Update 'llama2' -> 'llama3' in most places (#4116)
* Update 'llama2' -> 'llama3' in most places --------- Co-authored-by: Patrick Devine <patrick@infrahq.com>
This commit is contained in:
Dr Nic Williams
GitHub
parent
267e25a750
commit
e8aaea030e
21 changed files with 94 additions and 102 deletions
58
docs/api.md
58
docs/api.md
|
|
@ -17,7 +17,7 @@
|
|||
|
||||
### Model names
|
||||
|
||||
Model names follow a `model:tag` format, where `model` can have an optional namespace such as `example/model`. Some examples are `orca-mini:3b-q4_1` and `llama2:70b`. The tag is optional and, if not provided, will default to `latest`. The tag is used to identify a specific version.
|
||||
Model names follow a `model:tag` format, where `model` can have an optional namespace such as `example/model`. Some examples are `orca-mini:3b-q4_1` and `llama3:70b`. The tag is optional and, if not provided, will default to `latest`. The tag is used to identify a specific version.
|
||||
|
||||
### Durations
|
||||
|
||||
|
|
@ -66,7 +66,7 @@ Enable JSON mode by setting the `format` parameter to `json`. This will structur
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/generate -d '{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"prompt": "Why is the sky blue?"
|
||||
}'
|
||||
```
|
||||
|
|
@ -77,7 +77,7 @@ A stream of JSON objects is returned:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"created_at": "2023-08-04T08:52:19.385406455-07:00",
|
||||
"response": "The",
|
||||
"done": false
|
||||
|
|
@ -99,7 +99,7 @@ To calculate how fast the response is generated in tokens per second (token/s),
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"created_at": "2023-08-04T19:22:45.499127Z",
|
||||
"response": "",
|
||||
"done": true,
|
||||
|
|
@ -121,7 +121,7 @@ A response can be received in one reply when streaming is off.
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/generate -d '{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"prompt": "Why is the sky blue?",
|
||||
"stream": false
|
||||
}'
|
||||
|
|
@ -133,7 +133,7 @@ If `stream` is set to `false`, the response will be a single JSON object:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"created_at": "2023-08-04T19:22:45.499127Z",
|
||||
"response": "The sky is blue because it is the color of the sky.",
|
||||
"done": true,
|
||||
|
|
@ -155,7 +155,7 @@ If `stream` is set to `false`, the response will be a single JSON object:
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/generate -d '{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"prompt": "What color is the sky at different times of the day? Respond using JSON",
|
||||
"format": "json",
|
||||
"stream": false
|
||||
|
|
@ -166,7 +166,7 @@ curl http://localhost:11434/api/generate -d '{
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"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,
|
||||
|
|
@ -289,7 +289,7 @@ 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": "llama2",
|
||||
"model": "llama3",
|
||||
"prompt": "Why is the sky blue?",
|
||||
"stream": false,
|
||||
"options": {
|
||||
|
|
@ -332,7 +332,7 @@ curl http://localhost:11434/api/generate -d '{
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"created_at": "2023-08-04T19:22:45.499127Z",
|
||||
"response": "The sky is blue because it is the color of the sky.",
|
||||
"done": true,
|
||||
|
|
@ -354,7 +354,7 @@ If an empty prompt is provided, the model will be loaded into memory.
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/generate -d '{
|
||||
"model": "llama2"
|
||||
"model": "llama3"
|
||||
}'
|
||||
```
|
||||
|
||||
|
|
@ -364,7 +364,7 @@ A single JSON object is returned:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"created_at": "2023-12-18T19:52:07.071755Z",
|
||||
"response": "",
|
||||
"done": true
|
||||
|
|
@ -407,7 +407,7 @@ Send a chat message with a streaming response.
