
base_model:
|
2 |
gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
|
3 |
dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
|
4 |
## (optional)
|
5 |
-
experts_per_token:
|
6 |
experts:
|
7 |
-
- source_model:
|
8 |
positive_prompts:
|
9 |
-
|
10 |
-
|
11 |
-
|
12 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
13 |
positive_prompts:
|
14 |
-
|
15 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
16 |
positive_prompts:
|
17 |
-
|
18 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
19 |
positive_prompts:
|
20 |
-
|
21 |
-
|
22 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
base_model: chihoonlee10/T3Q-EN-DPO-Mistral-7B
|
2 |
gate_mode: hidden # one of "hidden", "cheap_embed", or "random"
|
3 |
dtype: bfloat16 # output dtype (float32, float16, or bfloat16)
|
4 |
## (optional)
|
5 |
+
experts_per_token: 2
|
6 |
experts:
|
7 |
+
- source_model: Kukedlc/Jupiter-k-7B-slerp
|
8 |
positive_prompts:
|
9 |
+
- "This puzzle involves identifying a repeating pattern. Can you analyze the examples and complete the missing element?"
|
10 |
+
- "These grids seem to follow a specific visual pattern. Can you analyze the examples and apply the pattern to solve the puzzle?"
|
11 |
+
- "Look for a consistent rule in how the elements are arranged. Can you use that rule to predict the missing element?"
|
12 |
+
- "This task requires applying logical deduction. Can you analyze the information and choose the answer that follows logically?"
|
13 |
+
- "Reason through the cause-and-effect relationships in the examples. Can you use that logic to solve the puzzle?"
|
14 |
+
- "Analyze the relationship between the input and output in the examples. Can you apply that relationship to solve the new problem?"
|
15 |
+
- "This puzzle requires modifying the image based on a specific rule. Can you analyze the changes in the examples and apply them to solve the puzzle?"
|
16 |
+
- "Focus on the visual changes demonstrated in the training examples. Can you replicate those changes to solve the new problem?"
|
17 |
+
- "This task involves manipulating shapes or colors based on a pattern. Can you analyze the examples and apply the pattern to the new image?"
|
18 |
+
- "These puzzles involve manipulating numbers according to a specific rule. Can you analyze the pattern and solve the missing number?"
|
19 |
+
- "Focus on the mathematical operations demonstrated in the examples. Can you apply those operations to solve the new equation?"
|
20 |
+
- "Look for relationships between the numbers in the training examples. Can you use that relationship to predict the missing number?"
|
21 |
+
- "This task requires understanding the arrangement of objects in space. Can you analyze the movement patterns in the examples and predict the next step?"
|
22 |
+
- "Focus on the spatial relationships between elements in the grids. Can you replicate those relationships to solve the new puzzle?"
|
23 |
+
- "Analyze the rotation, reflection, or translation demonstrated in the examples. Can you apply that manipulation to solve the new problem?"
|
24 |
+
- source_model: InferenceIllusionist/Excalibur-7b-DPO
|
25 |
positive_prompts:
|
26 |
+
- "This passage contains factual information. Can you summarize the key details about [topic]?"
|
27 |
+
- "Based on the information provided, what can you tell me about [entity]?"
|
28 |
+
- "Is the following statement true or false according to the passage: [statement]?"
|
29 |
+
- "What caused [event] to happen in the passage?"
|
30 |
+
- "Why did [character] take the action of [action]?"
|
31 |
+
- "If [condition] were true, what would likely happen next?"
|
32 |
+
- "How are [entity A] and [entity B] similar/different?"
|
33 |
+
- "Which option, [A] or [B], is more likely based on the information provided?"
|
34 |
+
- "Rank the following options ([list]) based on [criteria] according to the passage."
|
35 |
+
- "Does the following statement logically follow from the information provided: [statement]?"
|
36 |
+
- "Identify any inconsistencies or contradictions in the passage."
|
37 |
+
- "Can you draw a logical conclusion based on the evidence presented?"
|
38 |
+
- "What can be inferred about [concept] based on the information provided?"
|
39 |
+
- "What is the underlying meaning or implication of the author's statement?"
|
40 |
+
- "Can you fill in the blanks with the most likely word(s) based on the context?"
|
41 |
+
- "What are some potential consequences of [event]?"
|
42 |
+
- "Can you generate creative solutions to the problem presented in the passage?"
|
43 |
+
- "Based on the information provided, propose a course of action for [character]."
|
44 |
+
- source_model: yam-peleg/Experiment21-7B
|
45 |
positive_prompts:
|
46 |
+
- "Be truthful and objective in your response. Avoid speculation or making claims that cannot be verified."
|
47 |
+
- "Focus on providing factual information based on the evidence presented in the source material."
