baalajimaestro/ollama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

feat: add support for min_p (resolve #1142) (#1825)

Browse source
This commit is contained in:
Tibor Schmidt 2024-07-27 23:37:40 +02:00 committed by GitHub
parent f2a96c7d77
commit f3d7a481b7
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
6 changed files with 6 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

1
api/types.go
View file

@ -209,6 +209,7 @@ type Options struct {
NumPredict int `json:"num_predict,omitempty"`
TopK int `json:"top_k,omitempty"`
TopP float32 `json:"top_p,omitempty"`
MinP float32 `json:"min_p,omitempty"`
TFSZ float32 `json:"tfs_z,omitempty"`
TypicalP float32 `json:"typical_p,omitempty"`
RepeatLastN int `json:"repeat_last_n,omitempty"`

1
cmd/interactive.go
View file

@ -138,6 +138,7 @@ func generateInteractive(cmd *cobra.Command, opts runOptions) error {
fmt.Fprintln(os.Stderr, " /set parameter num_predict <int> Max number of tokens to predict")
fmt.Fprintln(os.Stderr, " /set parameter top_k <int> Pick from top k num of tokens")
fmt.Fprintln(os.Stderr, " /set parameter top_p <float> Pick token based on sum of probabilities")
fmt.Fprintln(os.Stderr, " /set parameter min_p <float> Pick token based on top token probability * min_p")
fmt.Fprintln(os.Stderr, " /set parameter num_ctx <int> Set the context size")
fmt.Fprintln(os.Stderr, " /set parameter temperature <float> Set creativity level")
fmt.Fprintln(os.Stderr, " /set parameter repeat_penalty <float> How strongly to penalize repetitions")

1
docs/api.md
View file

@ -336,6 +336,7 @@ curl http://localhost:11434/api/generate -d '{
"num_predict": 100,
"top_k": 20,
"top_p": 0.9,
"min_p": 0.0,
"tfs_z": 0.5,
"typical_p": 0.7,
"repeat_last_n": 33,

1
docs/modelfile.md
View file

@ -141,6 +141,7 @@ PARAMETER <parameter> <parametervalue>
| num_predict | Maximum number of tokens to predict when generating text. (Default: 128, -1 = infinite generation, -2 = fill context) | int | num_predict 42 |
| top_k | Reduces the probability of generating nonsense. A higher value (e.g. 100) will give more diverse answers, while a lower value (e.g. 10) will be more conservative. (Default: 40) | int | top_k 40 |
| top_p | Works together with top-k. A higher value (e.g., 0.95) will lead to more diverse text, while a lower value (e.g., 0.5) will generate more focused and conservative text. (Default: 0.9) | float | top_p 0.9 |
| min_p | Alternative to the top_p, and aims to ensure a balance of quality and variety. The parameter *p* represents the minimum probability for a token to be considered, relative to the probability of the most likely token. For example, with *p*=0.05 and the most likely token having a probability of 0.9, logits with a value less than 0.045 are filtered out. (Default: 0.0) | float | min_p 0.05 |
### TEMPLATE

1
llm/server.go
View file

@ -727,6 +727,7 @@ func (s *llmServer) Completion(ctx context.Context, req CompletionRequest, fn fu
"temperature": req.Options.Temperature,
"top_k": req.Options.TopK,
"top_p": req.Options.TopP,
"min_p": req.Options.MinP,
"tfs_z": req.Options.TFSZ,
"typical_p": req.Options.TypicalP,
"repeat_last_n": req.Options.RepeatLastN,

1
parser/parser_test.go
View file

@ -451,6 +451,7 @@ func TestParseFileParameters(t *testing.T) {
"num_predict 1": {"num_predict", "1"},
"top_k 1": {"top_k", "1"},
"top_p 1.0": {"top_p", "1.0"},
"min_p 0.05": {"min_p", "0.05"},
"tfs_z 1.0": {"tfs_z", "1.0"},
"typical_p 1.0": {"typical_p", "1.0"},
"repeat_last_n 1": {"repeat_last_n", "1"},