Delta-Vector / Hamanasu-QwQ-V1.5-Instruct

huggingface.co
Total runs: 42
24-hour runs: 1
7-day runs: 14
30-day runs: 31
Model's Last Updated: March 18 2025

Introduction of Hamanasu-QwQ-V1.5-Instruct

Model Details of Hamanasu-QwQ-V1.5-Instruct

Model Visualization

Hamanasu 32B
🌌 Overview

This model is the Instruct tuned version of Hamanasu-QwQ-V1, This model removes the reasoning gimmick of QwQ. The model has dry but good prose and stays terse, All thanks to Ruka-Hamanasu for funding the train.

⚔️ Hardware
  • 8x H100s
  • Epochs: 2
  • Base: Delta-Vector/Hamanasu-32B-V1-QwQ
  • Amount of Tokens: 60M
💰 Prompting

This model uses ChatML formatting

<|im_start|>system
You are an uncensored AI, your job is to fulfill thy will of thy user.<|im_end|>
<|im_start|>User request
Take off your helmet.<|im_end|>
<|im_start|>No i shall not. This is the way.
🎲 Recommended Sampler Preset
temperature: 1.1
min_p: 0.1
Axolotl Config ꒰(˶• ᴗ •˶)꒱
base_model: NewEden/Hamanasu-32B-V1
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer

hub_model_id: NewEden/Hamanasu-FFT-Instruct
hub_strategy: "all_checkpoints"
push_dataset_to_hub:
hf_use_auth_token: true

plugins:
  - axolotl.integrations.liger.LigerPlugin
liger_rope: true
liger_rms_norm: true
liger_swiglu: true
liger_fused_linear_cross_entropy: true

load_in_8bit: false
load_in_4bit: false
strict: false

datasets:
  - path: NewEden/Hydrus-R1-Thinking-Sharegpt
    type: dan-chat-advanced
  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
    type: dan-chat-advanced
  - path: Nitral-AI/ARES-ShareGPT
    type: dan-chat-advanced
  - path: NewEden/Hydrus-HelpSteer2
    type: dan-chat-advanced
  - path: PocketDoc/Dans-Codemaxx-CodeFeedback-Conversations
    type: dan-chat-advanced
  - path: PocketDoc/Dans-Toolmaxx-Agent
    type: dan-chat-advanced
  - path: PocketDoc/Dans-Assistantmaxx-Tulu3-IF
    type: dan-chat-advanced
  - path: NewEden/Hydrus-SonnetOrca
    type: dan-chat-advanced
  - path: NewEden/Hydrus-Chat_error-Pure-Dove-sharegpt
    type: dan-chat-advanced 
  - path: NewEden/No_Robots-R1-Filtered
    type: dan-chat-advanced
  - path: NewEden/GSM8K-R1-filtered
    type: dan-chat-advanced  
  - path: NewEden/Hydrus_Anthropic_hh_harmful-sharegpt
    type: dan-chat-advanced  
  - path: NewEden/Hydrus-Instruct-SmolTalk
    type: dan-chat-advanced
  - path: PocketDoc/Dans-Logicmaxx-Skunkworks
    type: dan-chat-advanced
  - path: PocketDoc/Dans-Logicmaxx-SAT-AP
    type: dan-chat-advanced
  - path: PocketDoc/Dans-Toolmaxx-ShellCommands
    type: dan-chat-advanced
  - path: PocketDoc/Dans-Taskmaxx-Edit
    type: dan-chat-advanced
dataset_prepared_path: prepared_data
val_set_size: 0.0
output_dir: ./qwq-inst

sequence_len: 32768
sample_packing: true
pad_to_sequence_len: true

wandb_project: qwq
wandb_entity:
wandb_watch:
wandb_name: instruct-attempt-03
wandb_log_model:

gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: paged_adamw_8bit
lr_scheduler: cosine
learning_rate: 5e-6

train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false

gradient_checkpointing: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 1
xformers_attention:
flash_attention: true

warmup_steps: 40
evals_per_epoch:
eval_table_size:
eval_max_new_tokens:
saves_per_epoch: 2
debug:
deepspeed: deepspeed_configs/zero3_bf16.json
weight_decay: 0.02
fsdp:
fsdp_config:
special_tokens:
⚡ Credits

Made by
Delta-Vector

Runs of Delta-Vector Hamanasu-QwQ-V1.5-Instruct on huggingface.co

42
Total runs
1
24-hour runs
1
3-day runs
14
7-day runs
31
30-day runs

More Information About Hamanasu-QwQ-V1.5-Instruct huggingface.co Model

Hamanasu-QwQ-V1.5-Instruct huggingface.co

Hamanasu-QwQ-V1.5-Instruct huggingface.co is an AI model on huggingface.co that provides Hamanasu-QwQ-V1.5-Instruct's model effect (), which can be used instantly with this Delta-Vector Hamanasu-QwQ-V1.5-Instruct model. huggingface.co supports a free trial of the Hamanasu-QwQ-V1.5-Instruct model, and also provides paid use of the Hamanasu-QwQ-V1.5-Instruct. Support call Hamanasu-QwQ-V1.5-Instruct model through api, including Node.js, Python, http.

Hamanasu-QwQ-V1.5-Instruct huggingface.co Url

https://huggingface.co/Delta-Vector/Hamanasu-QwQ-V1.5-Instruct

Delta-Vector Hamanasu-QwQ-V1.5-Instruct online free

Hamanasu-QwQ-V1.5-Instruct huggingface.co is an online trial and call api platform, which integrates Hamanasu-QwQ-V1.5-Instruct's modeling effects, including api services, and provides a free online trial of Hamanasu-QwQ-V1.5-Instruct, you can try Hamanasu-QwQ-V1.5-Instruct online for free by clicking the link below.

Delta-Vector Hamanasu-QwQ-V1.5-Instruct online free url in huggingface.co:

https://huggingface.co/Delta-Vector/Hamanasu-QwQ-V1.5-Instruct

Hamanasu-QwQ-V1.5-Instruct install

Hamanasu-QwQ-V1.5-Instruct is an open source model from GitHub that offers a free installation service, and any user can find Hamanasu-QwQ-V1.5-Instruct on GitHub to install. At the same time, huggingface.co provides the effect of Hamanasu-QwQ-V1.5-Instruct install, users can directly use Hamanasu-QwQ-V1.5-Instruct installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

Hamanasu-QwQ-V1.5-Instruct install url in huggingface.co:

https://huggingface.co/Delta-Vector/Hamanasu-QwQ-V1.5-Instruct

Url of Hamanasu-QwQ-V1.5-Instruct

Hamanasu-QwQ-V1.5-Instruct huggingface.co Url

Provider of Hamanasu-QwQ-V1.5-Instruct huggingface.co

Delta-Vector
ORGANIZATIONS

Other API from Delta-Vector

huggingface.co

Total runs: 46
Run Growth: 13
Growth Rate: 28.26%
Updated:December 31 2024
huggingface.co

Total runs: 36
Run Growth: 13
Growth Rate: 36.11%
Updated:December 31 2024