Instructions to use RedHatAI/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RedHatAI/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds with Transformers:

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

pipe = pipeline("text-generation", model="RedHatAI/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("RedHatAI/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds")
model = AutoModelForCausalLM.from_pretrained("RedHatAI/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds", 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 RedHatAI/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RedHatAI/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds"
# 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/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/RedHatAI/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds

SGLang

How to use RedHatAI/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds 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/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds" \
    --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/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds",
		"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/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds" \
        --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/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use RedHatAI/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds with Docker Model Runner:
```
docker model run hf.co/RedHatAI/OpenHermes-2.5-Mistral-7B-pruned50-quant-ds
```

mgoin commited on Nov 21, 2023

Commit

fed89b0

1 Parent(s): 816ad03

Create recipe.yaml

Browse files

Files changed (1) hide show

recipe.yaml +31 -0

recipe.yaml ADDED Viewed

	@@ -0,0 +1,31 @@

+test_stage:
+  obcq_modifiers:
+    QuantizationModifier:
+      ignore:
+        # These operations don't make sense to quantize
+        - MistralRotaryEmbedding
+        - MistralRMSNorm
+        - SiLUActivation
+        # Skip quantizing the BMMs
+        # - QuantizableMatMul
+        # Skip quantizing the layers with the most sensitive activations
+        - model.layers.1.mlp.down_proj
+        - model.layers.31.mlp.down_proj
+        - model.layers.30.mlp.down_proj
+        - model.layers.30.mlp.gate_proj
+        - model.layers.30.mlp.up_proj
+      post_oneshot_calibration: true
+      scheme_overrides:
+        Embedding:
+          input_activations: null
+          weights:
+            num_bits: 8
+            symmetric: false
+    SparseGPTModifier:
+      sparsity: 0.5
+      block_size: 128
+      sequential_update: true
+      quantize: true
+      percdamp: 0.01
+      mask_structure: "0:0"
+      targets: ["re:model.layers.\\d*$"]