|
48 |
+
- "If you are unsure about something, it's okay to say 'I don't know' or 'I can't find information to support that claim'."
|
49 |
+
- "Be aware of potential biases in the source material and strive to present a neutral perspective."
|
50 |
+
- "If a source seems biased, identify the bias and consider alternative viewpoints."
|
51 |
+
- "Avoid using language that promotes stereotypes or prejudices."
|
52 |
+
- "Cite your sources when referencing information from external materials."
|
53 |
+
- "Acknowledge the limitations of your knowledge and the potential for different interpretations."
|
54 |
+
- "Be transparent about your confidence level in your answer."
|
55 |
+
- "Explain your reasoning process and how you arrived at your answer."
|
56 |
+
- "Provide evidence to support your claims whenever possible."
|
57 |
+
- "If there are multiple perspectives on an issue, present them fairly and objectively."
|
58 |
+
- source_model: senseable/WestLake-7B-v2
|
59 |
positive_prompts:
|
60 |
+
- "This sentence contains a pronoun ('he' or 'she'). Pay close attention to the context to determine who the pronoun refers to."
|
61 |
+
- "Identify the two potential referents for the pronoun ('he' or 'she') in this sentence. Analyze the context to choose the correct one."
|
62 |
+
- "This scenario describes two individuals. Use the information provided to understand who the pronoun refers to in the sentence."
|
63 |
+
- "Focus on the actions described in the sentence and the roles of the individuals involved. This will help determine the pronoun referent."
|
64 |
+
- "Analyze the relationship between the individuals mentioned in the sentence. The pronoun likely refers to the one performing the action."
|
65 |
+
- "Consider the animacy of the potential referents. Pronouns typically refer to animate beings (people or animals) in the context."
|
66 |
+
- "Don't rely solely on the pronoun itself. Utilize the entire sentence and surrounding context to understand its meaning."
|
67 |
+
- "Look for clues in the sentence that indicate who the pronoun refers to. This could include gender, possession, or actions described."
|
68 |
+
- "Imagine the scenario described in the sentence. Visualizing the situation can help you identify the intended referent."
|
69 |
+
- "Evaluate the plausibility of each potential referent for the pronoun. Choose the one that makes the most logical sense in the context."
|
70 |
+
- "Think about the actions described and the roles of the individuals involved. Does it make more sense for one or the other to perform the action?"
|
71 |
+
- "Consider the world knowledge you possess. Does the sentence describe a situation where one referent is more likely than the other?"
|
model-00001-of-00005.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b3391957ad1fcacac319678cbc5d2a3871e854c8eb5abedf19d46d8a4c0fba14
|
3 |
+
size 9919666872
|
model-00002-of-00005.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9898670488
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1f41a8f5ae493bf80ce115a3c436537dae54ed8a09540d80a5103251c432147f
|
3 |
size 9898670488
|
model-00003-of-00005.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9982573720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:2d6695ac15e3bf03106ae33f695710a8d8807d227010123e2e3e5e8759211972
|
3 |
size 9982573720
|
model-00004-of-00005.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 9982573720
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e227e74b71acecaf8d2572590f2861f4cd5812738ea3d437ac920c91429624cc
|
3 |
size 9982573720
|
model-00005-of-00005.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 8523972544
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb15c9ac1d085517ea659cb20cebc463b4cf896586bcf9f60456a6c12da0c39c
|
3 |
size 8523972544
|
model.safetensors.index.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
special_tokens_map.json
CHANGED
@@ -1,8 +1,4 @@
|
|
1 |
{
|
2 |
-
