docs: update examples to use llama3.1 (#6718)
This commit is contained in:
Jeffrey Morgan
GitHub
parent
4a8069f9c4
commit
83a9b5271a
6 changed files with 45 additions and 45 deletions
48
docs/api.md
48
docs/api.md
|
|
@ -69,7 +69,7 @@ Enable JSON mode by setting the `format` parameter to `json`. This will structur
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/generate -d '{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"prompt": "Why is the sky blue?"
|
||||
}'
|
||||
```
|
||||
|
|
@ -80,7 +80,7 @@ A stream of JSON objects is returned:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"created_at": "2023-08-04T08:52:19.385406455-07:00",
|
||||
"response": "The",
|
||||
"done": false
|
||||
|
|
@ -102,7 +102,7 @@ To calculate how fast the response is generated in tokens per second (token/s),
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"created_at": "2023-08-04T19:22:45.499127Z",
|
||||
"response": "",
|
||||
"done": true,
|
||||
|
|
@ -124,7 +124,7 @@ A response can be received in one reply when streaming is off.
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/generate -d '{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"prompt": "Why is the sky blue?",
|
||||
"stream": false
|
||||
}'
|
||||
|
|
@ -136,7 +136,7 @@ If `stream` is set to `false`, the response will be a single JSON object:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"created_at": "2023-08-04T19:22:45.499127Z",
|
||||
"response": "The sky is blue because it is the color of the sky.",
|
||||
"done": true,
|
||||
|
|
@ -194,7 +194,7 @@ curl http://localhost:11434/api/generate -d '{
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/generate -d '{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"prompt": "What color is the sky at different times of the day? Respond using JSON",
|
||||
"format": "json",
|
||||
"stream": false
|
||||
|
|
@ -205,7 +205,7 @@ curl http://localhost:11434/api/generate -d '{
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"created_at": "2023-11-09T21:07:55.186497Z",
|
||||
"response": "{\n\"morning\": {\n\"color\": \"blue\"\n},\n\"noon\": {\n\"color\": \"blue-gray\"\n},\n\"afternoon\": {\n\"color\": \"warm gray\"\n},\n\"evening\": {\n\"color\": \"orange\"\n}\n}\n",
|
||||
"done": true,
|
||||
|
|
@ -327,7 +327,7 @@ If you want to set custom options for the model at runtime rather than in the Mo
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/generate -d '{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"prompt": "Why is the sky blue?",
|
||||
"stream": false,
|
||||
"options": {
|
||||
|
|
@ -368,7 +368,7 @@ curl http://localhost:11434/api/generate -d '{
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"created_at": "2023-08-04T19:22:45.499127Z",
|
||||
"response": "The sky is blue because it is the color of the sky.",
|
||||
"done": true,
|
||||
|
|
@ -390,7 +390,7 @@ If an empty prompt is provided, the model will be loaded into memory.
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/generate -d '{
|
||||
"model": "llama3"
|
||||
"model": "llama3.1"
|
||||
}'
|
||||
```
|
||||
|
||||
|
|
@ -400,7 +400,7 @@ A single JSON object is returned:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"created_at": "2023-12-18T19:52:07.071755Z",
|
||||
"response": "",
|
||||
"done": true
|
||||
|
|
@ -445,7 +445,7 @@ Send a chat message with a streaming response.
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/chat -d '{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
|
|
@ -461,7 +461,7 @@ A stream of JSON objects is returned:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"created_at": "2023-08-04T08:52:19.385406455-07:00",
|
||||
"message": {
|
||||
"role": "assistant",
|
||||
|
|
@ -476,7 +476,7 @@ Final response:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"created_at": "2023-08-04T19:22:45.499127Z",
|
||||
"done": true,
|
||||
"total_duration": 4883583458,
|
||||
|
|
@ -494,7 +494,7 @@ Final response:
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/chat -d '{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
|
|
@ -509,7 +509,7 @@ curl http://localhost:11434/api/chat -d '{
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "registry.ollama.ai/library/llama3:latest",
|
||||
"model": "llama3.1",
|
||||
"created_at": "2023-12-12T14:13:43.416799Z",
|
||||
"message": {
|
||||
"role": "assistant",
|
||||
|
|
@ -533,7 +533,7 @@ Send a chat message with a conversation history. You can use this same approach
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/chat -d '{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
|
|
@ -557,7 +557,7 @@ A stream of JSON objects is returned:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"created_at": "2023-08-04T08:52:19.385406455-07:00",
|
||||
"message": {
|
||||
"role": "assistant",
|
||||
|
|
@ -571,7 +571,7 @@ Final response:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"created_at": "2023-08-04T19:22:45.499127Z",
|
||||
"done": true,
|
||||
"total_duration": 8113331500,
|
||||
|
|
@ -629,7 +629,7 @@ curl http://localhost:11434/api/chat -d '{
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/chat -d '{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
|
|
@ -647,7 +647,7 @@ curl http://localhost:11434/api/chat -d '{
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "registry.ollama.ai/library/llama3:latest",
|
||||
"model": "llama3.1",
|
||||
"created_at": "2023-12-12T14:13:43.416799Z",
|
||||
"message": {
|
||||
"role": "assistant",
|
||||
|
|
@ -904,7 +904,7 @@ Show information about a model including details, modelfile, template, parameter
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/show -d '{
|
||||
"name": "llama3"
|
||||
"name": "llama3.1"
|
||||
}'
|
||||
```
|
||||
|
||||
|
|
@ -965,7 +965,7 @@ Copy a model. Creates a model with another name from an existing model.