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/chat -d '{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
|
|
@ -423,7 +423,7 @@ A stream of JSON objects is returned:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"created_at": "2023-08-04T08:52:19.385406455-07:00",
|
||||
"message": {
|
||||
"role": "assistant",
|
||||
|
|
@ -438,7 +438,7 @@ Final response:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"created_at": "2023-08-04T19:22:45.499127Z",
|
||||
"done": true,
|
||||
"total_duration": 4883583458,
|
||||
|
|
@ -456,7 +456,7 @@ Final response:
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/chat -d '{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
|
|
@ -471,7 +471,7 @@ curl http://localhost:11434/api/chat -d '{
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "registry.ollama.ai/library/llama2:latest",
|
||||
"model": "registry.ollama.ai/library/llama3:latest",
|
||||
"created_at": "2023-12-12T14:13:43.416799Z",
|
||||
"message": {
|
||||
"role": "assistant",
|
||||
|
|
@ -495,7 +495,7 @@ Send a chat message with a conversation history. You can use this same approach
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/chat -d '{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
|
|
@ -519,7 +519,7 @@ A stream of JSON objects is returned:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"created_at": "2023-08-04T08:52:19.385406455-07:00",
|
||||
"message": {
|
||||
"role": "assistant",
|
||||
|
|
@ -533,7 +533,7 @@ Final response:
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"created_at": "2023-08-04T19:22:45.499127Z",
|
||||
"done": true,
|
||||
"total_duration": 8113331500,
|
||||
|
|
@ -591,7 +591,7 @@ curl http://localhost:11434/api/chat -d '{
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/chat -d '{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"messages": [
|
||||
{
|
||||
"role": "user",
|
||||
|
|
@ -609,7 +609,7 @@ curl http://localhost:11434/api/chat -d '{
|
|||
|
||||
```json
|
||||
{
|
||||
"model": "registry.ollama.ai/library/llama2:latest",
|
||||
"model": "registry.ollama.ai/library/llama3:latest",
|
||||
"created_at": "2023-12-12T14:13:43.416799Z",
|
||||
"message": {
|
||||
"role": "assistant",
|
||||
|
|
@ -651,7 +651,7 @@ Create a new model from a `Modelfile`.
|
|||
```shell
|
||||
curl http://localhost:11434/api/create -d '{
|
||||
"name": "mario",
|
||||
"modelfile": "FROM llama2\nSYSTEM You are mario from Super Mario Bros."
|
||||
"modelfile": "FROM llama3\nSYSTEM You are mario from Super Mario Bros."
|
||||
}'
|
||||
```
|
||||
|
||||
|
|
@ -758,7 +758,7 @@ A single JSON object will be returned.
|
|||
}
|
||||
},
|
||||
{
|
||||
"name": "llama2:latest",
|
||||
"name": "llama3:latest",
|
||||
"modified_at": "2023-12-07T09:32:18.757212583-08:00",
|
||||
"size": 3825819519,
|
||||
"digest": "fe938a131f40e6f6d40083c9f0f430a515233eb2edaa6d72eb85c50d64f2300e",
|
||||
|
|
@ -792,7 +792,7 @@ Show information about a model including details, modelfile, template, parameter
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/show -d '{
|
||||
"name": "llama2"
|
||||
"name": "llama3"
|
||||
}'
|
||||
```
|
||||
|
||||
|
|
@ -827,8 +827,8 @@ Copy a model. Creates a model with another name from an existing model.
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/copy -d '{
|
||||
"source": "llama2",
|
||||
"destination": "llama2-backup"
|
||||
"source": "llama3",
|
||||
"destination": "llama3-backup"
|
||||
}'
|
||||
```
|
||||
|
||||
|
|
@ -854,7 +854,7 @@ Delete a model and its data.
