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

Extend api/show and ollama show to return more model info (#4881)

Browse source 
* API Show Extended

* Initial Draft of Information

Co-Authored-By: Patrick Devine <pdevine@sonic.net>

* Clean Up

* Descriptive arg error messages and other fixes

* Second Draft of Show with Projectors Included

* Remove Chat Template

* Touches

* Prevent wrapping from files

* Verbose functionality

* Docs

* Address Feedback

* Lint

* Resolve Conflicts

* Function Name

* Tests for api/show model info

* Show Test File

* Add Projector Test

* Clean routes

* Projector Check

* Move Show Test

* Touches

* Doc update

---------

Co-authored-by: Patrick Devine <pdevine@sonic.net>
This commit is contained in:
royjhan 2024-06-19 14:19:02 -07:00 committed by GitHub
parent 97c59be653
commit fedf71635e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 243 additions and 30 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

19
api/types.go
View file

@ -253,6 +253,7 @@ type ShowRequest struct {
Model string `json:"model"`
System string `json:"system"`
Template string `json:"template"`
Verbose bool `json:"verbose"`
Options map[string]interface{} `json:"options"`
@ -262,14 +263,16 @@ type ShowRequest struct {
// ShowResponse is the response returned from [Client.Show].
type ShowResponse struct {
License string `json:"license,omitempty"`
Modelfile string `json:"modelfile,omitempty"`
Parameters string `json:"parameters,omitempty"`
Template string `json:"template,omitempty"`
System string `json:"system,omitempty"`
Details ModelDetails `json:"details,omitempty"`
Messages []Message `json:"messages,omitempty"`
ModifiedAt time.Time `json:"modified_at,omitempty"`
License string `json:"license,omitempty"`
Modelfile string `json:"modelfile,omitempty"`
Parameters string `json:"parameters,omitempty"`
Template string `json:"template,omitempty"`
System string `json:"system,omitempty"`
Details ModelDetails `json:"details,omitempty"`
Messages []Message `json:"messages,omitempty"`
ModelInfo map[string]any `json:"model_info,omitempty"`
ProjectorInfo map[string]any `json:"projector_info,omitempty"`
ModifiedAt time.Time `json:"modified_at,omitempty"`
}
// CopyRequest is the request passed to [Client.Copy].

