DavidAU commited on
Commit
cbe3629
·
verified ·
1 Parent(s): 98d542f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +11 -0
README.md CHANGED
@@ -274,8 +274,11 @@ Please see sections below this for advanced usage, more details, settings notes
274
  | **Penalty Samplers** |
275
 
276
  | repeat-last-n | Number of tokens to consider for penalties. Critical for preventing repetition. Default: 64 |
 
277
  | repeat-penalty | Penalizes repeated token sequences. Range: 1.0-1.15. Default: 1.0 |
 
278
  | presence-penalty | Penalizes token presence in previous text. Range: 0-0.2 for Class 3, 0.1-0.35 for Class 4 |
 
279
  | frequency-penalty | Penalizes token frequency in previous text. Range: 0-0.25 for Class 3, 0.4-0.8 for Class 4 |
280
 
281
  | penalize-nl | Penalizes newline tokens. Generally unused. Default: false |
@@ -284,10 +287,14 @@ Please see sections below this for advanced usage, more details, settings notes
284
  | **Secondary Samplers** |
285
 
286
  | mirostat | Controls perplexity during sampling. Modes: 0 (off), 1, or 2 |
 
287
  | mirostat-lr | Mirostat learning rate. Default: 0.1 |
 
288
  | mirostat-ent | Mirostat target entropy. Default: 5.0 |
289
 
 
290
  | dynatemp-range | Range for dynamic temperature adjustment. Default: 0.0 |
 
291
  | dynatemp-exp | Exponent for dynamic temperature scaling. Default: 1.0 |
292
 
293
  | tfs | Tail free sampling - removes low-probability tokens. Default: 1.0 |
@@ -295,16 +302,20 @@ Please see sections below this for advanced usage, more details, settings notes
295
  | typical | Selects tokens more likely than random given prior text. Default: 1.0 |
296
 
297
  | xtc-probability | Probability of token removal. Range: 0-1 |
 
298
  | xtc-threshold | Threshold for considering token removal. Default: 0.1 |
299
 
300
 
301
  | **Advanced Samplers** |
302
 
303
  | dry_multiplier | Controls DRY (Don't Repeat Yourself) intensity. Range: 0.8-1.12+ |
 
304
  | dry_allowed_length | Allowed length for repeated sequences in DRY. Default: 2 |
 
305
  | dry_base | Base value for DRY calculations. Range: 1.15-1.75+ for Class 4 |
306
 
307
  | smoothing_factor | Quadratic sampling intensity. Range: 1-3 for Class 3, 3-5+ for Class 4 |
 
308
  | smoothing_curve | Quadratic sampling curve. Range: 1 for Class 3, 1.5-2 for Class 4 |
309
 
310
 
 
274
  | **Penalty Samplers** |
275
 
276
  | repeat-last-n | Number of tokens to consider for penalties. Critical for preventing repetition. Default: 64 |
277
+
278
  | repeat-penalty | Penalizes repeated token sequences. Range: 1.0-1.15. Default: 1.0 |
279
+
280
  | presence-penalty | Penalizes token presence in previous text. Range: 0-0.2 for Class 3, 0.1-0.35 for Class 4 |
281
+
282
  | frequency-penalty | Penalizes token frequency in previous text. Range: 0-0.25 for Class 3, 0.4-0.8 for Class 4 |
283
 
284
  | penalize-nl | Penalizes newline tokens. Generally unused. Default: false |
 
287
  | **Secondary Samplers** |
288
 
289
  | mirostat | Controls perplexity during sampling. Modes: 0 (off), 1, or 2 |
290
+
291
  | mirostat-lr | Mirostat learning rate. Default: 0.1 |
292
+
293
  | mirostat-ent | Mirostat target entropy. Default: 5.0 |
294
 
295
+
296
  | dynatemp-range | Range for dynamic temperature adjustment. Default: 0.0 |
297
+
298
  | dynatemp-exp | Exponent for dynamic temperature scaling. Default: 1.0 |
299
 
300
  | tfs | Tail free sampling - removes low-probability tokens. Default: 1.0 |
 
302
  | typical | Selects tokens more likely than random given prior text. Default: 1.0 |
303
 
304
  | xtc-probability | Probability of token removal. Range: 0-1 |
305
+
306
  | xtc-threshold | Threshold for considering token removal. Default: 0.1 |
307
 
308
 
309
  | **Advanced Samplers** |
310
 
311
  | dry_multiplier | Controls DRY (Don't Repeat Yourself) intensity. Range: 0.8-1.12+ |
312
+
313
  | dry_allowed_length | Allowed length for repeated sequences in DRY. Default: 2 |
314
+
315
  | dry_base | Base value for DRY calculations. Range: 1.15-1.75+ for Class 4 |
316
 
317
  | smoothing_factor | Quadratic sampling intensity. Range: 1-3 for Class 3, 3-5+ for Class 4 |
318
+
319
  | smoothing_curve | Quadratic sampling curve. Range: 1 for Class 3, 1.5-2 for Class 4 |
320
 
321