Instructions to use RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic")
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, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic")
model = AutoModelForMultimodalLM.from_pretrained("RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic", device_map="auto")
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 RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic

SGLang

How to use RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic 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 "RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic" \
    --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": "RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic",
		"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 "RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic" \
        --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": "RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic with Docker Model Runner:
```
docker model run hf.co/RedHatAI/Ministral-3-14B-Instruct-2512-FP8-dynamic
```

ChibuUkachi commited on Jan 30

Commit

2949aa9

verified ·

1 Parent(s): c7cc540

Upload folder using huggingface_hub

Browse files

Files changed (5) hide show

config.json +160 -0
consolidated.safetensors +2 -2
model.safetensors +3 -0
params.json +160 -0
recipe.yaml +1 -1

config.json CHANGED Viewed

@@ -219,6 +219,166 @@
       "model.multi_modal_projector.patch_merger.merging_layer",
       "model.multi_modal_projector.linear_1",
       "model.multi_modal_projector.linear_2",
       "lm_head"
     ],
     "kv_cache_scheme": null,

       "model.multi_modal_projector.patch_merger.merging_layer",
       "model.multi_modal_projector.linear_1",
       "model.multi_modal_projector.linear_2",
+      "model.language_model.layers.0.self_attn.q_proj",
+      "model.language_model.layers.0.self_attn.k_proj",
+      "model.language_model.layers.0.self_attn.v_proj",
+      "model.language_model.layers.0.self_attn.o_proj",
+      "model.language_model.layers.1.self_attn.q_proj",
+      "model.language_model.layers.1.self_attn.k_proj",
+      "model.language_model.layers.1.self_attn.v_proj",
+      "model.language_model.layers.1.self_attn.o_proj",
+      "model.language_model.layers.2.self_attn.q_proj",
+      "model.language_model.layers.2.self_attn.k_proj",
+      "model.language_model.layers.2.self_attn.v_proj",
+      "model.language_model.layers.2.self_attn.o_proj",
+      "model.language_model.layers.3.self_attn.q_proj",
+      "model.language_model.layers.3.self_attn.k_proj",
+      "model.language_model.layers.3.self_attn.v_proj",
+      "model.language_model.layers.3.self_attn.o_proj",
+      "model.language_model.layers.4.self_attn.q_proj",
+      "model.language_model.layers.4.self_attn.k_proj",
+      "model.language_model.layers.4.self_attn.v_proj",
+      "model.language_model.layers.4.self_attn.o_proj",
+      "model.language_model.layers.5.self_attn.q_proj",
+      "model.language_model.layers.5.self_attn.k_proj",
+      "model.language_model.layers.5.self_attn.v_proj",
+      "model.language_model.layers.5.self_attn.o_proj",
+      "model.language_model.layers.6.self_attn.q_proj",
+      "model.language_model.layers.6.self_attn.k_proj",
+      "model.language_model.layers.6.self_attn.v_proj",
+      "model.language_model.layers.6.self_attn.o_proj",
+      "model.language_model.layers.7.self_attn.q_proj",
+      "model.language_model.layers.7.self_attn.k_proj",
+      "model.language_model.layers.7.self_attn.v_proj",
+      "model.language_model.layers.7.self_attn.o_proj",
+      "model.language_model.layers.8.self_attn.q_proj",
+      "model.language_model.layers.8.self_attn.k_proj",
+      "model.language_model.layers.8.self_attn.v_proj",
+      "model.language_model.layers.8.self_attn.o_proj",
+      "model.language_model.layers.9.self_attn.q_proj",
+      "model.language_model.layers.9.self_attn.k_proj",
+      "model.language_model.layers.9.self_attn.v_proj",
+      "model.language_model.layers.9.self_attn.o_proj",
+      "model.language_model.layers.10.self_attn.q_proj",
+      "model.language_model.layers.10.self_attn.k_proj",
+      "model.language_model.layers.10.self_attn.v_proj",
+      "model.language_model.layers.10.self_attn.o_proj",
+      "model.language_model.layers.11.self_attn.q_proj",
+      "model.language_model.layers.11.self_attn.k_proj",
+      "model.language_model.layers.11.self_attn.v_proj",
+      "model.language_model.layers.11.self_attn.o_proj",
+      "model.language_model.layers.12.self_attn.q_proj",
+      "model.language_model.layers.12.self_attn.k_proj",
+      "model.language_model.layers.12.self_attn.v_proj",
+      "model.language_model.layers.12.self_attn.o_proj",
+      "model.language_model.layers.13.self_attn.q_proj",
+      "model.language_model.layers.13.self_attn.k_proj",
+      "model.language_model.layers.13.self_attn.v_proj",
+      "model.language_model.layers.13.self_attn.o_proj",
+      "model.language_model.layers.14.self_attn.q_proj",
+      "model.language_model.layers.14.self_attn.k_proj",
+      "model.language_model.layers.14.self_attn.v_proj",
+      "model.language_model.layers.14.self_attn.o_proj",
+      "model.language_model.layers.15.self_attn.q_proj",
+      "model.language_model.layers.15.self_attn.k_proj",
+      "model.language_model.layers.15.self_attn.v_proj",
+      "model.language_model.layers.15.self_attn.o_proj",
+      "model.language_model.layers.16.self_attn.q_proj",
