Instructions to use grimulkan/llama2_70b_longlora_fp16_32k_ROPE8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use grimulkan/llama2_70b_longlora_fp16_32k_ROPE8 with Transformers:

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

pipe = pipeline("text-generation", model="grimulkan/llama2_70b_longlora_fp16_32k_ROPE8")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("grimulkan/llama2_70b_longlora_fp16_32k_ROPE8")
model = AutoModelForCausalLM.from_pretrained("grimulkan/llama2_70b_longlora_fp16_32k_ROPE8")

Notebooks
Google Colab
Kaggle
Local Apps

vLLM

How to use grimulkan/llama2_70b_longlora_fp16_32k_ROPE8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "grimulkan/llama2_70b_longlora_fp16_32k_ROPE8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "grimulkan/llama2_70b_longlora_fp16_32k_ROPE8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/grimulkan/llama2_70b_longlora_fp16_32k_ROPE8

SGLang

How to use grimulkan/llama2_70b_longlora_fp16_32k_ROPE8 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 "grimulkan/llama2_70b_longlora_fp16_32k_ROPE8" \
    --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": "grimulkan/llama2_70b_longlora_fp16_32k_ROPE8",
		"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 "grimulkan/llama2_70b_longlora_fp16_32k_ROPE8" \
        --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": "grimulkan/llama2_70b_longlora_fp16_32k_ROPE8",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use grimulkan/llama2_70b_longlora_fp16_32k_ROPE8 with Docker Model Runner:
```
docker model run hf.co/grimulkan/llama2_70b_longlora_fp16_32k_ROPE8
```

Benchs

by Nexesenex - opened Jan 31, 2024

Discussion

Nexesenex

Jan 31, 2024

•

edited Feb 1, 2024

Here are my benchs for the Q3_K_S quant of this model :

llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,Hellaswag,84.50000000,,400,2024-01-31 01:40:00,PEC8,70b,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,
llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,Hellaswag,84.4,,1000,2024-01-31 01:40:00,PEC8,70b,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,
llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,Hellaswag_Bin,79.75,,400,2024-01-31 01:40:00,PEC8,70b,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,
llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,Hellaswag_Bin,82.8,,1000,2024-01-31 01:40:00,PEC8,70b,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,
llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,Arc-Challenge,43.47826087,,299,2024-01-31 05:40:00,PEC8,70b,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,
llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,Arc-Easy,65.96491228,,570,2024-01-31 05:40:00,PEC8,70b,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,
llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,MMLU,44.72843450,,313,2024-01-31 05:40:00,PEC8,70b,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,
llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,Thruthful-QA,28.27417381,,817,2024-01-31 05:40:00,PEC8,70b,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,
llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,Winogrande,75.7695,,1267,2024-01-31 05:40:00,PEC8,70b,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,
llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,wikitext,128.7588,512,512,2024-01-31 01:40:00,PEC2,70b,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,81
llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,wikitext,9.9775,512,512,2024-01-31 01:40:00,PEC2.5,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,81
llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,wikitext,4.1192,512,512,2024-01-31 01:40:00,PEC8,70b,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,655
llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,wikitext,3.4525,4096,4096,2024-01-31 01:40:00,PEC8,70b,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,81
llama2-70b-longlora-rope8-32k.Q3_K_S.gguf,-,wikitext,3.3829,6144,6144,2024-01-31 01:40:00,PEC8,70b,Mistral_Medium,32768,,,GGUF,Yukang,grimulkan,54

grimulkan

Owner Feb 1, 2024

•

edited Feb 1, 2024

Here are the 70b 3-bit quants in one graph:

LongLORA base seems not that great to start with. Now that we know Miqu is Mistral-Medium, we know may not get it to fine-tune, unfortunately. But I wonder if ABF is a better approach to long-context.

A pity Codellama sucks, otherwise that might tell us more about ABF.

Is the Wintergoddess this one? If so, that was done using the same LongLORA base. It holds its own over the base, and contradicts my claim that longLORA is not the best base.

ChuckMcSneed

Feb 1, 2024

Nope, that's not my model. it seems to be this one. The original is gone.

grimulkan

Owner Feb 1, 2024

Ah, that mystery one. I forgot that story. Well, maybe longLORA does suck then...

FlareRebellion

Feb 1, 2024

LongLORA base seems not that great to start with. Now that we know Miqu is Mistral-Medium, we know may not get it to fine-tune, unfortunately. But I wonder if ABF is a better approach to long-context.

Huh did I miss something? The guy said it's an early alpha version (sure feels like one too). It's not mistral medium (or Mistral is lying).

grimulkan

Owner Feb 1, 2024

•

edited Feb 1, 2024

An early alpha of medium I guess I should have said. A llama2 FT as many had speculated - which is the relevant part for this discussion. It shows what might be possible with good data selection and rope scaling method and existing Llama2.

ChuckMcSneed

Feb 2, 2024

Got my extended WinterGoddess tested on open llm leaderboard. Seems like extending to 32k kills gsm8k and mmlu. Losses here seem to be far less brutal than on my own bench, where almost half of performance is lost:

grimulkan

Owner Feb 2, 2024

•

edited Feb 2, 2024

Cool. Pity we can't test Nexesenex/WinterGoddess-1.4x-limarpv3-70B-L2-32k-Requant.GGUF in the open leaderboard. Maybe with back-conversion to fp16 like how they did with Miqu.

I am changing my priority and experimenting with ABF. Will look to release a base (non-instruct-tuned) model with that soon, and hopefully a LORA too that can be merged into existing models. Would be interesting to see if it kills performance like the longLORA does.

Nexesenex

Feb 3, 2024

For the guys with the know-how, the source to dequant and make a fp16 is that Q4_K_S quant : https://huggingface.co/mishima/WinterGoddess-1.4x-limarpv3-70B-L2-32k.GGUF

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment