Comments (5)
You are missing -- in front of your load_in_4bit
from h2ogpt.
You are missing -- in front of your
load_in_4bit
Thank you for your reply, I tried your solution, however the problem persists
CUDA_VISIBLE_DEVICES=1 python generate.py --base_model=h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v3 --score_model=None prompt_type=human_bot --cli=False --load_in_4bit=True device_map=auto
Using Model h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v3
load INSTRUCTOR_Transformer
max_seq_length 512
Must install DocTR and LangChain installed if enabled DocTR, disabling
Starting get_model: h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v3
Could not determine --max_seq_len, setting to 2048. Pass if not correct
Could not determine --max_seq_len, setting to 2048. Pass if not correct
Starting get_model: h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v3
Could not determine --max_seq_len, setting to 2048. Pass if not correct
Could not determine --max_seq_len, setting to 2048. Pass if not correct
Starting get_model: h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v3
Could not determine --max_seq_len, setting to 2048. Pass if not correct
Could not determine --max_seq_len, setting to 2048. Pass if not correct
Starting get_model: h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v3
Could not determine --max_seq_len, setting to 2048. Pass if not correct
Could not determine --max_seq_len, setting to 2048. Pass if not correct
Traceback (most recent call last):
File "/home/alexander/h2ogpt/generate.py", line 20, in <module>
entrypoint_main()
File "/home/alexander/h2ogpt/generate.py", line 16, in entrypoint_main
H2O_Fire(main)
File "/home/alexander/h2ogpt/src/utils.py", line 73, in H2O_Fire
fire.Fire(component=component, command=args)
File "/home/alexander/anaconda3/envs/h2ogpt/lib/python3.10/site-packages/fire/core.py", line 141, in Fire
component_trace = _Fire(component, args, parsed_flag_args, context, name)
File "/home/alexander/anaconda3/envs/h2ogpt/lib/python3.10/site-packages/fire/core.py", line 475, in _Fire
component, remaining_args = _CallAndUpdateTrace(
File "/home/alexander/anaconda3/envs/h2ogpt/lib/python3.10/site-packages/fire/core.py", line 691, in _CallAndUpdateTrace
component = fn(*varargs, **kwargs)
File "/home/alexander/h2ogpt/src/gen.py", line 2269, in main
model0, tokenizer0, device = get_model_retry(reward_type=False,
File "/home/alexander/h2ogpt/src/gen.py", line 2621, in get_model_retry
model1, tokenizer1, device1 = get_model(**kwargs)
File "/home/alexander/h2ogpt/src/gen.py", line 3277, in get_model
return get_hf_model(load_8bit=load_8bit,
File "/home/alexander/h2ogpt/src/gen.py", line 3437, in get_hf_model
model_kwargs['quantization_config'] = BitsAndBytesConfig(
File "/home/alexander/anaconda3/envs/h2ogpt/lib/python3.10/site-packages/transformers/utils/quantization_config.py", line 284, in __init__
self.post_init()
File "/home/alexander/anaconda3/envs/h2ogpt/lib/python3.10/site-packages/transformers/utils/quantization_config.py", line 320, in post_init
raise ValueError("load_in_8bit must be a boolean")
ValueError: load_in_8bit must be a boolean
from h2ogpt.
At end you have device_map=auto
that has no meaning to the CLI. It interprets it as the next argument.
from h2ogpt.
At end you have
device_map=auto
that has no meaning to the CLI. It interprets it as the next argument.
Before it worked fine, now even
python generate.py --base_model=h2oai/h2ogpt-gm-oasst1-en-2048-falcon-7b-v3 --score_model=None prompt_type=human_bot --cli=False
this command doesn't work
However,
python generate.py --base_model=TheBloke/CapybaraHermes-2.5-Mistral-7B-GGUF --score_model=None prompt_type=human_bot --cli=False
when I call base model from TheBloke works for me
What do you think?
from h2ogpt.
You again miss -- before "prompt_type".
from h2ogpt.
Related Issues (20)
- Intel ARC GPU support
- Document Storage HOT 2
- How should I upload my personal data to the h2o website I deployed and make it persistent? HOT 1
- Collection Selection showen multiple times HOT 1
- Question: correct prompts template for llama3-instruct HOT 9
- httpx.ConnectError with --openai_server=True --ssl-verify=False HOT 9
- h2ogpt on ubuntu server HOT 3
- branding capitalization HOT 1
- Support for https://huggingface.co/lightblue/suzume-llama-3-8B-multilingual HOT 3
- OCR issue HOT 1
- shared / personal collections HOT 1
- Failed to initial linux full script intallation HOT 2
- random assertion errors due to evaluate_nochat HOT 13
- Run docker image on any machine which haven't internet connection HOT 19
- h2ogpt vllm-check init-container stuck when istio injection
- GPU offloading mistralai_mistral-7b-instruct-v0.2 HOT 3
- Windows fatal exception: Access violation HOT 3
- Failed to load models HOT 2
- TimeoutError: answer_question_using_context timed out, took more than 60s
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from h2ogpt.