+      "model.language_model.layers.16.self_attn.k_proj",
+      "model.language_model.layers.16.self_attn.v_proj",
+      "model.language_model.layers.16.self_attn.o_proj",
+      "model.language_model.layers.17.self_attn.q_proj",
+      "model.language_model.layers.17.self_attn.k_proj",
+      "model.language_model.layers.17.self_attn.v_proj",
+      "model.language_model.layers.17.self_attn.o_proj",
+      "model.language_model.layers.18.self_attn.q_proj",
+      "model.language_model.layers.18.self_attn.k_proj",
+      "model.language_model.layers.18.self_attn.v_proj",
+      "model.language_model.layers.18.self_attn.o_proj",
+      "model.language_model.layers.19.self_attn.q_proj",
+      "model.language_model.layers.19.self_attn.k_proj",
+      "model.language_model.layers.19.self_attn.v_proj",
+      "model.language_model.layers.19.self_attn.o_proj",
+      "model.language_model.layers.20.self_attn.q_proj",
+      "model.language_model.layers.20.self_attn.k_proj",
+      "model.language_model.layers.20.self_attn.v_proj",
+      "model.language_model.layers.20.self_attn.o_proj",
+      "model.language_model.layers.21.self_attn.q_proj",
+      "model.language_model.layers.21.self_attn.k_proj",
+      "model.language_model.layers.21.self_attn.v_proj",
+      "model.language_model.layers.21.self_attn.o_proj",
+      "model.language_model.layers.22.self_attn.q_proj",
+      "model.language_model.layers.22.self_attn.k_proj",
+      "model.language_model.layers.22.self_attn.v_proj",
+      "model.language_model.layers.22.self_attn.o_proj",
+      "model.language_model.layers.23.self_attn.q_proj",
+      "model.language_model.layers.23.self_attn.k_proj",
+      "model.language_model.layers.23.self_attn.v_proj",
+      "model.language_model.layers.23.self_attn.o_proj",
+      "model.language_model.layers.24.self_attn.q_proj",
+      "model.language_model.layers.24.self_attn.k_proj",
+      "model.language_model.layers.24.self_attn.v_proj",
+      "model.language_model.layers.24.self_attn.o_proj",
+      "model.language_model.layers.25.self_attn.q_proj",
+      "model.language_model.layers.25.self_attn.k_proj",
+      "model.language_model.layers.25.self_attn.v_proj",
+      "model.language_model.layers.25.self_attn.o_proj",
+      "model.language_model.layers.26.self_attn.q_proj",
+      "model.language_model.layers.26.self_attn.k_proj",
+      "model.language_model.layers.26.self_attn.v_proj",
+      "model.language_model.layers.26.self_attn.o_proj",
+      "model.language_model.layers.27.self_attn.q_proj",
+      "model.language_model.layers.27.self_attn.k_proj",
+      "model.language_model.layers.27.self_attn.v_proj",
+      "model.language_model.layers.27.self_attn.o_proj",
+      "model.language_model.layers.28.self_attn.q_proj",
+      "model.language_model.layers.28.self_attn.k_proj",
+      "model.language_model.layers.28.self_attn.v_proj",
+      "model.language_model.layers.28.self_attn.o_proj",
+      "model.language_model.layers.29.self_attn.q_proj",
+      "model.language_model.layers.29.self_attn.k_proj",
+      "model.language_model.layers.29.self_attn.v_proj",
+      "model.language_model.layers.29.self_attn.o_proj",
+      "model.language_model.layers.30.self_attn.q_proj",
+      "model.language_model.layers.30.self_attn.k_proj",
+      "model.language_model.layers.30.self_attn.v_proj",
+      "model.language_model.layers.30.self_attn.o_proj",
+      "model.language_model.layers.31.self_attn.q_proj",
+      "model.language_model.layers.31.self_attn.k_proj",
+      "model.language_model.layers.31.self_attn.v_proj",
+      "model.language_model.layers.31.self_attn.o_proj",
+      "model.language_model.layers.32.self_attn.q_proj",
+      "model.language_model.layers.32.self_attn.k_proj",
+      "model.language_model.layers.32.self_attn.v_proj",
+      "model.language_model.layers.32.self_attn.o_proj",
+      "model.language_model.layers.33.self_attn.q_proj",
+      "model.language_model.layers.33.self_attn.k_proj",
+      "model.language_model.layers.33.self_attn.v_proj",
+      "model.language_model.layers.33.self_attn.o_proj",
+      "model.language_model.layers.34.self_attn.q_proj",
+      "model.language_model.layers.34.self_attn.k_proj",
+      "model.language_model.layers.34.self_attn.v_proj",
+      "model.language_model.layers.34.self_attn.o_proj",
+      "model.language_model.layers.35.self_attn.q_proj",
+      "model.language_model.layers.35.self_attn.k_proj",
+      "model.language_model.layers.35.self_attn.v_proj",
+      "model.language_model.layers.35.self_attn.o_proj",
+      "model.language_model.layers.36.self_attn.q_proj",
+      "model.language_model.layers.36.self_attn.k_proj",
+      "model.language_model.layers.36.self_attn.v_proj",
+      "model.language_model.layers.36.self_attn.o_proj",
+      "model.language_model.layers.37.self_attn.q_proj",
+      "model.language_model.layers.37.self_attn.k_proj",
+      "model.language_model.layers.37.self_attn.v_proj",
+      "model.language_model.layers.37.self_attn.o_proj",
+      "model.language_model.layers.38.self_attn.q_proj",
+      "model.language_model.layers.38.self_attn.k_proj",
+      "model.language_model.layers.38.self_attn.v_proj",
+      "model.language_model.layers.38.self_attn.o_proj",
+      "model.language_model.layers.39.self_attn.q_proj",
+      "model.language_model.layers.39.self_attn.k_proj",
+      "model.language_model.layers.39.self_attn.v_proj",
+      "model.language_model.layers.39.self_attn.o_proj",
       "lm_head"
     ],
     "kv_cache_scheme": null,

