ABEJA-QwQ32b-Reasoning-Japanese-v1.0

26
13
1 language
license:apache-2.0
by
abeja
Language Model
OTHER
32B params
New
26 downloads
Early-stage
Try on Hugging FaceAdd to Compare
Edge AI:
Mobile
Laptop
Server
72GB+ RAM
Mobile
Laptop
Server
Quick Summary

ABEJA-QwQ32b-Reasoning-Japanese-v1.

Device Compatibility

Mobile
4-6GB RAM
Laptop
16GB RAM
Server
GPU
Minimum Recommended
30GB+ RAM

Code Examples

使い方pythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "abeja/ABEJA-QwQ32b-Reasoning-Japanese-v1.0"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "人とAIが協調するためには？"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768,
    do_sample=True,
    temperature=0.6,
    top_k=40,
    top_p=0.95,
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(response)
使い方pythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "abeja/ABEJA-QwQ32b-Reasoning-Japanese-v1.0"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "人とAIが協調するためには？"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768,
    do_sample=True,
    temperature=0.6,
    top_k=40,
    top_p=0.95,
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(response)
使い方pythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "abeja/ABEJA-QwQ32b-Reasoning-Japanese-v1.0"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "人とAIが協調するためには？"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768,
    do_sample=True,
    temperature=0.6,
    top_k=40,
    top_p=0.95,
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(response)
使い方pythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "abeja/ABEJA-QwQ32b-Reasoning-Japanese-v1.0"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "人とAIが協調するためには？"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768,
    do_sample=True,
    temperature=0.6,
    top_k=40,
    top_p=0.95,
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(response)
使い方pythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "abeja/ABEJA-QwQ32b-Reasoning-Japanese-v1.0"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "人とAIが協調するためには？"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768,
    do_sample=True,
    temperature=0.6,
    top_k=40,
    top_p=0.95,
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(response)
使い方pythontransformers
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "abeja/ABEJA-QwQ32b-Reasoning-Japanese-v1.0"

model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype="auto",
    device_map="auto"
)
tokenizer = AutoTokenizer.from_pretrained(model_name)

prompt = "人とAIが協調するためには？"
messages = [
    {"role": "user", "content": prompt}
]
text = tokenizer.apply_chat_template(
    messages,
    tokenize=False,
    add_generation_prompt=True
)
model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768
)
generated_ids = model.generate(
    **model_inputs,
    max_new_tokens=32768,
    do_sample=True,
    temperature=0.6,
    top_k=40,
    top_p=0.95,
)
generated_ids = [
    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
]

response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]

print(response)

Deploy This Model

Production-ready deployment in minutes

Together.ai

Instant API access to this model

Fastest API

Production-ready inference API. Start free, scale to millions.

Try Free API

Replicate

One-click model deployment

Easiest Setup

Run models in the cloud with simple API. No DevOps required.

Deploy Now

Disclosure: We may earn a commission from these partners. This helps keep LLMYourWay free.