Instructions to use T145/KRONOS-8B-V4 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use T145/KRONOS-8B-V4 with Transformers:

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

pipe = pipeline("text-generation", model="T145/KRONOS-8B-V4")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("T145/KRONOS-8B-V4")
model = AutoModelForCausalLM.from_pretrained("T145/KRONOS-8B-V4", 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 T145/KRONOS-8B-V4 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "T145/KRONOS-8B-V4"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "T145/KRONOS-8B-V4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/T145/KRONOS-8B-V4

SGLang

How to use T145/KRONOS-8B-V4 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 "T145/KRONOS-8B-V4" \
    --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": "T145/KRONOS-8B-V4",
		"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 "T145/KRONOS-8B-V4" \
        --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": "T145/KRONOS-8B-V4",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use T145/KRONOS-8B-V4 with Docker Model Runner:
```
docker model run hf.co/T145/KRONOS-8B-V4
```

T145 commited on Dec 19, 2024

Commit

7f6855b

verified ·

1 Parent(s): f9faad0

Update README.md

Browse files

Files changed (1) hide show

README.md +52 -52

README.md CHANGED Viewed

@@ -1,52 +1,52 @@
----
-base_model:
-- mukaj/Llama-3.1-Hawkish-8B
-- T145/KRONOS-8B-V1-P3
-- T145/KRONOS-8B-V1-P1
-- unsloth/Meta-Llama-3.1-8B-Instruct
-- T145/KRONOS-8B-V1-P2
-library_name: transformers
-tags:
-- mergekit
-- merge
----
-# Untitled Model (1)
-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 [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) as a base.
-### Models Merged
-The following models were included in the merge:
-* [mukaj/Llama-3.1-Hawkish-8B](https://huggingface.co/mukaj/Llama-3.1-Hawkish-8B)
-* [T145/KRONOS-8B-V1-P3](https://huggingface.co/T145/KRONOS-8B-V1-P3)
-* [T145/KRONOS-8B-V1-P1](https://huggingface.co/T145/KRONOS-8B-V1-P1)
-* [T145/KRONOS-8B-V1-P2](https://huggingface.co/T145/KRONOS-8B-V1-P2)
-### Configuration
-The following YAML configuration was used to produce this model:
-```yaml
-base_model: unsloth/Meta-Llama-3.1-8B-Instruct
-dtype: bfloat16
-merge_method: model_stock
-slices:
-- sources:
-  - layer_range: [0, 32]
-    model: T145/KRONOS-8B-V1-P1
-  - layer_range: [0, 32]
-    model: T145/KRONOS-8B-V1-P2
-  - layer_range: [0, 32]
-    model: T145/KRONOS-8B-V1-P3
-  - layer_range: [0, 32]
-    model: mukaj/Llama-3.1-Hawkish-8B
-  - layer_range: [0, 32]
-    model: unsloth/Meta-Llama-3.1-8B-Instruct
-tokenizer_source: base
-```

+---
+base_model:
+- mukaj/Llama-3.1-Hawkish-8B
+- T145/KRONOS-8B-V1-P3
+- T145/KRONOS-8B-V1-P1
+- unsloth/Meta-Llama-3.1-8B-Instruct
+- T145/KRONOS-8B-V1-P2
+library_name: transformers
+tags:
+- mergekit
+- merge
+---
+# KRONOS 8B V4
+The goal with this merge is to have a significant step towards why the older TIES merges nuke the IFEval score. Present hypothesis is that merging on the non-instruct model causes this disparity, as IFEval measures instruction-following capacity. It's also possible that either P1 or P3 causes the problem.
+## Merge Details
+### Merge Method
+This model was merged using the [Model Stock](https://arxiv.org/abs/2403.19522) merge method using [unsloth/Meta-Llama-3.1-8B-Instruct](https://huggingface.co/unsloth/Meta-Llama-3.1-8B-Instruct) as a base.
+### Models Merged
+The following models were included in the merge:
+* [mukaj/Llama-3.1-Hawkish-8B](https://huggingface.co/mukaj/Llama-3.1-Hawkish-8B)
+* [T145/KRONOS-8B-V1-P3](https://huggingface.co/T145/KRONOS-8B-V1-P3)
+* [T145/KRONOS-8B-V1-P1](https://huggingface.co/T145/KRONOS-8B-V1-P1)
+* [T145/KRONOS-8B-V1-P2](https://huggingface.co/T145/KRONOS-8B-V1-P2)
+### Configuration
+The following YAML configuration was used to produce this model:
+```yaml
+base_model: unsloth/Meta-Llama-3.1-8B-Instruct
+dtype: bfloat16
+merge_method: model_stock
+slices:
+- sources:
+  - layer_range: [0, 32]
+    model: T145/KRONOS-8B-V1-P1
+  - layer_range: [0, 32]
+    model: T145/KRONOS-8B-V1-P2
+  - layer_range: [0, 32]
+    model: T145/KRONOS-8B-V1-P3
+  - layer_range: [0, 32]
+    model: mukaj/Llama-3.1-Hawkish-8B
+  - layer_range: [0, 32]
+    model: unsloth/Meta-Llama-3.1-8B-Instruct
+tokenizer_source: base
+```