🚀 模型倉庫：magnum-v4-123b
本倉庫包含模型的GGUF量化版本。如果你需要原始權重，請點擊此處查找。
這是一系列旨在複製Claude 3系列模型（特別是Sonnet和Opus）散文質量的模型。該模型在mistralai/Mistral-Large-Instruct-2407的基礎上進行微調。
🚀 快速開始
本倉庫包含模型的GGUF量化版本。如果你需要原始權重，請點擊此處查找。
✨ 主要特性
這是一系列旨在複製Claude 3系列模型（特別是Sonnet和Opus）散文質量的模型。該模型在mistralai/Mistral-Large-Instruct-2407的基礎上進行微調。
💻 使用示例
基礎用法
典型的輸入格式如下：
<s>[INST] SYSTEM MESSAGE\nUSER MESSAGE[/INST] ASSISTANT MESSAGE</s>[INST] USER MESSAGE[/INST]
高級用法
SillyTavern模板
以下是SillyTavern中使用的指令模板和上下文模板。
上下文模板
default SillyTavern template works fine
指令模板
default SillyTavern template works fine
Axolotl配置
查看Axolotl配置
base_model: mistralai/Mistral-Large-Instruct-2407
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
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: anthracite-org/c2_logs_16k_mistral-large_v1.2
type: sharegpt
conversation: mistral
- path: anthracite-org/kalo-opus-instruct-22k-no-refusal
type: sharegpt
conversation: mistral
- path: lodrick-the-lafted/kalo-opus-instruct-3k-filtered
type: sharegpt
conversation: mistral
- path: anthracite-org/nopm_claude_writing_fixed
type: sharegpt
conversation: mistral
- path: anthracite-org/kalo_opus_misc_240827
type: sharegpt
conversation: mistral
- path: anthracite-org/kalo_misc_part2
type: sharegpt
conversation: mistral
shuffle_merged_datasets: true
dataset_prepared_path: ./data/magnum-123b-data
val_set_size: 0.0
output_dir: ./data/123b-fft-out
sequence_len: 16384
sample_packing: true
pad_to_sequence_len: true
adapter:
lora_model_dir:
lora_r:
lora_alpha:
lora_dropout:
lora_target_linear:
lora_fan_in_fan_out:
wandb_project: 123b-magnum-fft
wandb_entity:
wandb_watch:
wandb_name: alter-attempt-04
wandb_log_model:
gradient_accumulation_steps: 4
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.0000015
train_on_inputs: false
group_by_length: false
bf16: auto
fp16:
tf32: false
gradient_checkpointing: unsloth
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: 0.01
fsdp:
fsdp_config:
special_tokens:
🔧 技術細節
數據集
訓練
我們使用了由Eric Hartford慷慨提供的8個mi300x GPU對模型進行全參數微調。
📄 許可證
本模型使用的許可證為MRL（other）。
🙏 致謝
我們要感謝Eric Hartford為本次訓練提供計算資源。同時，也要感謝Anthracite的所有成員，是他們讓這次微調成為可能。
⚠️ 安全說明
...
%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20%23061b40;%20}%20.st1%20{%20fill:%20%23306af1;%20}%20.st2%20{%20fill:%20%235ce5cf;%20}%20%3c/style%3e%3c/defs%3e%3cg%3e%3cpath%20class='st0'%20d='M55,10.5h9v3h-9v9h12V7.5h-12v3ZM64,19.5h-6v-3h6v3Z'/%3e%3cpolygon%20class='st0'%20points='69%2016.5%2078%2016.5%2078%2019.5%2069%2019.5%2069%2022.5%2081%2022.5%2081%2013.5%2072%2013.5%2072%2010.5%2081%2010.5%2081%207.5%2069%207.5%2069%2016.5'/%3e%3cpolygon%20class='st0'%20points='95%2010.5%2095%207.5%2083%207.5%2083%2022.5%2095%2022.5%2095%2019.5%2086%2019.5%2086%2016.5%2095%2016.5%2095%2013.5%2086%2013.5%2086%2010.5%2095%2010.5'/%3e%3cpath%20class='st0'%20d='M40,1.5v21h11.6l1.4-1.4v-7.6h0c0,0-1.4-1.5-1.4-1.5l1.4-1.4V2.9l-1.4-1.4h-11.6ZM50,19.5h-7v-6h7v6ZM50,10.5h-7v-6h7v6Z'/%3e%3c/g%3e%3cpath%20class='st1'%20d='M23.1,24L14.7,4.8l-4.9,11.2h3.8l-1.8,4H3.3L12.1,0H2C.9,0,0,.9,0,2v20c0,1.1.9,2,2,2h21.1Z'/%3e%3cpath%20class='st2'%20d='M34,0h-16.8l10.6,24h6.2c1.1,0,2-.9,2-2V2C36,.9,35.1,0,34,0ZM32.5,20h-4V4h4v16Z'/%3e%3c/svg%3e)
Transformers 支持多種語言