Instructions to use schonsense/70B_Triage with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use schonsense/70B_Triage with Transformers:

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

pipe = pipeline("text-generation", model="schonsense/70B_Triage")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("schonsense/70B_Triage")
model = AutoModelForCausalLM.from_pretrained("schonsense/70B_Triage", 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=256)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use schonsense/70B_Triage with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "schonsense/70B_Triage"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "schonsense/70B_Triage",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/schonsense/70B_Triage

SGLang

How to use schonsense/70B_Triage 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 "schonsense/70B_Triage" \
    --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": "schonsense/70B_Triage",
		"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 "schonsense/70B_Triage" \
        --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": "schonsense/70B_Triage",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use schonsense/70B_Triage with Docker Model Runner:
```
docker model run hf.co/schonsense/70B_Triage
```

schonsense commited on Feb 12

Commit

0d63c8c

verified ·

1 Parent(s): cd01d50

Update README.md

Browse files

Files changed (1) hide show

README.md +58 -58

README.md CHANGED Viewed

@@ -1,58 +1,58 @@
----
-base_model:
-- HPAI-BSC/Llama3.1-Aloe-Beta-70B
-- Writer/Palmyra-Med-70B-32K
-- sam-paech/Llama-3.3-70B-Instruct-ftpo_1k
-library_name: transformers
-tags:
-- mergekit
-- merge
----
-# sce_med
-This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
-## Merge Details
-### Merge Method
-This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [sam-paech/Llama-3.3-70B-Instruct-ftpo_1k](https://huggingface.co/sam-paech/Llama-3.3-70B-Instruct-ftpo_1k) as a base.
-### Models Merged
-The following models were included in the merge:
-* [HPAI-BSC/Llama3.1-Aloe-Beta-70B](https://huggingface.co/HPAI-BSC/Llama3.1-Aloe-Beta-70B)
-* [Writer/Palmyra-Med-70B-32K](https://huggingface.co/Writer/Palmyra-Med-70B-32K)
-* D:\mergekit\yamls\IPOplectic
-### Configuration
-The following YAML configuration was used to produce this model:
-```yaml
-merge_method: sce
-select_topk: 0.25
-models:
-  - model: sam-paech/Llama-3.3-70B-Instruct-ftpo_1k
-  - model: HPAI-BSC/Llama3.1-Aloe-Beta-70B
-  - model: Writer/Palmyra-Med-70B-32K
-  - model: "D:\\mergekit\\yamls\\IPOplectic"
-base_model: sam-paech/Llama-3.3-70B-Instruct-ftpo_1k
-parameters:
-  normalize: false
-  int8_mask: true
-dtype: float32
-out_dtype: bfloat16
-tokenizer:
-  source: base
-  pad_to_multiple_of: 8
-```

+---
+base_model:
+- HPAI-BSC/Llama3.1-Aloe-Beta-70B
+- Writer/Palmyra-Med-70B-32K
+- sam-paech/Llama-3.3-70B-Instruct-ftpo_1k
+- schonsense/IPOplectic
+library_name: transformers
+tags:
+- mergekit
+- merge
+---
+# sce_med
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+## Merge Details
+### Merge Method
+This model was merged using the [SCE](https://arxiv.org/abs/2408.07990) merge method using [sam-paech/Llama-3.3-70B-Instruct-ftpo_1k](https://huggingface.co/sam-paech/Llama-3.3-70B-Instruct-ftpo_1k) as a base.
+### Models Merged
+The following models were included in the merge:
+* [HPAI-BSC/Llama3.1-Aloe-Beta-70B](https://huggingface.co/HPAI-BSC/Llama3.1-Aloe-Beta-70B)
+* [Writer/Palmyra-Med-70B-32K](https://huggingface.co/Writer/Palmyra-Med-70B-32K)
+* [schonsense/IPOplectic](https://huggingface.co/schonsense/IPOplectic)
+### Configuration
+The following YAML configuration was used to produce this model:
+```yaml
+merge_method: sce
+select_topk: 0.25
+models:
+  - model: sam-paech/Llama-3.3-70B-Instruct-ftpo_1k
+  - model: HPAI-BSC/Llama3.1-Aloe-Beta-70B
+  - model: Writer/Palmyra-Med-70B-32K
+  - model: "D:\\mergekit\\yamls\\IPOplectic"
+base_model: sam-paech/Llama-3.3-70B-Instruct-ftpo_1k
+parameters:
+  normalize: false
+  int8_mask: true
+dtype: float32
+out_dtype: bfloat16
+tokenizer:
+  source: base
+  pad_to_multiple_of: 8
+```