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/copy -d '{
|
||||
"source": "llama3",
|
||||
"source": "llama3.1",
|
||||
"destination": "llama3-backup"
|
||||
}'
|
||||
```
|
||||
|
|
@ -1020,7 +1020,7 @@ Download a model from the ollama library. Cancelled pulls are resumed from where
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/pull -d '{
|
||||
"name": "llama3"
|
||||
"name": "llama3.1"
|
||||
}'
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -32,7 +32,7 @@ When using the API, specify the `num_ctx` parameter:
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/generate -d '{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"prompt": "Why is the sky blue?",
|
||||
"options": {
|
||||
"num_ctx": 4096
|
||||
|
|
@ -247,12 +247,12 @@ The `keep_alive` parameter can be set to:
|
|||
|
||||
For example, to preload a model and leave it in memory use:
|
||||
```shell
|
||||
curl http://localhost:11434/api/generate -d '{"model": "llama3", "keep_alive": -1}'
|
||||
curl http://localhost:11434/api/generate -d '{"model": "llama3.1", "keep_alive": -1}'
|
||||
```
|
||||
|
||||
To unload the model and free up memory use:
|
||||
```shell
|
||||
curl http://localhost:11434/api/generate -d '{"model": "llama3", "keep_alive": 0}'
|
||||
curl http://localhost:11434/api/generate -d '{"model": "llama3.1", "keep_alive": 0}'
|
||||
```
|
||||
|
||||
Alternatively, you can change the amount of time all models are loaded into memory by setting the `OLLAMA_KEEP_ALIVE` environment variable when starting the Ollama server. The `OLLAMA_KEEP_ALIVE` variable uses the same parameter types as the `keep_alive` parameter types mentioned above. Refer to section explaining [how to configure the Ollama server](#how-do-i-configure-ollama-server) to correctly set the environment variable.
|
||||
|
|
|
|||
|
|
@ -11,7 +11,7 @@ A model file is the blueprint to create and share models with Ollama.
|
|||
- [Examples](#examples)
|
||||
- [Instructions](#instructions)
|
||||
- [FROM (Required)](#from-required)
|
||||
- [Build from llama3.1](#build-from-llama31)
|
||||
- [Build from existing model](#build-from-existing-model)
|
||||
- [Build from a Safetensors model](#build-from-a-safetensors-model)
|
||||
- [Build from a GGUF file](#build-from-a-gguf-file)
|
||||
- [PARAMETER](#parameter)
|
||||
|
|
@ -50,7 +50,7 @@ INSTRUCTION arguments
|
|||
An example of a `Modelfile` creating a mario blueprint:
|
||||
|
||||
```modelfile
|
||||
FROM llama3
|
||||
FROM llama3.1
|
||||
# sets the temperature to 1 [higher is more creative, lower is more coherent]
|
||||
PARAMETER temperature 1
|
||||
# sets the context window size to 4096, this controls how many tokens the LLM can use as context to generate the next token
|
||||
|
|
@ -72,10 +72,10 @@ More examples are available in the [examples directory](../examples).
|
|||
To view the Modelfile of a given model, use the `ollama show --modelfile` command.
|
||||
|
||||
```bash
|
||||
> ollama show --modelfile llama3
|
||||
> ollama show --modelfile llama3.1
|
||||
# Modelfile generated by "ollama show"
|
||||
# To build a new Modelfile based on this one, replace the FROM line with:
|
||||
# FROM llama3:latest
|
||||
# FROM llama3.1:latest
|
||||
FROM /Users/pdevine/.ollama/models/blobs/sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29
|
||||
TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>
|
||||
|
||||
|
|
@ -100,7 +100,7 @@ The `FROM` instruction defines the base model to use when creating a model.