"additional_special_tokens": [
|
3 |
-
"<|end_of_turn|>",
|
4 |
-
"<|pad_0|>"
|
5 |
-
],
|
6 |
"bos_token": {
|
7 |
"content": "<s>",
|
8 |
"lstrip": false,
|
@@ -11,14 +7,13 @@
|
|
11 |
"single_word": false
|
12 |
},
|
13 |
"eos_token": {
|
14 |
-
"content": "
|
15 |
"lstrip": false,
|
16 |
"normalized": false,
|
17 |
"rstrip": false,
|
18 |
"single_word": false
|
19 |
},
|
20 |
"pad_token": "<s>",
|
21 |
-
"sep_token": "<sep>",
|
22 |
"unk_token": {
|
23 |
"content": "<unk>",
|
24 |
"lstrip": false,
|
|
|
1 |
{
|
|
|
|
|
|
|
|
|
2 |
"bos_token": {
|
3 |
"content": "<s>",
|
4 |
"lstrip": false,
|
|
|
7 |
"single_word": false
|
8 |
},
|
9 |
"eos_token": {
|
10 |
+
"content": "</s>",
|
11 |
"lstrip": false,
|
12 |
"normalized": false,
|
13 |
"rstrip": false,
|
14 |
"single_word": false
|
15 |
},
|
16 |
"pad_token": "<s>",
|
|
|
17 |
"unk_token": {
|
18 |
"content": "<unk>",
|
19 |
"lstrip": false,
|
tokenizer.json
CHANGED
@@ -36,33 +36,6 @@
|
|
36 |
"rstrip": false,
|
37 |
"normalized": false,
|
38 |
"special": true
|
39 |
-
},
|
40 |
-
{
|
41 |
-
"id": 32000,
|
42 |
-
"content": "<|end_of_turn|>",
|
43 |
-
"single_word": false,
|
44 |
-
"lstrip": false,
|
45 |
-
"rstrip": false,
|
46 |
-
"normalized": false,
|
47 |
-
"special": true
|
48 |
-
},
|
49 |
-
{
|
50 |
-
"id": 32001,
|
51 |
-
"content": "<|pad_0|>",
|
52 |
-
"single_word": false,
|
53 |
-
"lstrip": false,
|
54 |
-
"rstrip": false,
|
55 |
-
"normalized": false,
|
56 |
-
"special": true
|
57 |
-
},
|
58 |
-
{
|
59 |
-
"id": 32002,
|
60 |
-
"content": "<sep>",
|
61 |
-
"single_word": false,
|
62 |
-
"lstrip": false,
|
63 |
-
"rstrip": false,
|
64 |
-
"normalized": false,
|
65 |
-
"special": true
|
66 |
}
|
67 |
],
|
68 |
"normalizer": {
|
|
|
36 |
"rstrip": false,
|
37 |
"normalized": false,
|
38 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
39 |
}
|
40 |
],
|
41 |
"normalizer": {
|
tokenizer_config.json
CHANGED
@@ -25,47 +25,19 @@
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
28 |
-
},
|
29 |
-
"32000": {
|
30 |
-
"content": "<|end_of_turn|>",
|
31 |
-
"lstrip": false,
|
32 |
-
"normalized": false,
|
33 |
-
"rstrip": false,
|
34 |
-
"single_word": false,
|
35 |
-
"special": true
|
36 |
-
},
|
37 |
-
"32001": {
|
38 |
-
"content": "<|pad_0|>",
|
39 |
-
"lstrip": false,
|
40 |
-
"normalized": false,
|
41 |
-
"rstrip": false,
|
42 |
-
"single_word": false,
|
43 |
-
"special": true
|
44 |
-
},
|
45 |
-
"32002": {
|
46 |
-
"content": "<sep>",
|
47 |
-
"lstrip": false,
|
48 |
-
"normalized": false,
|
49 |
-
"rstrip": false,
|
50 |
-
"single_word": false,
|
51 |
-
"special": true
|
52 |
}
|
53 |
},
|
54 |
-
"additional_special_tokens": [
|
55 |
-
"<|end_of_turn|>",
|
56 |
-
"<|pad_0|>"
|
57 |
-
],
|
58 |
"bos_token": "<s>",
|
59 |
-
"chat_template": "{{ bos_token }}{% for message in messages %}{{ 'GPT4 Correct ' + message['role'].title() + ': ' + message['content'] + '<|end_of_turn|>'}}{% endfor %}{% if add_generation_prompt %}{{ 'GPT4 Correct Assistant:' }}{% endif %}",
|
60 |
"clean_up_tokenization_spaces": false,
|
61 |
-
"eos_token": "
|
62 |
"legacy": true,
|
63 |
-
"model_max_length":
|
64 |
"pad_token": "<s>",
|
65 |
-
"
|
66 |
"sp_model_kwargs": {},
|
67 |
"spaces_between_special_tokens": false,
|
68 |
"tokenizer_class": "LlamaTokenizer",
|
69 |
"unk_token": "<unk>",
|
70 |
-
"use_default_system_prompt":
|
71 |
}
|
|
|
25 |
"rstrip": false,
|
26 |
"single_word": false,
|
27 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
}
|
29 |
},
|
30 |
+
"additional_special_tokens": [],
|
|
|
|
|
|
|
31 |
"bos_token": "<s>",
|
|
|
32 |
"clean_up_tokenization_spaces": false,
|
33 |
+
"eos_token": "</s>",
|
34 |
"legacy": true,
|
35 |
+
"model_max_length": 32768,
|
36 |
"pad_token": "<s>",
|
37 |
+
"padding_side": "left",
|
38 |
"sp_model_kwargs": {},
|
39 |
"spaces_between_special_tokens": false,
|
40 |
"tokenizer_class": "LlamaTokenizer",
|
41 |
"unk_token": "<unk>",
|
42 |
+
"use_default_system_prompt": false
|
43 |
}
|