|
|||
|
||||
```shell
|
||||
curl -X DELETE http://localhost:11434/api/delete -d '{
|
||||
"name": "llama2:13b"
|
||||
"name": "llama3:13b"
|
||||
}'
|
||||
```
|
||||
|
||||
|
|
@ -882,7 +882,7 @@ Download a model from the ollama library. Cancelled pulls are resumed from where
|
|||
|
||||
```shell
|
||||
curl http://localhost:11434/api/pull -d '{
|
||||
"name": "llama2"
|
||||
"name": "llama3"
|
||||
}'
|
||||
```
|
||||
|
||||
|
|
|
|||
|
|
@ -32,7 +32,7 @@ When using the API, specify the `num_ctx` parameter:
|
|||
|
||||
```
|
||||
curl http://localhost:11434/api/generate -d '{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"prompt": "Why is the sky blue?",
|
||||
"options": {
|
||||
"num_ctx": 4096
|
||||
|
|
@ -221,12 +221,12 @@ 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": "llama2", "keep_alive": -1}'
|
||||
curl http://localhost:11434/api/generate -d '{"model": "llama3", "keep_alive": -1}'
|
||||
```
|
||||
|
||||
To unload the model and free up memory use:
|
||||
```shell
|
||||
curl http://localhost:11434/api/generate -d '{"model": "llama2", "keep_alive": 0}'
|
||||
curl http://localhost:11434/api/generate -d '{"model": "llama3", "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.
|
||||
|
|
|
|||
|
|
@ -10,7 +10,7 @@ A model file is the blueprint to create and share models with Ollama.
|
|||
- [Examples](#examples)
|
||||
- [Instructions](#instructions)
|
||||
- [FROM (Required)](#from-required)
|
||||
- [Build from llama2](#build-from-llama2)
|
||||
- [Build from llama3](#build-from-llama3)
|
||||
- [Build from a bin file](#build-from-a-bin-file)
|
||||
- [PARAMETER](#parameter)
|
||||
- [Valid Parameters and Values](#valid-parameters-and-values)
|
||||
|
|
@ -48,7 +48,7 @@ INSTRUCTION arguments
|
|||
An example of a `Modelfile` creating a mario blueprint:
|
||||
|
||||
```modelfile
|
||||
FROM llama2
|
||||
FROM llama3
|
||||
# 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
|
||||
|
|
@ -67,33 +67,25 @@ To use this:
|
|||
|
||||
More examples are available in the [examples directory](../examples).
|
||||
|
||||
### `Modelfile`s in [ollama.com/library][1]
|
||||
|
||||
There are two ways to view `Modelfile`s underlying the models in [ollama.com/library][1]:
|
||||
|
||||
- Option 1: view a details page from a model's tags page:
|
||||
1. Go to a particular model's tags (e.g. https://ollama.com/library/llama2/tags)
|
||||
2. Click on a tag (e.g. https://ollama.com/library/llama2:13b)
|
||||
3. Scroll down to "Layers"
|
||||
- Note: if the [`FROM` instruction](#from-required) is not present,
|
||||
it means the model was created from a local file
|
||||
- Option 2: use `ollama show` to print the `Modelfile` for any local models like so:
|
||||
To view the Modelfile of a given model, use the `ollama show --modelfile` command.
|
||||
|
||||
```bash
|
||||
> ollama show --modelfile llama2:13b
|
||||
> ollama show --modelfile llama3
|
||||
# Modelfile generated by "ollama show"
|
||||
# To build a new Modelfile based on this one, replace the FROM line with:
|
||||
# FROM llama2:13b
|
||||
# FROM llama3:latest
|
||||
FROM /Users/pdevine/.ollama/models/blobs/sha256-00e1317cbf74d901080d7100f57580ba8dd8de57203072dc6f668324ba545f29
|
||||
TEMPLATE """{{ if .System }}<|start_header_id|>system<|end_header_id|>
|
||||
|
||||
FROM /root/.ollama/models/blobs/sha256:123abc
|
||||
TEMPLATE """[INST] {{ if .System }}<<SYS>>{{ .System }}<</SYS>>
|
||||
{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
|
||||
|
||||
{{ end }}{{ .Prompt }} [/INST] """
|
||||
SYSTEM """"""
|
||||
PARAMETER stop [INST]
|
||||
PARAMETER stop [/INST]
|
||||
PARAMETER stop <<SYS>>
|
||||
PARAMETER stop <</SYS>>
|
||||
{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
|
||||
|
||||
{{ .Response }}<|eot_id|>"""
|
||||
PARAMETER stop "<|start_header_id|>"
|
||||
PARAMETER stop "<|end_header_id|>"
|
||||
PARAMETER stop "<|eot_id|>"
|
||||
PARAMETER stop "<|reserved_special_token"
|
||||
```
|
||||
|
||||
## Instructions
|
||||
|
|
@ -106,10 +98,10 @@ The `FROM` instruction defines the base model to use when creating a model.
