Update README.md

README.md

@@ -16,16 +16,20 @@ These settings / suggestions can be applied to all models including GGUF, EXL2,
 It also includes critical settings for Class 3 and Class 4 models at this repo - DavidAU - to enhance and control generation
 for specific as a well as outside use case(s) including role play, chat and other use case(s).
 
-This settings can also fix a number of model issues such as:
+This settings can also fix a number of model issues (any model) such as:
 
 - "Gibberish"
-- letter, word, phrase, paragraph repeats
-- coherence
+- Generation length (including out of control generation)
+- Chat quality.
+- Letter, word, phrase, paragraph repeats
+- Coherence
 - instruction following
 - creativeness or lack there of or .. too much - purple prose. 
 - low quant (ie q2k, iq1s, iq2s) issues.
+- general output quality.
+- role play related issues.
 
-Likewise setting can also improve model generation and/or general overall "smoothness" / "quality" of model operation.
+Likewise ALL the setting below can also improve model generation and/or general overall "smoothness" / "quality" of model operation.
 
 Even if you are not using my models, you may find this document useful for any model available online.
 
@@ -209,6 +213,8 @@ PENALITY SAMPLERS:
 
 These samplers "trim" or "prune" output in real time. The longer the generation, the stronger overall effect.
 
+CLASS 4: For these models it is important to activate / set all samplers as noted for maximum quality and control.
+
 PRIMARY:
 
 <B>repeat-last-n</B>                       	
@@ -308,7 +314,7 @@ mirostat_eta: 0.1 is a good value.
 
 
 This is the big one ; activating this will help with creative generation. It can also help with stability. Also note which 
-samplers are disable/ignored here, and that "mirostat_eta" is a learning rate.
+samplers are disabled/ignored here, and that "mirostat_eta" is a learning rate.
 
 This is both a sampler (and pruner) and enhancement all in one.
 
@@ -369,8 +375,7 @@ Suggest you experiment with this one, with other advanced samplers disabled to s
 <B>l,    logit-bias TOKEN_ID(+/-)BIAS   </B>
 
 modifies the likelihood of token appearing in the completion,
-                                        		i.e. `--logit-bias 15043+1` to increase likelihood of token ' Hello',
-                                        		or `--logit-bias 15043-1` to decrease likelihood of token ' Hello'
+i.e. `--logit-bias 15043+1` to increase likelihood of token ' Hello',  or `--logit-bias 15043-1` to decrease likelihood of token ' Hello'
 
 This may or may not be available. This requires a bit more work.
 
@@ -383,28 +388,6 @@ I suggest you get some "bad outputs" ; get the "tokens" (actual number for the "
 Careful testing is required, as this can have unclear side effects.
 
 
-------------------------------------------------------------------------------
-OTHER:
-------------------------------------------------------------------------------
-
-
-<B>-s,    --seed SEED     </B>                	 
-
-RNG seed (default: -1, use random seed for -1)
-
-<B>samplers SAMPLERS             </B>          
-
-samplers that will be used for generation in the order, separated by ';' (default: top_k;tfs_z;typ_p;top_p;min_p;xtc;temperature)
-
-<B>sampling-seq SEQUENCE          </B>    
-
-simplified sequence for samplers that will be used (default: kfypmxt)
-
-<B>ignore-eos                    </B>             	
-
-ignore end of stream token and continue generating (implies --logit-bias EOS-inf)
-
-
 ------------------------------------------------------------------------------
 ADVANCED SAMPLERS:
 ------------------------------------------------------------------------------