lamhieu commited on
Commit
4f481d7
β€’
1 Parent(s): fe37b81

chore: update README.md content

Browse files
Files changed (1) hide show
  1. README.md +30 -5
README.md CHANGED
@@ -48,7 +48,7 @@ The Ghost 8B Beta model outperforms prominent models such as Llama 3.1 8B Instru
48
 
49
  ### Updates
50
 
51
- * **16 Aug 2024**: The model has been released to version 160824, expanding support from 9 languages ​​to 16 languages. The model has improved math, reasoning, and following instructions better than the previous version.
52
 
53
  ### Thoughts
54
 
@@ -77,18 +77,19 @@ We believe that it is possible to optimize language models that are not too larg
77
 
78
  We create many distributions to give you the best access options that best suit your needs.
79
 
80
- | Version | Model card |
81
- | ------- | ------------------------------------------------------------------- |
82
  | BF16 | [πŸ€— HuggingFace](https://huggingface.co/ghost-x/ghost-8b-beta-1608) |
83
  | GGUF | [πŸ€— HuggingFace](https://huggingface.co/ghost-x/ghost-8b-beta-1608-gguf) |
84
  | AWQ | [πŸ€— HuggingFace](https://huggingface.co/ghost-x/ghost-8b-beta-1608-awq) |
 
85
 
86
  ### License
87
 
88
  The Ghost 8B Beta model is released under the [Ghost Open LLMs LICENSE](https://ghost-x.org/ghost-open-llms-license), [Llama 3 LICENSE](https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE).
89
 
90
- * For individuals, the model is free to use for personal and research purposes.
91
- * For commercial use of Ghost 8B Beta, it's also free, but please contact us for confirmation. You can email us at "lamhieu.vk [at] gmail.com" with a brief introduction of your project. If possible, include your logo so we can feature it as a case study. We will confirm your permission to use the model. For commercial use as a service, no email confirmation is needed, but we'd appreciate a notification so we can keep track and potentially recommend your services to partners using the model.
92
 
93
  Additionally, it would be great if you could mention or credit the model when it benefits your work.
94
 
@@ -304,6 +305,30 @@ For direct use with `unsloth`, you can easily get started with the following ste
304
  print(results)
305
  ```
306
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
307
  ### Instructions
308
 
309
  Here are specific instructions and explanations for each use case.
 
48
 
49
  ### Updates
50
 
51
+ - **16 Aug 2024**: The model has been released to version 160824, expanding support from 9 languages ​​to 16 languages. The model has improved math, reasoning, and following instructions better than the previous version.
52
 
53
  ### Thoughts
54
 
 
77
 
78
  We create many distributions to give you the best access options that best suit your needs.
79
 
80
+ | Version | Model card |
81
+ | ------- | ------------------------------------------------------------------------ |
82
  | BF16 | [πŸ€— HuggingFace](https://huggingface.co/ghost-x/ghost-8b-beta-1608) |
83
  | GGUF | [πŸ€— HuggingFace](https://huggingface.co/ghost-x/ghost-8b-beta-1608-gguf) |
84
  | AWQ | [πŸ€— HuggingFace](https://huggingface.co/ghost-x/ghost-8b-beta-1608-awq) |
85
+ | MLX | [πŸ€— HuggingFace](https://huggingface.co/ghost-x/ghost-8b-beta-1608-mlx) |
86
 
87
  ### License
88
 
89
  The Ghost 8B Beta model is released under the [Ghost Open LLMs LICENSE](https://ghost-x.org/ghost-open-llms-license), [Llama 3 LICENSE](https://huggingface.co/meta-llama/Meta-Llama-3-8B/blob/main/LICENSE).
90
 
91
+ - For individuals, the model is free to use for personal and research purposes.
92
+ - For commercial use of Ghost 8B Beta, it's also free, but please contact us for confirmation. You can email us at "lamhieu.vk [at] gmail.com" with a brief introduction of your project. If possible, include your logo so we can feature it as a case study. We will confirm your permission to use the model. For commercial use as a service, no email confirmation is needed, but we'd appreciate a notification so we can keep track and potentially recommend your services to partners using the model.
93
 
94
  Additionally, it would be great if you could mention or credit the model when it benefits your work.
95
 
 
305
  print(results)
306
  ```
307
 
308
+ #### Use with MLX
309
+
310
+ For direct use with `mlx`, you can easily get started with the following steps.
311
+
312
+ - Firstly, you need to install unsloth via the command below with `pip`.
313
+
314
+ ```bash
315
+ pip install mlx-lm
316
+ ```
317
+
318
+ - Right now, you can start using the model directly.
319
+ ```python
320
+ from mlx_lm import load, generate
321
+
322
+ model, tokenizer = load("ghost-x/ghost-8b-beta-1608-mlx")
323
+ messages = [
324
+ {"role": "system", "content": ""},
325
+ {"role": "user", "content": "Why is the sky blue ?"},
326
+ ]
327
+ prompt = tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
328
+ response = generate(model, tokenizer, prompt=prompt, verbose=True)
329
+ ```
330
+
331
+
332
  ### Instructions
333
 
334
  Here are specific instructions and explanations for each use case.