consolidated.safetensors CHANGED Viewed

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3d4dd5d413c3954d2dac20bc487c2328b99f1a5d478a953636dfa0c2aeb7d33
-size 15730613144

 version https://git-lfs.github.com/spec/v1
+oid sha256:2d4a815f19dd1ff35189b7a0de281b7642ac2d327950860b75f34c50818e2cd2
+size 17826847760

model.safetensors ADDED Viewed

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:38c01b03cbca6b286733024a1d76fa1328b7b13a9530cea46bc507f16a2acf14
+size 17826859088

params.json CHANGED Viewed

@@ -259,6 +259,166 @@
       "model.multi_modal_projector.patch_merger.merging_layer",
       "model.multi_modal_projector.linear_1",
       "model.multi_modal_projector.linear_2",
       "lm_head"
     ],
     "sparsity_config": {}

       "model.multi_modal_projector.patch_merger.merging_layer",
       "model.multi_modal_projector.linear_1",
       "model.multi_modal_projector.linear_2",
+      "language_model.model.layers.0.self_attn.q_proj",
+      "language_model.model.layers.0.self_attn.k_proj",
+      "language_model.model.layers.0.self_attn.v_proj",
+      "language_model.model.layers.0.self_attn.o_proj",
+      "language_model.model.layers.1.self_attn.q_proj",
+      "language_model.model.layers.1.self_attn.k_proj",
+      "language_model.model.layers.1.self_attn.v_proj",
+      "language_model.model.layers.1.self_attn.o_proj",
+      "language_model.model.layers.2.self_attn.q_proj",
+      "language_model.model.layers.2.self_attn.k_proj",
+      "language_model.model.layers.2.self_attn.v_proj",
+      "language_model.model.layers.2.self_attn.o_proj",
+      "language_model.model.layers.3.self_attn.q_proj",
+      "language_model.model.layers.3.self_attn.k_proj",
+      "language_model.model.layers.3.self_attn.v_proj",
+      "language_model.model.layers.3.self_attn.o_proj",
+      "language_model.model.layers.4.self_attn.q_proj",
+      "language_model.model.layers.4.self_attn.k_proj",
+      "language_model.model.layers.4.self_attn.v_proj",
+      "language_model.model.layers.4.self_attn.o_proj",
+      "language_model.model.layers.5.self_attn.q_proj",
+      "language_model.model.layers.5.self_attn.k_proj",
+      "language_model.model.layers.5.self_attn.v_proj",
+      "language_model.model.layers.5.self_attn.o_proj",
+      "language_model.model.layers.6.self_attn.q_proj",
+      "language_model.model.layers.6.self_attn.k_proj",
+      "language_model.model.layers.6.self_attn.v_proj",
+      "language_model.model.layers.6.self_attn.o_proj",
+      "language_model.model.layers.7.self_attn.q_proj",
+      "language_model.model.layers.7.self_attn.k_proj",
+      "language_model.model.layers.7.self_attn.v_proj",
+      "language_model.model.layers.7.self_attn.o_proj",
+      "language_model.model.layers.8.self_attn.q_proj",
+      "language_model.model.layers.8.self_attn.k_proj",
+      "language_model.model.layers.8.self_attn.v_proj",
+      "language_model.model.layers.8.self_attn.o_proj",
+      "language_model.model.layers.9.self_attn.q_proj",
+      "language_model.model.layers.9.self_attn.k_proj",
+      "language_model.model.layers.9.self_attn.v_proj",
+      "language_model.model.layers.9.self_attn.o_proj",
+      "language_model.model.layers.10.self_attn.q_proj",
+      "language_model.model.layers.10.self_attn.k_proj",
+      "language_model.model.layers.10.self_attn.v_proj",
+      "language_model.model.layers.10.self_attn.o_proj",
+      "language_model.model.layers.11.self_attn.q_proj",
+      "language_model.model.layers.11.self_attn.k_proj",