143
cmd/cmd.go
View file

@ -579,10 +579,6 @@ func ShowHandler(cmd *cobra.Command, args []string) error {
return err
}
if len(args) != 1 {
return errors.New("missing model name")
}
license, errLicense := cmd.Flags().GetBool("license")
modelfile, errModelfile := cmd.Flags().GetBool("modelfile")
parameters, errParams := cmd.Flags().GetBool("parameters")
@ -625,8 +621,29 @@ func ShowHandler(cmd *cobra.Command, args []string) error {
if flagsSet > 1 {
return errors.New("only one of '--license', '--modelfile', '--parameters', '--system', or '--template' can be specified")
} else if flagsSet == 0 {
return errors.New("one of '--license', '--modelfile', '--parameters', '--system', or '--template' must be specified")
}
if flagsSet == 1 {
req := api.ShowRequest{Name: args[0]}
resp, err := client.Show(cmd.Context(), &req)
if err != nil {
return err
}
switch showType {
case "license":
fmt.Println(resp.License)
case "modelfile":
fmt.Println(resp.Modelfile)
case "parameters":
fmt.Println(resp.Parameters)
case "system":
fmt.Println(resp.System)
case "template":
fmt.Println(resp.Template)
}
return nil
}
req := api.ShowRequest{Name: args[0]}
@ -635,22 +652,114 @@ func ShowHandler(cmd *cobra.Command, args []string) error {
return err
}
switch showType {
case "license":
fmt.Println(resp.License)
case "modelfile":
fmt.Println(resp.Modelfile)
case "parameters":
fmt.Println(resp.Parameters)
case "system":
fmt.Println(resp.System)
case "template":
fmt.Println(resp.Template)
arch := resp.ModelInfo["general.architecture"].(string)
modelData := [][]string{
{"arch", arch},
{"parameters", resp.Details.ParameterSize},
{"quantization", resp.Details.QuantizationLevel},
{"context length", fmt.Sprintf("%v", resp.ModelInfo[fmt.Sprintf("%s.context_length", arch)].(float64))},
{"embedding length", fmt.Sprintf("%v", resp.ModelInfo[fmt.Sprintf("%s.embedding_length", arch)].(float64))},
}
mainTableData := [][]string{
{"Model"},
{renderSubTable(modelData, false)},
}
if resp.ProjectorInfo != nil {
projectorData := [][]string{
{"arch", "clip"},
{"parameters", format.HumanNumber(uint64(resp.ProjectorInfo["general.parameter_count"].(float64)))},
{"projector type", resp.ProjectorInfo["clip.projector_type"].(string)},
{"embedding length", fmt.Sprintf("%v", resp.ProjectorInfo["clip.vision.embedding_length"].(float64))},
{"projection dimensionality", fmt.Sprintf("%v", resp.ProjectorInfo["clip.vision.projection_dim"].(float64))},
}
mainTableData = append(mainTableData,
[]string{"Projector"},
[]string{renderSubTable(projectorData, false)},
)
}
if resp.Parameters != "" {
mainTableData = append(mainTableData, []string{"Parameters"}, []string{formatParams(resp.Parameters)})
}
if resp.System != "" {
mainTableData = append(mainTableData, []string{"System"}, []string{renderSubTable(twoLines(resp.System), true)})
}
if resp.License != "" {
mainTableData = append(mainTableData, []string{"License"}, []string{renderSubTable(twoLines(resp.License), true)})
}
table := tablewriter.NewWriter(os.Stdout)
table.SetAutoWrapText(false)
table.SetBorder(false)
table.SetAlignment(tablewriter.ALIGN_LEFT)
for _, v := range mainTableData {
table.Append(v)
}
table.Render()
return nil
}
func renderSubTable(data [][]string, file bool) string {
var buf bytes.Buffer
table := tablewriter.NewWriter(&buf)
table.SetAutoWrapText(!file)
table.SetBorder(false)
table.SetNoWhiteSpace(true)
table.SetTablePadding("\t")
table.SetAlignment(tablewriter.ALIGN_LEFT)
for _, v := range data {
table.Append(v)
}
table.Render()
renderedTable := buf.String()
lines := strings.Split(renderedTable, "\n")
for i, line := range lines {
lines[i] = "\t" + line
}
return strings.Join(lines, "\n")
}
func twoLines(s string) [][]string {
lines := strings.Split(s, "\n")
res := [][]string{}
count := 0
for _, line := range lines {
line = strings.TrimSpace(line)
if line != "" {
count++
res = append(res, []string{line})
if count == 2 {
return res
}
}
}
return res
}
func formatParams(s string) string {
lines := strings.Split(s, "\n")
table := [][]string{}
for _, line := range lines {
table = append(table, strings.Fields(line))
}
return renderSubTable(table, false)
}
func CopyHandler(cmd *cobra.Command, args []string) error {
client, err := api.ClientFromEnvironment()
if err != nil {

