Instructions to use grimjim/llama-3-merge-pp-instruct-8B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimjim/llama-3-merge-pp-instruct-8B with Transformers:

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

pipe = pipeline("text-generation", model="grimjim/llama-3-merge-pp-instruct-8B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForMultimodalLM

tokenizer = AutoTokenizer.from_pretrained("grimjim/llama-3-merge-pp-instruct-8B")
model = AutoModelForMultimodalLM.from_pretrained("grimjim/llama-3-merge-pp-instruct-8B")
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]:]))

Inference
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use grimjim/llama-3-merge-pp-instruct-8B with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimjim/llama-3-merge-pp-instruct-8B"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimjim/llama-3-merge-pp-instruct-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/grimjim/llama-3-merge-pp-instruct-8B

SGLang

How to use grimjim/llama-3-merge-pp-instruct-8B 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 "grimjim/llama-3-merge-pp-instruct-8B" \
    --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": "grimjim/llama-3-merge-pp-instruct-8B",
		"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 "grimjim/llama-3-merge-pp-instruct-8B" \
        --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": "grimjim/llama-3-merge-pp-instruct-8B",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use grimjim/llama-3-merge-pp-instruct-8B with Docker Model Runner:
```
docker model run hf.co/grimjim/llama-3-merge-pp-instruct-8B
```

grimjim commited on Jun 19, 2024

Commit

c64e364

verified ·

1 Parent(s): 0714ee0

Update README.md

Browse files

Files changed (1) hide show

README.md +54 -55

README.md CHANGED Viewed

@@ -1,55 +1,54 @@
----
-language:
-- en
-base_model:
-- meta-llama/Meta-Llama-3-8B-Instruct
-- ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B
-library_name: transformers
-tags:
-- meta
-- llama-3
-- pytorch
-- mergekit
-- merge
-license: llama3
-license_link: LICENSE
-pipeline_tag: text-generation
----
-# llama-3-merge-pp-instruct-8B
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-Lightly tested at temperature=1.0, minP=0.02 with provisional Llama 3 Instruct prompts.
-Built with Meta Llama 3.
-## Merge Details
-### Merge Method
-This model was merged using the SLERP merge method.
-### Models Merged
-The following models were included in the merge:
-* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
-* [ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B)
-### Configuration
-The following YAML configuration was used to produce this model:
-```yaml
-slices:
-  - sources:
-    - model: ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B
-      layer_range: [0,32]
-    - model: meta-llama/Meta-Llama-3-8B-Instruct
-      layer_range: [0,32]
-merge_method: slerp
-base_model: ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B
-parameters:
-  t:
-    - value: 0.5
-dtype: bfloat16
-```

+---
+language:
+- en
+base_model:
+- meta-llama/Meta-Llama-3-8B-Instruct
+- ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B
+library_name: transformers
+tags:
+- meta
+- llama-3
+- pytorch
+- mergekit
+- merge
+license: cc-by-nc-4.0
+pipeline_tag: text-generation
+---
+# llama-3-merge-pp-instruct-8B
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+Lightly tested at temperature=1.0, minP=0.02 with provisional Llama 3 Instruct prompts.
+Built with Meta Llama 3.
+## Merge Details
+### Merge Method
+This model was merged using the SLERP merge method.
+### Models Merged
+The following models were included in the merge:
+* [meta-llama/Meta-Llama-3-8B-Instruct](https://huggingface.co/meta-llama/Meta-Llama-3-8B-Instruct)
+* [ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B](https://huggingface.co/ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B)
+### Configuration
+The following YAML configuration was used to produce this model:
+```yaml
+slices:
+  - sources:
+    - model: ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B
+      layer_range: [0,32]
+    - model: meta-llama/Meta-Llama-3-8B-Instruct
+      layer_range: [0,32]
+merge_method: slerp
+base_model: ChaoticNeutrals/Poppy_Porpoise-0.72-L3-8B
+parameters:
+  t:
+    - value: 0.5
+dtype: bfloat16
+```