Instructions to use furproxy/9b-88 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use furproxy/9b-88 with Transformers:

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

pipe = pipeline("image-text-to-text", model="furproxy/9b-88")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForImageTextToText

processor = AutoProcessor.from_pretrained("furproxy/9b-88")
model = AutoModelForImageTextToText.from_pretrained("furproxy/9b-88")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use furproxy/9b-88 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "furproxy/9b-88"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "furproxy/9b-88",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/furproxy/9b-88

SGLang

How to use furproxy/9b-88 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 "furproxy/9b-88" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "furproxy/9b-88",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

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 "furproxy/9b-88" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "furproxy/9b-88",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use furproxy/9b-88 with Docker Model Runner:
```
docker model run hf.co/furproxy/9b-88
```

furproxy commited on Apr 22

Commit

ecdaafc

verified ·

1 Parent(s): 1aebfff

Upload folder using huggingface_hub

Browse files

Files changed (8) hide show

.ipynb_checkpoints/README-checkpoint.md +3 -3
README.md +3 -3
all_results.json +5 -5
model.safetensors +1 -1
train_results.json +5 -5
trainer_log.jsonl +0 -0
trainer_state.json +0 -0
training_loss.png +0 -0

.ipynb_checkpoints/README-checkpoint.md CHANGED Viewed

@@ -37,12 +37,12 @@ More information needed
 The following hyperparameters were used during training:
 - family_to_muon_lr = {
         "language": _fallback(getattr(training_args, "language_muon_lr", 2e-5), language_lr),
-        "vision": _fallback(getattr(training_args, "vision_muon_lr", 4e-5), vision_lr),
-        "merger": _fallback(getattr(training_args, "merger_muon_lr", 2e-5), merger_lr),
     }
     family_to_adamw_lr = {
-        "language": _fallback(getattr(training_args, "language_adamw_lr", 1e-5), language_lr),
         "vision": _fallback(getattr(training_args, "vision_adamw_lr", 5e-6), vision_lr),
         "merger": _fallback(getattr(training_args, "merger_adamw_lr", 1e-5), merger_lr),
     }

 The following hyperparameters were used during training:
 - family_to_muon_lr = {
         "language": _fallback(getattr(training_args, "language_muon_lr", 2e-5), language_lr),
+        "vision": _fallback(getattr(training_args, "vision_muon_lr", 2e-5), vision_lr),
+        "merger": _fallback(getattr(training_args, "merger_muon_lr", 4e-5), merger_lr),
     }
     family_to_adamw_lr = {
+        "language": _fallback(getattr(training_args, "language_adamw_lr", 5e-6), language_lr),
         "vision": _fallback(getattr(training_args, "vision_adamw_lr", 5e-6), vision_lr),
         "merger": _fallback(getattr(training_args, "merger_adamw_lr", 1e-5), merger_lr),
     }

README.md CHANGED Viewed

@@ -37,12 +37,12 @@ More information needed
 The following hyperparameters were used during training:
 - family_to_muon_lr = {
         "language": _fallback(getattr(training_args, "language_muon_lr", 2e-5), language_lr),
-        "vision": _fallback(getattr(training_args, "vision_muon_lr", 4e-5), vision_lr),
-        "merger": _fallback(getattr(training_args, "merger_muon_lr", 2e-5), merger_lr),
     }
     family_to_adamw_lr = {
-        "language": _fallback(getattr(training_args, "language_adamw_lr", 1e-5), language_lr),
         "vision": _fallback(getattr(training_args, "vision_adamw_lr", 5e-6), vision_lr),
         "merger": _fallback(getattr(training_args, "merger_adamw_lr", 1e-5), merger_lr),
     }

 The following hyperparameters were used during training:
 - family_to_muon_lr = {
         "language": _fallback(getattr(training_args, "language_muon_lr", 2e-5), language_lr),
+        "vision": _fallback(getattr(training_args, "vision_muon_lr", 2e-5), vision_lr),
+        "merger": _fallback(getattr(training_args, "merger_muon_lr", 4e-5), merger_lr),
     }
     family_to_adamw_lr = {
+        "language": _fallback(getattr(training_args, "language_adamw_lr", 5e-6), language_lr),
         "vision": _fallback(getattr(training_args, "vision_adamw_lr", 5e-6), vision_lr),
         "merger": _fallback(getattr(training_args, "merger_adamw_lr", 1e-5), merger_lr),
     }

all_results.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
-    "effective_tokens_per_sec": 7286.899729026163,
     "epoch": 4.0,
     "total_flos": 3.4175049861232067e+18,
-    "train_loss": 0.7562091423920304,
-    "train_runtime": 9085.3052,
-    "train_samples_per_second": 5.957,
-    "train_steps_per_second": 0.199
 }

 {
+    "effective_tokens_per_sec": 8369.940564234135,
     "epoch": 4.0,
     "total_flos": 3.4175049861232067e+18,
+    "train_loss": 0.8386258969696222,
+    "train_runtime": 7909.6987,
+    "train_samples_per_second": 6.842,
+    "train_steps_per_second": 0.228
 }

model.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f61c55ce28d865474bb9f937dbfd9678293a9ff5a565896f364808ef09aa8e31
 size 20859273368

 version https://git-lfs.github.com/spec/v1
+oid sha256:29a3829346071e30b1ef236360853099f0ee06d5c8dea2b9e2d7eaa0a4b2a8e6
 size 20859273368

train_results.json CHANGED Viewed

@@ -1,9 +1,9 @@
 {
-    "effective_tokens_per_sec": 7286.899729026163,
     "epoch": 4.0,
     "total_flos": 3.4175049861232067e+18,
-    "train_loss": 0.7562091423920304,
-    "train_runtime": 9085.3052,
-    "train_samples_per_second": 5.957,
-    "train_steps_per_second": 0.199
 }

 {
+    "effective_tokens_per_sec": 8369.940564234135,
     "epoch": 4.0,
     "total_flos": 3.4175049861232067e+18,
+    "train_loss": 0.8386258969696222,
+    "train_runtime": 7909.6987,
+    "train_samples_per_second": 6.842,
+    "train_steps_per_second": 0.228
 }

trainer_log.jsonl CHANGED Viewed

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

trainer_state.json CHANGED Viewed

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

training_loss.png CHANGED Viewed