|
|||
FROM <model name>:<tag>
|
||||
```
|
||||
|
||||
#### Build from llama2
|
||||
#### Build from llama3
|
||||
|
||||
```modelfile
|
||||
FROM llama2
|
||||
FROM llama3
|
||||
```
|
||||
|
||||
A list of available base models:
|
||||
|
|
|
|||
|
|
@ -25,7 +25,7 @@ chat_completion = client.chat.completions.create(
|
|||
'content': 'Say this is a test',
|
||||
}
|
||||
],
|
||||
model='llama2',
|
||||
model='llama3',
|
||||
)
|
||||
```
|
||||
|
||||
|
|
@ -43,7 +43,7 @@ const openai = new OpenAI({
|
|||
|
||||
const chatCompletion = await openai.chat.completions.create({
|
||||
messages: [{ role: 'user', content: 'Say this is a test' }],
|
||||
model: 'llama2',
|
||||
model: 'llama3',
|
||||
})
|
||||
```
|
||||
|
||||
|
|
@ -53,7 +53,7 @@ const chatCompletion = await openai.chat.completions.create({
|
|||
curl http://localhost:11434/v1/chat/completions \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{
|
||||
"model": "llama2",
|
||||
"model": "llama3",
|
||||
"messages": [
|
||||
{
|
||||
"role": "system",
|
||||
|
|
@ -113,7 +113,7 @@ curl http://localhost:11434/v1/chat/completions \
|
|||
Before using a model, pull it locally `ollama pull`:
|
||||
|
||||
```shell
|
||||
ollama pull llama2
|
||||
ollama pull llama3
|
||||
```
|
||||
|
||||
### Default model names
|
||||
|
|
@ -121,7 +121,7 @@ ollama pull llama2
|
|||
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 llama2 gpt-3.5-turbo
|
||||
ollama cp llama3 gpt-3.5-turbo
|
||||
```
|
||||
|
||||
Afterwards, this new model name can be specified the `model` field:
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@ import { Ollama } from "langchain/llms/ollama";
|
|||
|
||||
const ollama = new Ollama({
|
||||
baseUrl: "http://localhost:11434",
|
||||
model: "llama2",
|
||||
model: "llama3",
|
||||
});
|
||||
|
||||
const answer = await ollama.invoke(`why is the sky blue?`);
|
||||
|
|
@ -23,7 +23,7 @@ const answer = await ollama.invoke(`why is the sky blue?`);
|
|||
console.log(answer);
|
||||
```
|
||||
|
||||
That will get us the same thing as if we ran `ollama run llama2 "why is the sky blue"` in the terminal. But we want to load a document from the web to ask a question against. **Cheerio** is a great library for ingesting a webpage, and **LangChain** uses it in their **CheerioWebBaseLoader**. So let's install **Cheerio** and build that part of the app.
|
||||
That will get us the same thing as if we ran `ollama run llama3 "why is the sky blue"` in the terminal. But we want to load a document from the web to ask a question against. **Cheerio** is a great library for ingesting a webpage, and **LangChain** uses it in their **CheerioWebBaseLoader**. So let's install **Cheerio** and build that part of the app.
|
||||
|
||||
```bash
|
||||
npm install cheerio
|
||||
|
|
|
|||
|
|
@ -1,3 +1,4 @@
|
|||
<<<<<<< HEAD
|
||||
# Ollama Windows Preview
|
||||
|
||||
Welcome to the Ollama Windows preview.
