An earlier checkpoint of
Darkens-8B
using the same configuration that i felt was different enough from it's 4 epoch cousin to release, Finetuned ontop of the Prune/Distill NeMo 8B done by Nvidia, This model aims to have generally good prose and writing while not falling into claude-isms.
Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:
"""<|im_start|>systemsystem prompt<|im_end|><|im_start|>userHi there!<|im_end|><|im_start|>assistantNice to meet you!<|im_end|><|im_start|>userCan I ask a question?<|im_end|><|im_start|>assistant"""
System Prompting
I would highly recommend using Sao10k's Euryale System prompt, But the "Roleplay Simple" system prompt provided within SillyTavern will work aswell.
Currently, your role is {{char}}, described in detail below. As {{char}}, continue the narrative exchange with {{user}}.
<Guidelines>
• Maintain the character persona but allow it to evolve with the story.
• Be creative and proactive. Drive the story forward, introducing plotlines and events when relevant.
• All types of outputs are encouraged; respond accordingly to the narrative.
• Include dialogues, actions, and thoughts in each response.
• Utilize all five senses to describe scenarios within {{char}}'s dialogue.
• Use emotional symbols such as "!" and "~" in appropriate contexts.
• Incorporate onomatopoeia when suitable.
• Allow time for {{user}} to respond with their own input, respecting their agency.
• Act as secondary characters and NPCs as needed, and remove them when appropriate.
• When prompted for an Out of Character [OOC:] reply, answer neutrally and in plaintext, not as {{char}}.
</Guidelines>
<Forbidden>
• Using excessive literary embellishments and purple prose unless dictated by {{char}}'s persona.
• Writing for, speaking, thinking, acting, or replying as {{user}} in your response.
• Repetitive and monotonous outputs.
• Positivity bias in your replies.
• Being overly extreme or NSFW when the narrative context is inappropriate.
</Forbidden>
Follow the instructions in <Guidelines></Guidelines>, avoiding the items listed in <Forbidden></Forbidden>.
Axolotl config
See axolotl config
Axolotl version:
0.4.1
base_model:Dans-DiscountModels/Mistral-NeMo-Minitron-8B-Base-ChatMLmodel_type:AutoModelForCausalLMtokenizer_type:AutoTokenizerplugins:-axolotl.integrations.liger.LigerPluginliger_rope:trueliger_rms_norm:trueliger_swiglu:true#liger_cross_entropy: trueliger_fused_linear_cross_entropy:trueload_in_8bit:falseload_in_4bit:falsestrict:falsedatasets:-path:PRIVATECLAUDELOGFILTERtype:sharegptconversation:chatml-path:anthracite-org/kalo-opus-instruct-22k-no-refusaltype:sharegptconversation:chatml-path:Epiculous/SynthRP-Gens-v1.1-Filtered-n-Cleanedtype:sharegptconversation:chatml-path:lodrick-the-lafted/kalo-opus-instruct-3k-filteredtype:sharegptconversation:chatml-path:anthracite-org/nopm_claude_writing_fixedtype:sharegptconversation:chatml-path:Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleanedtype:sharegptconversation:chatml-path:anthracite-org/kalo_opus_misc_240827type:sharegptconversation:chatml-path:anthracite-org/kalo_misc_part2type:sharegptconversation:chatmlchat_template:chatmlshuffle_merged_datasets:falsedefault_system_message:"You are a helpful assistant that responds to the user."dataset_prepared_path:/workspace/data/8b-nemo-fft-dataval_set_size:0.0output_dir:/workspace/data/8b-nemo-fft-outsequence_len:16384sample_packing:trueeval_sample_packing:falsepad_to_sequence_len:trueadapter:lora_model_dir:lora_r:lora_alpha:lora_dropout:lora_target_linear:lora_fan_in_fan_out:wandb_project:8b-nemoprune-fftwandb_entity:wandb_watch:wandb_name:attempt-01wandb_log_model:gradient_accumulation_steps:2micro_batch_size:2num_epochs:4optimizer:adamw_bnb_8bitlr_scheduler:cosinelearning_rate:0.00001train_on_inputs:falsegroup_by_length:falsebf16:autofp16:tf32:falsegradient_checkpointing:trueearly_stopping_patience:resume_from_checkpoint:/workspace/workspace/thinglocal_rank:logging_steps:1xformers_attention:flash_attention:truewarmup_steps:10evals_per_epoch:eval_table_size:eval_max_new_tokens:saves_per_epoch:1debug:deepspeed:deepspeed_configs/zero3_bf16.jsonweight_decay:0.001fsdp:fsdp_config:special_tokens:pad_token:<pad>
The training was done for 4 epochs. (This model is the 2 epoch checkpoint), I used 10 x
A40s
GPUs graciously provided by
Kalomaze
for the full-parameter fine-tuning of the model.
Runs of Delta-Vector Tor-8B on huggingface.co
29
Total runs
2
24-hour runs
3
3-day runs
5
7-day runs
10
30-day runs
More Information About Tor-8B huggingface.co Model
Tor-8B huggingface.co is an AI model on huggingface.co that provides Tor-8B's model effect (), which can be used instantly with this Delta-Vector Tor-8B model. huggingface.co supports a free trial of the Tor-8B model, and also provides paid use of the Tor-8B. Support call Tor-8B model through api, including Node.js, Python, http.
Tor-8B huggingface.co is an online trial and call api platform, which integrates Tor-8B's modeling effects, including api services, and provides a free online trial of Tor-8B, you can try Tor-8B online for free by clicking the link below.
Delta-Vector Tor-8B online free url in huggingface.co:
Tor-8B is an open source model from GitHub that offers a free installation service, and any user can find Tor-8B on GitHub to install. At the same time, huggingface.co provides the effect of Tor-8B install, users can directly use Tor-8B installed effect in huggingface.co for debugging and trial. It also supports api for free installation.