Merge remote-tracking branch 'upstream/main' into pr3702

convert/mistral.go

@@ -132,7 +132,7 @@ func (m *MistralModel) LoadVocab() error {
 	return nil
 }
 
-func (m *MistralModel) WriteGGUF() (string, error) {
+func (m *MistralModel) WriteGGUF(ws io.WriteSeeker) error {
 	kv := llm.KV{
 		"general.architecture":                   "llama",
 		"general.name":                           m.Name,
@@ -158,16 +158,5 @@ func (m *MistralModel) WriteGGUF() (string, error) {
 		"tokenizer.ggml.unknown_token_id": uint32(0),
 	}
 
-	f, err := os.CreateTemp("", "ollama-gguf")
-	if err != nil {
-		return "", err
-	}
-	defer f.Close()
-
-	mod := llm.NewGGUFV3(m.Params.ByteOrder)
-	if err := mod.Encode(f, kv, m.Tensors); err != nil {
-		return "", err
-	}
-
-	return f.Name(), nil
+	return llm.NewGGUFV3(m.Params.ByteOrder).Encode(ws, kv, m.Tensors)
 }

convert/mixtral.go

+package convert
+
+import (
+	"io"
+	"regexp"
+
+	"github.com/ollama/ollama/llm"
+)
+
+type MixtralModel struct {
+	ModelData
+}
+
+func (m *MixtralModel) GetTensors() error {
+	t, err := m.Format.GetTensors(m.Path, m.Params)
+	if err != nil {
+		return err
+	}
+
+	m.Tensors = []llm.Tensor{}
+
+	pattern := `^blk\.[0-9]+\.attn_(?P<layer>q|k)\.weight$`
+	re, err := regexp.Compile(pattern)
+	if err != nil {
+		return err
+	}
+
+	for _, l := range t {
+		matches := re.FindAllStringSubmatch(l.Name, -1)
+		if len(matches) > 0 {
+			wt := l.WriterTo.(safetensorWriterTo)
+			wt.handler = mistralLayerHandler
+			l.WriterTo = wt
+		}
+		m.Tensors = append(m.Tensors, l)
+	}
+
+	return nil
+}
+
+func (m *MixtralModel) LoadVocab() error {
+	v, err := LoadSentencePieceTokens(m.Path, m.Params)
+	if err != nil {
+		return err
+	}
+	m.Vocab = v
+	return nil
+}
+
+func (m *MixtralModel) WriteGGUF(ws io.WriteSeeker) error {
+	kv := llm.KV{
+		"general.architecture":          "llama",
+		"general.name":                  m.Name,
+		"llama.block_count":             uint32(m.Params.HiddenLayers),
+		"llama.context_length":          uint32(m.Params.ContextSize),
+		"llama.embedding_length":        uint32(m.Params.HiddenSize),
+		"llama.feed_forward_length":     uint32(m.Params.IntermediateSize),
+		"llama.attention.head_count":    uint32(m.Params.AttentionHeads),
+		"llama.attention.head_count_kv": uint32(m.Params.KeyValHeads),
+
+		"llama.rope.freq_base":                   float32(m.Params.RopeFrequencyBase),
+		"llama.attention.layer_norm_rms_epsilon": float32(m.Params.NormEPS),
+
+		"llama.expert_count":      uint32(m.Params.Experts),
+		"llama.expert_used_count": uint32(m.Params.ExpertsUsed),
+
+		"llama.vocab_size":           uint32(len(m.Vocab.Tokens)),
+		"llama.rope.dimension_count": uint32(m.Params.HiddenSize / m.Params.AttentionHeads),
+
+		"general.file_type":    uint32(1),
+		"tokenizer.ggml.model": "llama",
+
+		"tokenizer.ggml.tokens":     m.Vocab.Tokens,
+		"tokenizer.ggml.scores":     m.Vocab.Scores,
+		"tokenizer.ggml.token_type": m.Vocab.Types,
+
+		"tokenizer.ggml.bos_token_id":     uint32(m.Params.BoSTokenID),
+		"tokenizer.ggml.eos_token_id":     uint32(m.Params.EoSTokenID),
+		"tokenizer.ggml.unknown_token_id": uint32(0),
+		"tokenizer.ggml.add_bos_token":    true,
+		"tokenizer.ggml.add_eos_token":    false,
+	}
+
+	return llm.NewGGUFV3(m.Params.ByteOrder).Encode(ws, kv, m.Tensors)
+}

convert/safetensors.go

@@ -53,7 +53,7 @@ func (m *SafetensorFormat) GetTensors(dirpath string, params *Params) ([]llm.Ten
 		var err error
 		t, offset, err = m.readTensors(f, offset, params)
 		if err != nil {
-			slog.Error("%v", err)
+			slog.Error(err.Error())
 			return nil, err
 		}
 		tensors = append(tensors, t...)
@@ -93,7 +93,6 @@ func (m *SafetensorFormat) readTensors(fn string, offset uint64, params *Params)
 	}
 
 	slices.Sort(keys)
-
 	slog.Info("converting layers")
 
 	var tensors []llm.Tensor
@@ -105,7 +104,6 @@ func (m *SafetensorFormat) readTensors(fn string, offset uint64, params *Params)
 			return nil, 0, err
 		}
 
-		slog.Debug(fmt.Sprintf("metadata = %#v", data))
 		var size uint64
 		var kind uint32
 		switch len(data.Shape) {
@@ -124,7 +122,7 @@ func (m *SafetensorFormat) readTensors(fn string, offset uint64, params *Params)
 
 		ggufName, err := m.GetLayerName(k)
 		if err != nil {
-			slog.Error("%v", err)
+			slog.Error(err.Error())
 			return nil, 0, err
 		}
 