37
docs/api.md
View file

@ -777,11 +777,12 @@ A single JSON object will be returned.
POST /api/show
```
Show information about a model including details, modelfile, template, parameters, license, and system prompt.
Show information about a model including details, modelfile, template, parameters, license, system prompt.
### Parameters
- `name`: name of the model to show
- `verbose`: (optional) if set to `true`, returns full data for verbose response fields
### Examples
@ -798,14 +799,40 @@ curl http://localhost:11434/api/show -d '{
```json
{
"modelfile": "# Modelfile generated by \"ollama show\"\n# To build a new Modelfile based on this one, replace the FROM line with:\n# FROM llava:latest\n\nFROM /Users/matt/.ollama/models/blobs/sha256:200765e1283640ffbd013184bf496e261032fa75b99498a9613be4e94d63ad52\nTEMPLATE \"\"\"{{ .System }}\nUSER: {{ .Prompt }}\nASSISTANT: \"\"\"\nPARAMETER num_ctx 4096\nPARAMETER stop \"\u003c/s\u003e\"\nPARAMETER stop \"USER:\"\nPARAMETER stop \"ASSISTANT:\"",
"parameters": "num_ctx 4096\nstop \u003c/s\u003e\nstop USER:\nstop ASSISTANT:",
"template": "{{ .System }}\nUSER: {{ .Prompt }}\nASSISTANT: ",
"parameters": "num_keep 24\nstop \"<|start_header_id|>\"\nstop \"<|end_header_id|>\"\nstop \"<|eot_id|>\"",
"template": "{{ if .System }}<|start_header_id|>system<|end_header_id|>\n\n{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>\n\n{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>\n\n{{ .Response }}<|eot_id|>",
"details": {
"parent_model": "",
"format": "gguf",
"family": "llama",
"families": ["llama", "clip"],
"parameter_size": "7B",
"families": [
"llama"
],
"parameter_size": "8.0B",
"quantization_level": "Q4_0"
},
"model_info": {
"general.architecture": "llama",
"general.file_type": 2,
"general.parameter_count": 8030261248,
"general.quantization_version": 2,
"llama.attention.head_count": 32,
"llama.attention.head_count_kv": 8,
"llama.attention.layer_norm_rms_epsilon": 0.00001,
"llama.block_count": 32,
"llama.context_length": 8192,
"llama.embedding_length": 4096,
"llama.feed_forward_length": 14336,
"llama.rope.dimension_count": 128,
"llama.rope.freq_base": 500000,
"llama.vocab_size": 128256,
"tokenizer.ggml.bos_token_id": 128000,
"tokenizer.ggml.eos_token_id": 128009,
"tokenizer.ggml.merges": [], // populates if `verbose=true`
"tokenizer.ggml.model": "gpt2",
"tokenizer.ggml.pre": "llama-bpe",
"tokenizer.ggml.token_type": [], // populates if `verbose=true`
"tokenizer.ggml.tokens": [] // populates if `verbose=true`
}
}
```

35
server/routes.go
View file

@ -734,9 +734,44 @@ func GetModelInfo(req api.ShowRequest) (*api.ShowResponse, error) {
fmt.Fprint(&sb, m.String())
resp.Modelfile = sb.String()
kvData, err := getKVData(m.ModelPath, req.Verbose)
if err != nil {
return nil, err
}
delete(kvData, "general.name")
delete(kvData, "tokenizer.chat_template")
resp.ModelInfo = kvData
if len(m.ProjectorPaths) > 0 {
projectorData, err := getKVData(m.ProjectorPaths[0], req.Verbose)
if err != nil {
return nil, err
}
resp.ProjectorInfo = projectorData
}
return resp, nil
}
func getKVData(digest string, verbose bool) (llm.KV, error) {
kvData, err := llm.LoadModel(digest)
if err != nil {
return nil, err
}
kv := kvData.KV()
if !verbose {
for k := range kv {
if t, ok := kv[k].([]any); len(t) > 5 && ok {
kv[k] = []any{}
}
}
}
return kv, nil
}
func (s *Server) ListModelsHandler(c *gin.Context) {
ms, err := Manifests()
if err != nil {

39
server/routes_test.go
View file

@ -19,6 +19,7 @@ import (
"github.com/ollama/ollama/api"
"github.com/ollama/ollama/envconfig"
"github.com/ollama/ollama/llm"
"github.com/ollama/ollama/parser"
"github.com/ollama/ollama/types/model"
"github.com/ollama/ollama/version"
@ -212,6 +213,7 @@ func Test_Routes(t *testing.T) {
"top_p 0.9",
}
assert.Equal(t, expectedParams, params)
assert.InDelta(t, 0, showResp.ModelInfo["general.parameter_count"], 1e-9, "Parameter count should be 0")
},
},
}
@ -325,3 +327,40 @@ func TestCase(t *testing.T) {
})
}
}
func TestShow(t *testing.T) {
t.Setenv("OLLAMA_MODELS", t.TempDir())
envconfig.LoadConfig()
var s Server
createRequest(t, s.CreateModelHandler, api.CreateRequest{
Name: "show-model",
Modelfile: fmt.Sprintf(
"FROM %s\nFROM %s",
createBinFile(t, llm.KV{"general.architecture": "test"}, nil),
createBinFile(t, llm.KV{"general.architecture": "clip"}, nil),
),
})
w := createRequest(t, s.ShowModelHandler, api.ShowRequest{
Name: "show-model",
})
if w.Code != http.StatusOK {
t.Fatalf("expected status code 200, actual %d", w.Code)
}
var resp api.ShowResponse
if err := json.NewDecoder(w.Body).Decode(&resp); err != nil {
t.Fatal(err)
}
if resp.ModelInfo["general.architecture"] != "test" {
t.Fatal("Expected model architecture to be 'test', but got", resp.ModelInfo["general.architecture"])
}
if resp.ProjectorInfo["general.architecture"] != "clip" {
t.Fatal("Expected projector architecture to be 'clip', but got", resp.ProjectorInfo["general.architecture"])
}
}