|
||||
|
|
@ -27,7 +28,7 @@ Logs will often be helpful in diagnosing the problem (see
|
|||
|
||||
Here's a quick example showing API access from `powershell`
|
||||
```powershell
|
||||
(Invoke-WebRequest -method POST -Body '{"model":"llama2", "prompt":"Why is the sky blue?", "stream": false}' -uri http://localhost:11434/api/generate ).Content | ConvertFrom-json
|
||||
(Invoke-WebRequest -method POST -Body '{"model":"llama3", "prompt":"Why is the sky blue?", "stream": false}' -uri http://localhost:11434/api/generate ).Content | ConvertFrom-json
|
||||
```
|
||||
|
||||
## Troubleshooting
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
|
||||
When calling `ollama`, you can pass it a file to run all the prompts in the file, one after the other:
|
||||
|
||||
`ollama run llama2 < sourcequestions.txt`
|
||||
`ollama run llama3 < sourcequestions.txt`
|
||||
|
||||
This concept is used in the following example.
|
||||
|
||||
|
|
|
|||
|
|
@ -35,7 +35,7 @@ func main() {
|
|||
|
||||
ctx := context.Background()
|
||||
req := &api.ChatRequest{
|
||||
Model: "llama2",
|
||||
Model: "llama3",
|
||||
Messages: messages,
|
||||
}
|
||||
|
||||
|
|
|
|||
|
|
@ -51,7 +51,7 @@ while True:
|
|||
template=template,
|
||||
)
|
||||
|
||||
llm = Ollama(model="llama2:13b", callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]))
|
||||
llm = Ollama(model="llama3:8b", callback_manager=CallbackManager([StreamingStdOutCallbackHandler()]))
|
||||
qa_chain = RetrievalQA.from_chain_type(
|
||||
llm,
|
||||
retriever=vectorstore.as_retriever(),
|
||||
|
|
|
|||
|
|
@ -4,10 +4,10 @@ This example is a basic "hello world" of using LangChain with Ollama.
|
|||
|
||||
## Running the Example
|
||||
|
||||
1. Ensure you have the `llama2` model installed:
|
||||
1. Ensure you have the `llama3` model installed:
|
||||
|
||||
```bash
|
||||
ollama pull llama2
|
||||
ollama pull llama3
|
||||
```
|
||||
|
||||
2. Install the Python Requirements.
|
||||
|
|
@ -21,4 +21,3 @@ This example is a basic "hello world" of using LangChain with Ollama.
|
|||
```bash
|
||||
python main.py
|
||||
```
|
||||
|
||||
|
|
@ -1,6 +1,6 @@
|
|||
from langchain.llms import Ollama
|
||||
|
||||
input = input("What is your question?")
|
||||
llm = Ollama(model="llama2")
|
||||
llm = Ollama(model="llama3")
|
||||
res = llm.predict(input)
|
||||
print (res)
|
||||
|
|
|
|||
|
|
@ -1,4 +1,4 @@
|
|||
FROM llama2
|
||||
FROM llama3
|
||||
PARAMETER temperature 1
|
||||
SYSTEM """
|
||||
You are Mario from super mario bros, acting as an assistant.
|
||||
|
|
|
|||
|
|
@ -2,12 +2,12 @@
|
|||
|
||||
# Example character: Mario
|
||||
|
||||
This example shows how to create a basic character using Llama2 as the base model.
|
||||
This example shows how to create a basic character using Llama3 as the base model.
|
||||
|
||||
To run this example:
|
||||
|
||||
1. Download the Modelfile
|
||||
2. `ollama pull llama2` to get the base model used in the model file.
|
||||
2. `ollama pull llama3` to get the base model used in the model file.
|
||||
3. `ollama create NAME -f ./Modelfile`
|
||||
4. `ollama run NAME`
|
||||
|
||||
|
|
@ -18,7 +18,7 @@ Ask it some questions like "Who are you?" or "Is Peach in trouble again?"
|
|||
What the model file looks like:
|
||||
|
||||
```
|
||||
FROM llama2
|
||||
FROM llama3
|
||||
PARAMETER temperature 1
|
||||
SYSTEM """
|
||||
You are Mario from Super Mario Bros, acting as an assistant.