|
|||
FROM <model name>:<tag>
|
||||
```
|
||||
|
||||
#### Build from llama3.1
|
||||
#### Build from existing model
|
||||
|
||||
```modelfile
|
||||
FROM llama3.1
|
||||
|
|
|
|||
|
|
@ -25,7 +25,7 @@ chat_completion = client.chat.completions.create(
|
|||
'content': 'Say this is a test',
|
||||
}
|
||||
],
|
||||
model='llama3',
|
||||
model='llama3.1',
|
||||
)
|
||||
|
||||
response = client.chat.completions.create(
|
||||
|
|
@ -46,13 +46,13 @@ response = client.chat.completions.create(
|
|||
)
|
||||
|
||||
completion = client.completions.create(
|
||||
model="llama3",
|
||||
model="llama3.1",
|
||||
prompt="Say this is a test",
|
||||
)
|
||||
|
||||
list_completion = client.models.list()
|
||||
|
||||
model = client.models.retrieve("llama3")
|
||||
model = client.models.retrieve("llama3.1")
|
||||
|
||||
embeddings = client.embeddings.create(
|
||||
model="all-minilm",
|
||||
|
|
@ -74,7 +74,7 @@ const openai = new OpenAI({
|
|||
|
||||
const chatCompletion = await openai.chat.completions.create({
|
||||
messages: [{ role: 'user', content: 'Say this is a test' }],
|
||||
model: 'llama3',
|
||||
model: 'llama3.1',
|
||||
})
|
||||
|
||||
const response = await openai.chat.completions.create({
|
||||
|
|
@ -94,13 +94,13 @@ const response = await openai.chat.completions.create({
|
|||
})
|
||||
|
||||
const completion = await openai.completions.create({
|
||||
model: "llama3",
|
||||
model: "llama3.1",
|
||||
prompt: "Say this is a test.",
|
||||
})
|
||||
|
||||
const listCompletion = await openai.models.list()
|
||||
|
||||
const model = await openai.models.retrieve("llama3")
|
||||
const model = await openai.models.retrieve("llama3.1")
|
||||
|
||||
const embedding = await openai.embeddings.create({
|
||||
model: "all-minilm",
|
||||
|
|
@ -114,7 +114,7 @@ const embedding = await openai.embeddings.create({
|
|||
curl http://localhost:11434/v1/chat/completions \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"messages": [
|
||||
{
|
||||
"role": "system",
|
||||
|
|
@ -154,13 +154,13 @@ curl http://localhost:11434/v1/chat/completions \
|
|||
curl http://localhost:11434/v1/completions \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"model": "llama3",
|
||||
"model": "llama3.1",
|
||||
"prompt": "Say this is a test"
|
||||
}'
|
||||
|
||||
curl http://localhost:11434/v1/models
|
||||
|
||||
curl http://localhost:11434/v1/models/llama3
|
||||
curl http://localhost:11434/v1/models/llama3.1
|
||||
|
||||
curl http://localhost:11434/v1/embeddings \
|
||||
-H "Content-Type: application/json" \
|
||||
|
|
@ -274,7 +274,7 @@ curl http://localhost:11434/v1/embeddings \
|
|||
Before using a model, pull it locally `ollama pull`:
|
||||
|
||||
```shell
|
||||
ollama pull llama3
|
||||
ollama pull llama3.1
|
||||
```
|
||||
|
||||
### Default model names
|
||||
|
|
@ -282,7 +282,7 @@ ollama pull llama3
|
|||
For tooling that relies on default OpenAI model names such as `gpt-3.5-turbo`, use `ollama cp` to copy an existing model name to a temporary name:
|
||||
|
||||
```
|
||||
ollama cp llama3 gpt-3.5-turbo
|
||||
ollama cp llama3.1 gpt-3.5-turbo
|
||||
```
|
||||
|
||||
Afterwards, this new model name can be specified the `model` field:
|
||||
|
|
|
|||
|
|
@ -33,7 +33,7 @@ Omitting a template in these models puts the responsibility of correctly templat
|
|||
To add templates in your model, you'll need to add a `TEMPLATE` command to the Modelfile. Here's an example using Meta's Llama 3.
|
||||
|
||||
```dockerfile
|
||||
FROM llama3
|
||||
FROM llama3.1
|
||||
|
||||
TEMPLATE """{{- if .System }}<|start_header_id|>system<|end_header_id|>
|
||||
|
||||
|
|
|
|||
|
|
@ -29,7 +29,7 @@ Ollama uses unicode characters for progress indication, which may render as unkn
|
|||
|
||||
Here's a quick example showing API access from `powershell`
|
||||
```powershell
|
||||
(Invoke-WebRequest -method POST -Body '{"model":"llama3", "prompt":"Why is the sky blue?", "stream": false}' -uri http://localhost:11434/api/generate ).Content | ConvertFrom-json
|
||||
(Invoke-WebRequest -method POST -Body '{"model":"llama3.1", "prompt":"Why is the sky blue?", "stream": false}' -uri http://localhost:11434/api/generate ).Content | ConvertFrom-json
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
|
|
|||
Loading…
Reference in a new issue