Instructions to use aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold with Transformers:

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

pipe = pipeline("text-generation", model="aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold")
model = AutoModelForCausalLM.from_pretrained("aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.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(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold

SGLang

How to use aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold 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 "aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold" \
    --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": "aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold" \
        --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": "aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold with Docker Model Runner:
```
docker model run hf.co/aneeshm44/gpt-oss-92b-dynamic-pruning-98-threshold
```

aneeshm44 commited on Apr 22

Commit

a347dae

verified ·

1 Parent(s): 1a339ad

Upload pruning_summary.json with huggingface_hub

Browse files

Files changed (1) hide show

pruning_summary.json +265 -0

pruning_summary.json ADDED Viewed

	@@ -0,0 +1,265 @@

+{
+  "source_model_path": "/data/aneesh/gpt_oss_120b",
+  "mapping_path": "/data/aneesh/aimo/pruning/mappings/expert_mapping_120b_mxfp4_new_large.json",
+  "save_path": "models/threshold_98",
+  "threshold": 98.0,
+  "num_layers": 36,
+  "num_output_shards": 15,
+  "written_tensor_count": 687,
+  "pruned_tensor_count": 288,
+  "copied_tensor_count": 399,
+  "layer_stats": [
+    {
+      "layer": 0,
+      "total_experts": 128,
+      "needed": 114,
+      "pct_used": 89.0625,
+      "never_used": 0
+    },
+    {
+      "layer": 1,
+      "total_experts": 128,
+      "needed": 111,
+      "pct_used": 86.71875,
+      "never_used": 0
+    },
+    {
+      "layer": 2,
+      "total_experts": 128,
+      "needed": 102,
+      "pct_used": 79.6875,
+      "never_used": 0
+    },
+    {
+      "layer": 3,
+      "total_experts": 128,
+      "needed": 100,
+      "pct_used": 78.125,
+      "never_used": 0
+    },
+    {
+      "layer": 4,
+      "total_experts": 128,
+      "needed": 102,
+      "pct_used": 79.6875,
+      "never_used": 0
+    },
+    {
+      "layer": 5,
+      "total_experts": 128,
+      "needed": 107,
+      "pct_used": 83.59375,
+      "never_used": 0
+    },
+    {
+      "layer": 6,
+      "total_experts": 128,
+      "needed": 106,
+      "pct_used": 82.8125,
+      "never_used": 0
+    },
+    {
+      "layer": 7,
+      "total_experts": 128,
+      "needed": 102,
+      "pct_used": 79.6875,
+      "never_used": 0
+    },
+    {
+      "layer": 8,
+      "total_experts": 128,
+      "needed": 101,
+      "pct_used": 78.90625,
+      "never_used": 0
+    },
+    {
+      "layer": 9,
+      "total_experts": 128,
+      "needed": 98,
+      "pct_used": 76.5625,
+      "never_used": 0
+    },
+    {
+      "layer": 10,
+      "total_experts": 128,
+      "needed": 92,
+      "pct_used": 71.875,
+      "never_used": 0
+    },
+    {
+      "layer": 11,
+      "total_experts": 128,
+      "needed": 84,
+      "pct_used": 65.625,
+      "never_used": 0
+    },
+    {
+      "layer": 12,
+      "total_experts": 128,
+      "needed": 92,
+      "pct_used": 71.875,
+      "never_used": 0
+    },
+    {
+      "layer": 13,
+      "total_experts": 128,
+      "needed": 89,
+      "pct_used": 69.53125,
+      "never_used": 0
+    },
+    {
+      "layer": 14,
+      "total_experts": 128,
+      "needed": 98,
+      "pct_used": 76.5625,
+      "never_used": 0
+    },
+    {
+      "layer": 15,
+      "total_experts": 128,
+      "needed": 100,
+      "pct_used": 78.125,
+      "never_used": 0
+    },
+    {
+      "layer": 16,
+      "total_experts": 128,
+      "needed": 97,
+      "pct_used": 75.78125,
+      "never_used": 0
+    },
+    {
+      "layer": 17,
+      "total_experts": 128,
+      "needed": 100,
+      "pct_used": 78.125,
+      "never_used": 0
+    },
+    {
+      "layer": 18,
+      "total_experts": 128,
+      "needed": 103,
+      "pct_used": 80.46875,
+      "never_used": 0
+    },
+    {
+      "layer": 19,
+      "total_experts": 128,
+      "needed": 100,
+      "pct_used": 78.125,
+      "never_used": 0
+    },
+    {
+      "layer": 20,
+      "total_experts": 128,
+      "needed": 104,
+      "pct_used": 81.25,
+      "never_used": 0
+    },
+    {
+      "layer": 21,
+      "total_experts": 128,
+      "needed": 102,
+      "pct_used": 79.6875,
+      "never_used": 0
+    },
+    {
+      "layer": 22,
+      "total_experts": 128,
+      "needed": 103,
+      "pct_used": 80.46875,
+      "never_used": 0
+    },
+    {
+      "layer": 23,
+      "total_experts": 128,
+      "needed": 99,
+      "pct_used": 77.34375,
+      "never_used": 0
+    },
+    {
+      "layer": 24,
+      "total_experts": 128,
+      "needed": 101,
+      "pct_used": 78.90625,
+      "never_used": 0
+    },
+    {
+      "layer": 25,
+      "total_experts": 128,
+      "needed": 101,
+      "pct_used": 78.90625,
+      "never_used": 0
+    },
+    {
+      "layer": 26,
+      "total_experts": 128,
+      "needed": 101,
+      "pct_used": 78.90625,
+      "never_used": 0
+    },
+    {
+      "layer": 27,
+      "total_experts": 128,
+      "needed": 102,
+      "pct_used": 79.6875,
+      "never_used": 0
+    },
+    {
+      "layer": 28,
+      "total_experts": 128,
+      "needed": 97,
+      "pct_used": 75.78125,
+      "never_used": 0
+    },
+    {
+      "layer": 29,
+      "total_experts": 128,
+      "needed": 100,
+      "pct_used": 78.125,
+      "never_used": 0
+    },
+    {
+      "layer": 30,
+      "total_experts": 128,
+      "needed": 104,
+      "pct_used": 81.25,
+      "never_used": 0
+    },
+    {
+      "layer": 31,
+      "total_experts": 128,
+      "needed": 113,
+      "pct_used": 88.28125,
+      "never_used": 0
+    },
+    {
+      "layer": 32,
+      "total_experts": 128,
+      "needed": 102,
+      "pct_used": 79.6875,
+      "never_used": 0
+    },
+    {
+      "layer": 33,
+      "total_experts": 128,
+      "needed": 93,
+      "pct_used": 72.65625,
+      "never_used": 0
+    },
+    {
+      "layer": 34,
+      "total_experts": 128,
+      "needed": 94,
+      "pct_used": 73.4375,
+      "never_used": 0
+    },
+    {
+      "layer": 35,
+      "total_experts": 128,
+      "needed": 82,
+      "pct_used": 64.0625,
+      "never_used": 1
+    }
+  ]
+}