+      "language_model.model.layers.11.self_attn.v_proj",
+      "language_model.model.layers.11.self_attn.o_proj",
+      "language_model.model.layers.12.self_attn.q_proj",
+      "language_model.model.layers.12.self_attn.k_proj",
+      "language_model.model.layers.12.self_attn.v_proj",
+      "language_model.model.layers.12.self_attn.o_proj",
+      "language_model.model.layers.13.self_attn.q_proj",
+      "language_model.model.layers.13.self_attn.k_proj",
+      "language_model.model.layers.13.self_attn.v_proj",
+      "language_model.model.layers.13.self_attn.o_proj",
+      "language_model.model.layers.14.self_attn.q_proj",
+      "language_model.model.layers.14.self_attn.k_proj",
+      "language_model.model.layers.14.self_attn.v_proj",
+      "language_model.model.layers.14.self_attn.o_proj",
+      "language_model.model.layers.15.self_attn.q_proj",
+      "language_model.model.layers.15.self_attn.k_proj",
+      "language_model.model.layers.15.self_attn.v_proj",
+      "language_model.model.layers.15.self_attn.o_proj",
+      "language_model.model.layers.16.self_attn.q_proj",
+      "language_model.model.layers.16.self_attn.k_proj",
+      "language_model.model.layers.16.self_attn.v_proj",
+      "language_model.model.layers.16.self_attn.o_proj",
+      "language_model.model.layers.17.self_attn.q_proj",
+      "language_model.model.layers.17.self_attn.k_proj",
+      "language_model.model.layers.17.self_attn.v_proj",
+      "language_model.model.layers.17.self_attn.o_proj",
+      "language_model.model.layers.18.self_attn.q_proj",
+      "language_model.model.layers.18.self_attn.k_proj",
+      "language_model.model.layers.18.self_attn.v_proj",
+      "language_model.model.layers.18.self_attn.o_proj",
+      "language_model.model.layers.19.self_attn.q_proj",
+      "language_model.model.layers.19.self_attn.k_proj",
+      "language_model.model.layers.19.self_attn.v_proj",
+      "language_model.model.layers.19.self_attn.o_proj",
+      "language_model.model.layers.20.self_attn.q_proj",
+      "language_model.model.layers.20.self_attn.k_proj",
+      "language_model.model.layers.20.self_attn.v_proj",
+      "language_model.model.layers.20.self_attn.o_proj",
+      "language_model.model.layers.21.self_attn.q_proj",
+      "language_model.model.layers.21.self_attn.k_proj",
+      "language_model.model.layers.21.self_attn.v_proj",
+      "language_model.model.layers.21.self_attn.o_proj",
+      "language_model.model.layers.22.self_attn.q_proj",
+      "language_model.model.layers.22.self_attn.k_proj",
+      "language_model.model.layers.22.self_attn.v_proj",
+      "language_model.model.layers.22.self_attn.o_proj",
+      "language_model.model.layers.23.self_attn.q_proj",
+      "language_model.model.layers.23.self_attn.k_proj",
+      "language_model.model.layers.23.self_attn.v_proj",
+      "language_model.model.layers.23.self_attn.o_proj",
+      "language_model.model.layers.24.self_attn.q_proj",
+      "language_model.model.layers.24.self_attn.k_proj",
+      "language_model.model.layers.24.self_attn.v_proj",
+      "language_model.model.layers.24.self_attn.o_proj",
+      "language_model.model.layers.25.self_attn.q_proj",
+      "language_model.model.layers.25.self_attn.k_proj",
+      "language_model.model.layers.25.self_attn.v_proj",
+      "language_model.model.layers.25.self_attn.o_proj",
+      "language_model.model.layers.26.self_attn.q_proj",
+      "language_model.model.layers.26.self_attn.k_proj",
+      "language_model.model.layers.26.self_attn.v_proj",