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ import requests
|
|||
import json
|
||||
import random
|
||||
|
||||
model = "llama2"
|
||||
model = "llama3"
|
||||
template = {
|
||||
"firstName": "",
|
||||
"lastName": "",
|
||||
|
|
|
|||
|
|
@ -12,7 +12,7 @@ countries = [
|
|||
"France",
|
||||
]
|
||||
country = random.choice(countries)
|
||||
model = "llama2"
|
||||
model = "llama3"
|
||||
|
||||
prompt = f"generate one realistically believable sample data set of a persons first name, last name, address in {country}, and phone number. Do not use common names. Respond using JSON. Key names should have no backslashes, values should use plain ascii with no special characters."
|
||||
|
||||
|
|
|
|||
|
|
@ -6,10 +6,10 @@ There are two python scripts in this example. `randomaddresses.py` generates ran
|
|||
|
||||
## Running the Example
|
||||
|
||||
1. Ensure you have the `llama2` model installed:
|
||||
1. Ensure you have the `llama3` model installed:
|
||||
|
||||
```bash
|
||||
ollama pull llama2
|
||||
ollama pull llama3
|
||||
```
|
||||
|
||||
2. Install the Python Requirements.
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ import json
|
|||
import requests
|
||||
|
||||
# NOTE: ollama must be running for this to work, start the ollama app or run `ollama serve`
|
||||
model = "llama2" # TODO: update this for whatever model you wish to use
|
||||
model = "llama3" # TODO: update this for whatever model you wish to use
|
||||
|
||||
|
||||
def chat(messages):
|
||||
|
|
|
|||
|
|
@ -4,10 +4,10 @@ The **chat** endpoint is one of two ways to generate text from an LLM with Ollam
|
|||
|
||||
## Running the Example
|
||||
|
||||
1. Ensure you have the `llama2` model installed:
|
||||
1. Ensure you have the `llama3` model installed:
|
||||
|
||||
```bash
|
||||
ollama pull llama2
|
||||
ollama pull llama3
|
||||
```
|
||||
|
||||
2. Install the Python Requirements.
|
||||
|
|
|
|||
|
|
@ -4,10 +4,10 @@ This example demonstrates how one would create a set of 'mentors' you can have a
|
|||
|
||||
## Usage
|
||||
|
||||
1. Add llama2 to have the mentors ask your questions:
|
||||
1. Add llama3 to have the mentors ask your questions:
|
||||
|
||||
```bash
|
||||
ollama pull llama2
|
||||
ollama pull llama3
|
||||
```
|
||||
|
||||
2. Install prerequisites:
|
||||
|
|
|
|||
|
|
@ -15,7 +15,7 @@ async function characterGenerator() {
|
|||
ollama.setModel("stablebeluga2:70b-q4_K_M");
|
||||
const bio = await ollama.generate(`create a bio of ${character} in a single long paragraph. Instead of saying '${character} is...' or '${character} was...' use language like 'You are...' or 'You were...'. Then create a paragraph describing the speaking mannerisms and style of ${character}. Don't include anything about how ${character} looked or what they sounded like, just focus on the words they said. Instead of saying '${character} would say...' use language like 'You should say...'. If you use quotes, always use single quotes instead of double quotes. If there are any specific words or phrases you used a lot, show how you used them. `);
|
||||
|
||||
const thecontents = `FROM llama2\nSYSTEM """\n${bio.response.replace(/(\r\n|\n|\r)/gm, " ").replace('would', 'should')} All answers to questions should be related back to what you are most known for.\n"""`;
|
||||
const thecontents = `FROM llama3\nSYSTEM """\n${bio.response.replace(/(\r\n|\n|\r)/gm, " ").replace('would', 'should')} All answers to questions should be related back to what you are most known for.\n"""`;
|
||||
|
||||
fs.writeFile(path.join(directory, 'Modelfile'), thecontents, (err: any) => {
|
||||
if (err) throw err;
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
import * as readline from "readline";
|
||||
|
||||
const model = "llama2";
|
||||
const model = "llama3";
|
||||
type Message = {
|
||||
role: "assistant" | "user" | "system";
|
||||
content: string;
|
||||
|
|
|
|||
Loading…
Reference in a new issue