Instructions to use LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT")

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT

SGLang

How to use LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT with Docker Model Runner:
```
docker model run hf.co/LeroyDyer/_Spydaz_Web_AI_MistralStar_4BIT
```

LeroyDyer commited on Jul 21, 2024

Commit

88ef2e1

verified ·

1 Parent(s): b7636d1

Upload 4 files

Browse files

Files changed (2) hide show

configuration_mistral.py +4 -5
modeling_mistral.py +0 -0

configuration_mistral.py CHANGED Viewed

@@ -14,8 +14,8 @@
 # limitations under the License.
 """Mistral model configuration"""
-from transformers.configuration_utils import PretrainedConfig
-from transformers.utils import logging
 logger = logging.get_logger(__name__)
@@ -116,7 +116,7 @@ class MistralConfig(PretrainedConfig):
         rope_theta=10000.0,
         sliding_window=4096,
         attention_dropout=0.0,
-        max_thoughts=16,thought_length = 1024,
         merged_talk_heads=True,
         merged_lm_and_talk_heads=False,
         merged_lm_and_think_heads=True,
@@ -148,7 +148,6 @@ class MistralConfig(PretrainedConfig):
         self.rope_theta = rope_theta
         self.attention_dropout = attention_dropout
         self.max_thoughts = max_thoughts
-        self.thought_length = thought_length
         self.merged_talk_heads = merged_talk_heads
         self.merged_lm_and_talk_heads = merged_lm_and_talk_heads
         self.merged_lm_and_think_heads = merged_lm_and_think_heads
@@ -262,7 +261,7 @@ class MistralStarConfig(PretrainedConfig):
         sliding_window=4096,
         attention_dropout=0.0,
         max_thoughts=16,
-        thought_length = 1024,
         merged_talk_heads=True,
         merged_lm_and_talk_heads=False,
         merged_lm_and_think_heads=True,

 # limitations under the License.
 """Mistral model configuration"""
+from ...configuration_utils import PretrainedConfig
+from ...utils import logging
 logger = logging.get_logger(__name__)
         rope_theta=10000.0,
         sliding_window=4096,
         attention_dropout=0.0,
+        max_thoughts=16,
         merged_talk_heads=True,
         merged_lm_and_talk_heads=False,
         merged_lm_and_think_heads=True,
         self.rope_theta = rope_theta
         self.attention_dropout = attention_dropout
         self.max_thoughts = max_thoughts
         self.merged_talk_heads = merged_talk_heads
         self.merged_lm_and_talk_heads = merged_lm_and_talk_heads
         self.merged_lm_and_think_heads = merged_lm_and_think_heads
         sliding_window=4096,
         attention_dropout=0.0,
         max_thoughts=16,
+        thought_length = 10,
         merged_talk_heads=True,
         merged_lm_and_talk_heads=False,
         merged_lm_and_think_heads=True,

modeling_mistral.py CHANGED Viewed

The diff for this file is too large to render. See raw diff