Instructions to use adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701 with Transformers:

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

pipe = pipeline("text-generation", model="adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701")
model = AutoModelForCausalLM.from_pretrained("adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701

SGLang

How to use adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701 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 "adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701 with Docker Model Runner:
```
docker model run hf.co/adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701
```
Browse Quantizations to use this model in llama.cpp, Ollama, LM Studio, or any compatible app.

THIS MODEL IS EXPERIMENTAL AND MIGHT BE BUGGY, I DIDN'T PERFECT THE STRENGTH OF DPO AND SFT YET.

Yi-34B-200K trained via DPO on RAWrr_v1 at ctx 200 (lora_r 4, lora_alpha 8) and then via SFT at ctx 1400 (lora_r 16, lora_alpha 32) on AEZAKMI_v2. It's less prone to refusals than Yi-34B-200K-AEZAKMI-v2 but that's work in progress still - I want to do DPO with higher lora rank and ctx and then repeat SFT training. I haven't tested it too much, but on what I've seen, it's a good model.

If you want to re-produce this model by merging loras, start by downloading Yi-34B-200K-Llamafied.
Then merge it with https://huggingface.co/adamo1139/Yi-34B-200K-rawrr1-LORA-DPO-experimental-r2
Then merge the resulting model with https://huggingface.co/adamo1139/yi-34b-200k-aezakmi-v2-rawrr-v1-run1-experimental-LoRA

License: apache-2.0

Open LLM Leaderboard Evaluation Results

Detailed results can be found here

Metric	Value
Avg.	71.04
AI2 Reasoning Challenge (25-Shot)	66.81
HellaSwag (10-Shot)	85.79
MMLU (5-Shot)	75.44
TruthfulQA (0-shot)	57.91
Winogrande (5-shot)	80.35
GSM8k (5-shot)	59.97

Downloads last month: 63

Safetensors

Model size

34B params

Tensor type

F16

Model tree for adamo1139/Yi-34B-200K-AEZAKMI-RAW-1701

Quantizations

1 model

Evaluation results

normalized accuracy on AI2 Reasoning Challenge (25-Shot)
test set Open LLM Leaderboard

66.810
normalized accuracy on HellaSwag (10-Shot)
validation set Open LLM Leaderboard

85.790
accuracy on MMLU (5-Shot)
test set Open LLM Leaderboard

75.440
mc2 on TruthfulQA (0-shot)
validation set Open LLM Leaderboard

57.910
accuracy on Winogrande (5-shot)
validation set Open LLM Leaderboard

80.350
accuracy on GSM8k (5-shot)
test set Open LLM Leaderboard

59.970