exl2 quant (measurement.json in main branch)
check revisions for quants (3bpw,4bpw,5bpw,6bpw,8bpw)
Back from the dead! Hoping to make something cool to share with everyone! Introducing Crimson Dawn! Built atop the impressive Mistral-Nemo-Base-2407; Crimson Dawn was built with the idea that AI should not be a boring bland generic assistant, but something that you can connect with on a more personal level. Something that can be interesting in a Roleplay, but useful as an assistant too.
Prompting
Crimson Dawn was trained with the Mistral Instruct template, therefore it should be prompted in the same way that you would prompt any other mistral model.
"[INST] Prompt goes here [/INST]"
Current Top Sampler Settings
{
"temp": 1.25,
"temperature_last": true,
"top_p": 1,
"top_k": -1,
"top_a": 0,
"tfs": 1,
"epsilon_cutoff": 0,
"eta_cutoff": 0,
"typical_p": 1,
"min_p": 0.3,
"rep_pen": 1,
"rep_pen_range": 0,
"rep_pen_decay": 0,
"rep_pen_slope": 1,
"no_repeat_ngram_size": 0,
"penalty_alpha": 0,
"num_beams": 1,
"length_penalty": 1,
"min_length": 0,
"encoder_rep_pen": 1,
"freq_pen": 0,
"presence_pen": 0,
"skew": 0,
"do_sample": true,
"early_stopping": false,
"dynatemp": false,
"min_temp": 0,
"max_temp": 2,
"dynatemp_exponent": 1,
"smoothing_factor": 0,
"smoothing_curve": 1,
"dry_allowed_length": 2,
"dry_multiplier": 0,
"dry_base": 1.75,
"dry_sequence_breakers": "[\"\\n\", \":\", \"\\\"\", \"*\"]",
"dry_penalty_last_n": 0,
"add_bos_token": true,
"ban_eos_token": false,
"skip_special_tokens": true,
"mirostat_mode": 0,
"mirostat_tau": 5,
"mirostat_eta": 0.1,
"guidance_scale": 1,
"negative_prompt": "",
"grammar_string": "",
"json_schema": {},
"banned_tokens": "",
"sampler_priority": [
"temperature",
"dynamic_temperature",
"quadratic_sampling",
"top_k",
"top_p",
"typical_p",
"epsilon_cutoff",
"eta_cutoff",
"tfs",
"top_a",
"min_p",
"mirostat"
],
"samplers": [
"top_k",
"tfs_z",
"typical_p",
"top_p",
"min_p",
"temperature"
],
"ignore_eos_token": false,
"spaces_between_special_tokens": true,
"speculative_ngram": false,
"sampler_order": [
5,
6,
0,
1,
2,
3,
4
],
"logit_bias": [],
"ignore_eos_token_aphrodite": false,
"spaces_between_special_tokens_aphrodite": true,
"rep_pen_size": 0,
"genamt": 1024,
"max_length": 16384
}
Training
Training was done twice over 2 epochs each on two 2x NVIDIA A6000 GPUs using LoRA. A two-phased approach was used in which the base model was trained 2 epochs on RP data, the LoRA was then applied to base. Finally, the new modified base was trained 2 epochs on instruct, and the new instruct LoRA was applied to the modified base, resulting in what you see here.
Special Thanks
Special thanks to my friends over at Anthracite! Without their help and Kalomaze starting the synthetic data script, none of this would have been possible. Also want to thank my friends in The Chaotic Neutrals for their friendship, support, and guidance.