Instructions to use IFM/K2-Chat with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use IFM/K2-Chat with Transformers:

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

pipe = pipeline("text-generation", model="IFM/K2-Chat")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("IFM/K2-Chat")
model = AutoModelForCausalLM.from_pretrained("IFM/K2-Chat", 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 IFM/K2-Chat with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "IFM/K2-Chat"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "IFM/K2-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/IFM/K2-Chat

SGLang

How to use IFM/K2-Chat 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 "IFM/K2-Chat" \
    --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": "IFM/K2-Chat",
		"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 "IFM/K2-Chat" \
        --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": "IFM/K2-Chat",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use IFM/K2-Chat with Docker Model Runner:
```
docker model run hf.co/IFM/K2-Chat
```

victormiller commited on Oct 30, 2024

Commit

d02e2d1

verified ·

1 Parent(s): 274ce6d

Update README.md

Browse files

Files changed (1) hide show

README.md +46 -1

README.md CHANGED Viewed

@@ -2,7 +2,52 @@
 license: apache-2.0
 ---
 # K2-Chat: a fully-reproducible large language model outperforming Llama 2 70B Chat using 35% less compute
 K2 Chat is finetuned from [K2-65B](https://huggingface.co/LLM360/K2). K2 Chat outperforms Llama 2-70B-Chat on all evaluations conducted. The model also outperforms Llama 3-70B-Instruct on coding tasks.
 <center><img src="k2_chat_eval_table.png" alt="k2 eval table" /></center>

 license: apache-2.0
 ---
 # K2-Chat: a fully-reproducible large language model outperforming Llama 2 70B Chat using 35% less compute
+K2 Chat is finetuned from [K2-65B](https://huggingface.co/LLM360/K2). The most recent model update 10/31/24.
+In this release, we introduce function calling features and target improvements across math, coding, and safety.
+We utilized the following datasets:
+[Infinity-Instruct](https://huggingface.co/datasets/BAAI/Infinity-Instruct)
+[JiuZhang3.0-Corpus-SFT](https://huggingface.co/datasets/ToheartZhang/JiuZhang3.0-Corpus-SFT)
+[glaive-function-calling-v2-sharegpt](https://huggingface.co/datasets/hiyouga/glaive-function-calling-v2-sharegpt)
+## Results
+|                         | K2-Chat-060124 | K2-Chat |
+|-------------------------|---------|----------|
+| **Natural Language Benchmarks** |         |          |
+| MMLU (0-shot)           | 63.5    | 69.14    |
+| RACE (0-shot)           | 46.1    | 46.60    |
+| HellaSwag (10-shot)     | 81.7    | 80.80    |
+| PIQA (5-shot)           | 82.3    | 81.34    |
+| ARC-easy (5-shot)       | 84.6    | 79.00    |
+| ARC-challenge (25-shot) | 61.3    | 61.09    |
+| OpenBookQA (5-shot)     | 48.0    | 47.00    |
+| Winogrande (5-shot)     | 79.5    | 78.30    |
+| TruthfulQA (0-shot)     | 44.7    | 57.32    |
+| CrowS-Pairs (0-shot)    | 64.2    | 65.32    |
+| GSM8K (5-shot)          | 60.7    | 77.10    |
+| MathQA (5-shot)         | 44.8    | 43.12    |
+| LogiQA2.0 (0-shot)      | 38.0    | 36.83    |
+| BBH CoT (0-shot)        | 64.9    | 70.37    |
+| **Code Benchmarks**     |         |          |
+| HumanEval (pass@1)      | 47.9    | 71.20    |
+| **Domain Specific (Medical)** |   |          |
+| MedQA (0-shot)          | 53.6    | 52.87    |
+| MedMCQA (5-shot)        | 51.3    | 50.71    |
+| PubMedQA (0-shot)       | 75.0    | 71.20    |
+| **Other**               |         |          |
+| MT-Bench               | 6.87     | 7.55     |
+| JSON-Mode-Eval          | 77.21   | 90.09    |
+| **Overall Average Score**|         |          |
+| Avg Score               | 58.88   | 61.30    |
+## K2-Chat-060124
 K2 Chat is finetuned from [K2-65B](https://huggingface.co/LLM360/K2). K2 Chat outperforms Llama 2-70B-Chat on all evaluations conducted. The model also outperforms Llama 3-70B-Instruct on coding tasks.
 <center><img src="k2_chat_eval_table.png" alt="k2 eval table" /></center>