chore: update README.md content
Browse files
README.md
CHANGED
|
@@ -1,15 +1,22 @@
|
|
| 1 |
---
|
| 2 |
base_model: ghost-x/ghost-8b-beta
|
| 3 |
language:
|
| 4 |
-
- en
|
| 5 |
- vi
|
|
|
|
| 6 |
- es
|
| 7 |
- pt
|
| 8 |
-
- de
|
| 9 |
-
- it
|
| 10 |
-
- fr
|
| 11 |
-
- ko
|
| 12 |
- zh
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 13 |
license: other
|
| 14 |
license_name: ghost-open-llms
|
| 15 |
license_link: https://ghost-x.org/ghost-open-llms-license
|
|
@@ -26,7 +33,7 @@ widget:
|
|
| 26 |
---
|
| 27 |
|
| 28 |
|
| 29 |
-
<p><img src="
|
| 30 |
|
| 31 |
A large language model was developed with goals including excellent multilingual support, superior knowledge capabilities and cost efficiency.
|
| 32 |
|
|
@@ -179,7 +186,7 @@ For direct use with `transformers`, you can easily get started with the followin
|
|
| 179 |
AutoTokenizer,
|
| 180 |
)
|
| 181 |
|
| 182 |
-
base_model = "ghost-x/ghost-8b-beta"
|
| 183 |
model = AutoModelForCausalLM.from_pretrained(
|
| 184 |
base_model,
|
| 185 |
torch_dtype=torch.bfloat16,
|
|
@@ -210,7 +217,7 @@ For direct use with `transformers`, you can easily get started with the followin
|
|
| 210 |
BitsAndBytesConfig,
|
| 211 |
)
|
| 212 |
|
| 213 |
-
base_model = "ghost-x/ghost-8b-beta"
|
| 214 |
bnb_config = BitsAndBytesConfig(
|
| 215 |
load_in_4bit=True,
|
| 216 |
bnb_4bit_quant_type="nf4",
|
|
@@ -432,7 +439,7 @@ For deployment, we recommend using vLLM. You can enable the long-context capabil
|
|
| 432 |
- Utilize vLLM to deploy your model. For instance, you can set up an openAI-like server using the command:
|
| 433 |
|
| 434 |
```bash
|
| 435 |
-
python -m vllm.entrypoints.openai.api_server --served-model-name ghost-8b-beta --model ghost-x/ghost-8b-beta
|
| 436 |
```
|
| 437 |
|
| 438 |
- Try it now:
|
|
|
|
| 1 |
---
|
| 2 |
base_model: ghost-x/ghost-8b-beta
|
| 3 |
language:
|
|
|
|
| 4 |
- vi
|
| 5 |
+
- ko
|
| 6 |
- es
|
| 7 |
- pt
|
|
|
|
|
|
|
|
|
|
|
|
|
| 8 |
- zh
|
| 9 |
+
- fr
|
| 10 |
+
- it
|
| 11 |
+
- de
|
| 12 |
+
- ja
|
| 13 |
+
- ru
|
| 14 |
+
- pl
|
| 15 |
+
- nl
|
| 16 |
+
- hi
|
| 17 |
+
- tr
|
| 18 |
+
- id
|
| 19 |
+
- en
|
| 20 |
license: other
|
| 21 |
license_name: ghost-open-llms
|
| 22 |
license_link: https://ghost-x.org/ghost-open-llms-license
|
|
|
|
| 33 |
---
|
| 34 |
|
| 35 |
|
| 36 |
+
<p><img src="https://ghost-x.org/docs/models/ghost-8b-beta/images/logo.jpeg" width="40%" align="center" /></p>
|
| 37 |
|
| 38 |
A large language model was developed with goals including excellent multilingual support, superior knowledge capabilities and cost efficiency.
|
| 39 |
|
|
|
|
| 186 |
AutoTokenizer,
|
| 187 |
)
|
| 188 |
|
| 189 |
+
base_model = "ghost-x/ghost-8b-beta-1608"
|
| 190 |
model = AutoModelForCausalLM.from_pretrained(
|
| 191 |
base_model,
|
| 192 |
torch_dtype=torch.bfloat16,
|
|
|
|
| 217 |
BitsAndBytesConfig,
|
| 218 |
)
|
| 219 |
|
| 220 |
+
base_model = "ghost-x/ghost-8b-beta-1608"
|
| 221 |
bnb_config = BitsAndBytesConfig(
|
| 222 |
load_in_4bit=True,
|
| 223 |
bnb_4bit_quant_type="nf4",
|
|
|
|
| 439 |
- Utilize vLLM to deploy your model. For instance, you can set up an openAI-like server using the command:
|
| 440 |
|
| 441 |
```bash
|
| 442 |
+
python -m vllm.entrypoints.openai.api_server --served-model-name ghost-8b-beta --model ghost-x/ghost-8b-beta-1608
|
| 443 |
```
|
| 444 |
|
| 445 |
- Try it now:
|