sequelbox commited on
Commit
5ab53f9
1 Parent(s): 5e49be0

46c59c884b6859208f322326f73ca9d97d08eda4563d679b6fe3c5212285aff6

Browse files
Files changed (4) hide show
  1. README.md +5 -4
  2. config.json +1 -1
  3. generation_config.json +1 -1
  4. tokenizer.json +1 -6
README.md CHANGED
@@ -23,7 +23,7 @@ tags:
23
  base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
24
  datasets:
25
  - sequelbox/Tachibana
26
- - LDJnr/Pure-Dove
27
  model_type: llama
28
  license: llama3.1
29
  ---
@@ -32,11 +32,12 @@ license: llama3.1
32
  Enigma is a code-instruct model built on Llama 3.1 8b.
33
  - High quality code instruct performance within the Llama 3 Instruct chat format
34
  - Finetuned on synthetic code-instruct data generated with Llama 3.1 405b. [Find the current version of the dataset here!](https://huggingface.co/datasets/sequelbox/Tachibana)
 
35
 
36
 
37
  ## Version
38
 
39
- This is the **2024-08-10** release of Enigma for Llama 3.1 8b.
40
 
41
  Help us and recommend Enigma to your friends! We're excited for more Enigma releases in the future.
42
 
@@ -73,9 +74,9 @@ print(outputs[0]["generated_text"][-1])
73
  ```
74
 
75
  ## The Model
76
- Enigma is built on top of Llama 3.1 8b Instruct, using code-instruct data to supplement code-instruct performance using Llama 3.1 Instruct prompt style.
77
 
78
- Our current version of the Enigma code-instruct dataset is [sequelbox/Tachibana](https://huggingface.co/datasets/sequelbox/Tachibana), supplemented with a small selection of data from [LDJnr/Pure-Dove](https://huggingface.co/datasets/LDJnr/Pure-Dove) for general chat consistency.
79
 
80
 
81
  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/VCJ8Fmefd8cdVhXSSxJiD.jpeg)
 
23
  base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
24
  datasets:
25
  - sequelbox/Tachibana
26
+ - sequelbox/Supernova
27
  model_type: llama
28
  license: llama3.1
29
  ---
 
32
  Enigma is a code-instruct model built on Llama 3.1 8b.
33
  - High quality code instruct performance within the Llama 3 Instruct chat format
34
  - Finetuned on synthetic code-instruct data generated with Llama 3.1 405b. [Find the current version of the dataset here!](https://huggingface.co/datasets/sequelbox/Tachibana)
35
+ - Overall chat performance supplemented with [generalist synthetic data.](https://huggingface.co/datasets/sequelbox/Supernova)
36
 
37
 
38
  ## Version
39
 
40
+ This is the **2024-09-04** release of Enigma for Llama 3.1 8b, enhancing code-instruct and general chat capabilities.
41
 
42
  Help us and recommend Enigma to your friends! We're excited for more Enigma releases in the future.
43
 
 
74
  ```
75
 
76
  ## The Model
77
+ Enigma is built on top of Llama 3.1 8b Instruct, using high quality code-instruct data and general chat data in Llama 3.1 Instruct prompt style to supplement overall performance.
78
 
79
+ Our current version of Enigma is trained on code-instruct data from [sequelbox/Tachibana](https://huggingface.co/datasets/sequelbox/Tachibana) and general chat data from [sequelbox/Supernova.](https://huggingface.co/datasets/sequelbox/Supernova)
80
 
81
 
82
  ![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/63444f2687964b331809eb55/VCJ8Fmefd8cdVhXSSxJiD.jpeg)
config.json CHANGED
@@ -33,7 +33,7 @@
33
  "rope_theta": 500000.0,
34
  "tie_word_embeddings": false,
35
  "torch_dtype": "float32",
36
- "transformers_version": "4.44.0",
37
  "use_cache": true,
38
  "vocab_size": 128256
39
  }
 
33
  "rope_theta": 500000.0,
34
  "tie_word_embeddings": false,
35
  "torch_dtype": "float32",
36
+ "transformers_version": "4.44.2",
37
  "use_cache": true,
38
  "vocab_size": 128256
39
  }
generation_config.json CHANGED
@@ -8,5 +8,5 @@
8
  ],
9
  "temperature": 0.6,
10
  "top_p": 0.9,
11
- "transformers_version": "4.44.0"
12
  }
 
8
  ],
9
  "temperature": 0.6,
10
  "top_p": 0.9,
11
+ "transformers_version": "4.44.2"
12
  }
tokenizer.json CHANGED
@@ -1,11 +1,6 @@
1
  {
2
  "version": "1.0",
3
- "truncation": {
4
- "direction": "Right",
5
- "max_length": 5450,
6
- "strategy": "LongestFirst",
7
- "stride": 0
8
- },
9
  "padding": null,
10
  "added_tokens": [
11
  {
 
1
  {
2
  "version": "1.0",
3
+ "truncation": null,
 
 
 
 
 
4
  "padding": null,
5
  "added_tokens": [
6
  {