🚀 马格南（Magnum） v4 - 12B 模型
这是一系列旨在复刻Claude 3系列模型（特别是Sonnet和Opus）散文质量的模型。该模型基于 mistralai/Mistral - Nemo - Instruct - 2407 进行微调。
🚀 快速开始
本模型可用于文本生成任务，以下是使用时的一些关键信息。
✨ 主要特性
📦 安装相关
文档未提及安装步骤，暂不提供。
💻 使用示例
基础用法
典型的输入格式如下：
<s>[INST] SYSTEM MESSAGE
USER MESSAGE[/INST] ASSISTANT MESSAGE</s>[INST] USER MESSAGE[/INST]
高级用法
文档未提及高级用法相关代码示例，暂不提供。
📚 详细文档
SillyTavern模板
以下是SillyTavern中使用的指令（Instruct）和上下文（Context）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-Nemo-Instruct-2407
model_type: AutoModelForCausalLM
tokenizer_type: AutoTokenizer
hub_model_id: anthracite-org/magnum-v4-12b-r2
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: anthracite-org/c2_logs_32k_llama3_qwen2_v1.2_no_system
type: custommistralv3tekken
- path: anthracite-org/kalo-opus-instruct-22k-no-refusal-no-system
type: custommistralv3tekken
- path: anthracite-org/kalo-opus-instruct-3k-filtered-no-system
type: custommistralv3tekken
- path: anthracite-org/nopm_claude_writing_fixed
type: custommistralv3tekken
- path: anthracite-org/kalo_opus_misc_240827_no_system
type: custommistralv3tekken
- path: anthracite-org/kalo_misc_part2_no_system
type: custommistralv3tekken
shuffle_merged_datasets: true
dataset_prepared_path: /workspace/data/magnum-12b-data
val_set_size: 0.0
output_dir: /workspace/data/12b-fft-out
sequence_len: 32768
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: 12b-magnum-fft
wandb_entity:
wandb_watch:
wandb_name: v4-r2-attempt-01
wandb_log_model:
gradient_accumulation_steps: 2
micro_batch_size: 1
num_epochs: 2
optimizer: adamw_bnb_8bit
lr_scheduler: cosine
learning_rate: 0.00001
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/zero2.json
weight_decay: 0.1
fsdp:
fsdp_config:
special_tokens:
pad_token: <pad>
数据集
训练
模型训练进行了2个轮次（epochs）。使用了8块 [H100s](https://www.nvidia.com/en - us/data - center/h100/) GPU进行全参数微调，这些计算资源由 Recursal AI / Featherless AI 慷慨提供。
[
](https://github.com/OpenAccess - AI - Collective/axolotl)
安全
文档未提供相关详细内容。
[开放大语言模型排行榜评估结果](https://huggingface.co/spaces/open - llm - leaderboard/open_llm_leaderboard)
详细结果可查看 [此处](https://huggingface.co/datasets/open - llm - leaderboard/details_anthracite - org__magnum - v4 - 12b)
| 指标 |
值 |
| 平均值 |
19.95 |
| IFEval (0 - 样本) |
33.93 |
| BBH (3 - 样本) |
30.50 |
| MATH Lvl 5 (4 - 样本) |
9.82 |
| GPQA (0 - 样本) |
6.15 |
| MuSR (0 - 样本) |
10.36 |
| MMLU - PRO (5 - 样本) |
28.93 |
🔧 技术细节
文档未提供具体技术实现细节，跳过该章节。
📄 许可证
本模型使用Apache 2.0许可证。
致谢
我们要感谢Recursal / Featherless为本次训练提供计算资源。自第一代72B模型以来，Featherless一直托管我们的Magnum模型，让数千人能够使用我们的模型，助力我们不断发展。
我们也要感谢Anthracite的所有成员，是他们让这次微调得以实现。
%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 支持多种语言