+      "language_model.model.layers.26.self_attn.o_proj",
+      "language_model.model.layers.27.self_attn.q_proj",
+      "language_model.model.layers.27.self_attn.k_proj",
+      "language_model.model.layers.27.self_attn.v_proj",
+      "language_model.model.layers.27.self_attn.o_proj",
+      "language_model.model.layers.28.self_attn.q_proj",
+      "language_model.model.layers.28.self_attn.k_proj",
+      "language_model.model.layers.28.self_attn.v_proj",
+      "language_model.model.layers.28.self_attn.o_proj",
+      "language_model.model.layers.29.self_attn.q_proj",
+      "language_model.model.layers.29.self_attn.k_proj",
+      "language_model.model.layers.29.self_attn.v_proj",
+      "language_model.model.layers.29.self_attn.o_proj",
+      "language_model.model.layers.30.self_attn.q_proj",
+      "language_model.model.layers.30.self_attn.k_proj",
+      "language_model.model.layers.30.self_attn.v_proj",
+      "language_model.model.layers.30.self_attn.o_proj",
+      "language_model.model.layers.31.self_attn.q_proj",
+      "language_model.model.layers.31.self_attn.k_proj",
+      "language_model.model.layers.31.self_attn.v_proj",
+      "language_model.model.layers.31.self_attn.o_proj",
+      "language_model.model.layers.32.self_attn.q_proj",
+      "language_model.model.layers.32.self_attn.k_proj",
+      "language_model.model.layers.32.self_attn.v_proj",
+      "language_model.model.layers.32.self_attn.o_proj",
+      "language_model.model.layers.33.self_attn.q_proj",
+      "language_model.model.layers.33.self_attn.k_proj",
+      "language_model.model.layers.33.self_attn.v_proj",
+      "language_model.model.layers.33.self_attn.o_proj",
+      "language_model.model.layers.34.self_attn.q_proj",
+      "language_model.model.layers.34.self_attn.k_proj",
+      "language_model.model.layers.34.self_attn.v_proj",
+      "language_model.model.layers.34.self_attn.o_proj",
+      "language_model.model.layers.35.self_attn.q_proj",
+      "language_model.model.layers.35.self_attn.k_proj",
+      "language_model.model.layers.35.self_attn.v_proj",
+      "language_model.model.layers.35.self_attn.o_proj",
+      "language_model.model.layers.36.self_attn.q_proj",
+      "language_model.model.layers.36.self_attn.k_proj",
+      "language_model.model.layers.36.self_attn.v_proj",
+      "language_model.model.layers.36.self_attn.o_proj",
+      "language_model.model.layers.37.self_attn.q_proj",
+      "language_model.model.layers.37.self_attn.k_proj",
+      "language_model.model.layers.37.self_attn.v_proj",
+      "language_model.model.layers.37.self_attn.o_proj",
+      "language_model.model.layers.38.self_attn.q_proj",
+      "language_model.model.layers.38.self_attn.k_proj",
+      "language_model.model.layers.38.self_attn.v_proj",
+      "language_model.model.layers.38.self_attn.o_proj",
+      "language_model.model.layers.39.self_attn.q_proj",
+      "language_model.model.layers.39.self_attn.k_proj",
+      "language_model.model.layers.39.self_attn.v_proj",
+      "language_model.model.layers.39.self_attn.o_proj",
       "lm_head"
     ],
     "sparsity_config": {}

recipe.yaml CHANGED Viewed

@@ -2,5 +2,5 @@ default_stage:
   default_modifiers:
     QuantizationModifier:
       targets: [Linear]
-      ignore: ['re:.*lm_head', 're:.*vision_tower.*', 're:.*multi_modal_projector.*']
       scheme: FP8_DYNAMIC

   default_modifiers:
     QuantizationModifier:
       targets: [Linear]
+      ignore: ['re:.*lm_head', 're:.*vision_tower.*', 're:.*multi_modal_projector.*', 're:.*self_attn']
       scheme: FP8_DYNAMIC