Instructions to use drisspg/float8_dynamic_act_float8_weight-opt-125m with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use drisspg/float8_dynamic_act_float8_weight-opt-125m with Transformers:

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

pipe = pipeline("text-generation", model="drisspg/float8_dynamic_act_float8_weight-opt-125m")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("drisspg/float8_dynamic_act_float8_weight-opt-125m")
model = AutoModelForCausalLM.from_pretrained("drisspg/float8_dynamic_act_float8_weight-opt-125m")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use drisspg/float8_dynamic_act_float8_weight-opt-125m with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "drisspg/float8_dynamic_act_float8_weight-opt-125m"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "drisspg/float8_dynamic_act_float8_weight-opt-125m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/drisspg/float8_dynamic_act_float8_weight-opt-125m

SGLang

How to use drisspg/float8_dynamic_act_float8_weight-opt-125m 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 "drisspg/float8_dynamic_act_float8_weight-opt-125m" \
    --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": "drisspg/float8_dynamic_act_float8_weight-opt-125m",
		"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 "drisspg/float8_dynamic_act_float8_weight-opt-125m" \
        --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": "drisspg/float8_dynamic_act_float8_weight-opt-125m",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use drisspg/float8_dynamic_act_float8_weight-opt-125m with Docker Model Runner:
```
docker model run hf.co/drisspg/float8_dynamic_act_float8_weight-opt-125m
```

drisspg commited on Mar 19, 2025

Commit

de4b3d0

verified ·

1 Parent(s): 7739f5e

Upload OPTForCausalLM

Browse files

Files changed (1) hide show

config.json +27 -25

config.json CHANGED Viewed

@@ -26,33 +26,35 @@
     "modules_to_not_convert": null,
     "quant_method": "torchao",
     "quant_type": {
-      "_data": {
-        "activation_dtype": {
-          "_data": "float8_e4m3fn",
-          "_type": "torch.dtype"
-        },
-        "granularity": {
-          "_data": {},
-          "_type": "PerRow",
-          "_version": 1
-        },
-        "mm_config": {
-          "_data": {
-            "emulate": false,
-            "pad_inner_dim": false,
-            "use_fast_accum": true
           },
-          "_type": "Float8MMConfig",
-          "_version": 1
         },
-        "set_inductor_config": true,
-        "weight_dtype": {
-          "_data": "float8_e4m3fn",
-          "_type": "torch.dtype"
-        }
-      },
-      "_type": "Float8DynamicActivationFloat8WeightConfig",
-      "_version": 1
     },
     "quant_type_kwargs": {}
   },

     "modules_to_not_convert": null,
     "quant_method": "torchao",
     "quant_type": {
+      "default": {
+        "_data": {
+          "activation_dtype": {
+            "_data": "float8_e4m3fn",
+            "_type": "torch.dtype"
+          },
+          "granularity": {
+            "_data": {},
+            "_type": "PerRow",
+            "_version": 1
+          },
+          "mm_config": {
+            "_data": {
+              "emulate": false,
+              "pad_inner_dim": false,
+              "use_fast_accum": true
+            },
+            "_type": "Float8MMConfig",
+            "_version": 1
           },
+          "set_inductor_config": true,
+          "weight_dtype": {
+            "_data": "float8_e4m3fn",
+            "_type": "torch.dtype"
+          }
         },
+        "_type": "Float8DynamicActivationFloat8WeightConfig",
+        "_version": 1
+      }
     },
     "quant_type_kwargs": {}
   },