@@ -150,11 +148,13 @@ func (m *SafetensorFormat) readTensors(fn string, offset uint64, params *Params)
 			padding:  8 + jsonSize,
 		}
 
-		tensors = append(tensors, t)
 		offset += size
+		tensors = append(tensors, t)
 	}
+
 	slog.Debug(fmt.Sprintf("total tensors for file = %d", len(tensors)))
 	slog.Debug(fmt.Sprintf("offset = %d", offset))
+
 	return tensors, offset, nil
 }
 
@@ -194,6 +194,10 @@ func (m *SafetensorFormat) GetLayerName(n string) (string, error) {
 		"model.layers.(\\d+).self_attn.o_proj.weight":                   "blk.$1.attn_output.weight",
 		"model.layers.(\\d+).self_attn.q_proj.weight":                   "blk.$1.attn_q.weight",
 		"model.layers.(\\d+).self_attn.v_proj.weight":                   "blk.$1.attn_v.weight",
+		"model.layers.(\\d+).block_sparse_moe.gate.weight":              "blk.$1.ffn_gate_inp.weight",
+		"model.layers.(\\d+).block_sparse_moe.experts.(\\d+).w1.weight": "blk.$1.ffn_gate.$2.weight",
+		"model.layers.(\\d+).block_sparse_moe.experts.(\\d+).w2.weight": "blk.$1.ffn_down.$2.weight",
+		"model.layers.(\\d+).block_sparse_moe.experts.(\\d+).w3.weight": "blk.$1.ffn_up.$2.weight",
 	}
 
 	v, ok := directMap[n]
@@ -286,6 +290,15 @@ func (m *SafetensorFormat) GetModelArch(name, dirPath string, params *Params) (M
 					Format: m,
 				},
 			}, nil
+		case "MixtralForCausalLM":
+			return &MixtralModel{
+				ModelData{
+					Name:   name,
+					Path:   dirPath,
+					Params: params,
+					Format: m,
+				},
+			}, nil
 		case "GemmaForCausalLM":
 			return &GemmaModel{
 				ModelData{

convert/torch.go

@@ -74,7 +74,7 @@ func (tf *TorchFormat) GetTensors(dirpath string, params *Params) ([]llm.Tensor,
 
 			ggufName, err := tf.GetLayerName(k.(string))
 			if err != nil {
-				slog.Error("%v", err)
+				slog.Error(err.Error())
 				return nil, err
 			}
 			slog.Debug(fmt.Sprintf("finding name for '%s' -> '%s'", k.(string), ggufName))

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
@@ -90,16 +90,16 @@ The final response in the stream also includes additional data about the generat
 - `load_duration`: time spent in nanoseconds loading the model
 - `prompt_eval_count`: number of tokens in the prompt
 - `prompt_eval_duration`: time spent in nanoseconds evaluating the prompt
-- `eval_count`: number of tokens the response
+- `eval_count`: number of tokens in the response
 - `eval_duration`: time in nanoseconds spent generating the response
 - `context`: an encoding of the conversation used in this response, this can be sent in the next request to keep a conversational memory
 - `response`: empty if the response was streamed, if not streamed, this will contain the full response
 
-To calculate how fast the response is generated in tokens per second (token/s), divide `eval_count` / `eval_duration`.
+To calculate how fast the response is generated in tokens per second (token/s), divide `eval_count` / `eval_duration` * `10^9`.
 
 ```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"
 }'
 ```
 

docs/development.md

@@ -51,7 +51,7 @@ Typically the build scripts will auto-detect CUDA, however, if your Linux distro
 or installation approach uses unusual paths, you can specify the location by
 specifying an environment variable `CUDA_LIB_DIR` to the location of the shared
 libraries, and `CUDACXX` to the location of the nvcc compiler. You can customize
-set set of target CUDA architectues by setting `CMAKE_CUDA_ARCHITECTURES` (e.g. "50;60;70")
+a set of target CUDA architectures by setting `CMAKE_CUDA_ARCHITECTURES` (e.g. "50;60;70")
 
 Then generate dependencies:
 

docs/faq.md

@@ -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
@@ -140,7 +140,7 @@ Refer to the section [above](#how-do-i-configure-ollama-server) for how to set e
 
 - macOS: `~/.ollama/models`
 - Linux: `/usr/share/ollama/.ollama/models`
-- Windows: `C:\Users\<username>\.ollama\models`
+- Windows: `C:\Users\%username%\.ollama\models`
 
 ### How do I set them to a different location?
 
@@ -221,10 +221,20 @@ 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.
+
+If you wish to override the `OLLAMA_KEEP_ALIVE` setting, use the `keep_alive` API parameter with the `/api/generate` or `/api/chat` API endpoints.
+
+## How do I manage the maximum number of requests the server can queue
+
+If too many requests are sent to the server, it will respond with a 503 error
+indicating the server is overloaded.  You can adjust how many requests may be
+queue by setting `OLLAMA_MAX_QUEUE`
\ No newline at end of file

docs/import.md

@@ -125,7 +125,7 @@ Publishing models is in early alpha. If you'd like to publish your model to shar
 
 1. Create [an account](https://ollama.com/signup)
 2. Copy your Ollama public key:
-  - macOS: `cat ~/.ollama/id_ed25519.pub`
+  - macOS: `cat ~/.ollama/id_ed25519.pub | pbcopy`
   - Windows: `type %USERPROFILE%\.ollama\id_ed25519.pub`
   - Linux: `cat /usr/share/ollama/.ollama/id_ed25519.pub`
 3. Add your public key to your [Ollama account](https://ollama.com/settings/keys)
@@ -136,6 +136,8 @@ Next, copy your model to your username's namespace:
 ollama cp example <your username>/example
 ```
 
+> Note: model names may only contain lowercase letters, digits, and the characters `.`, `-`, and `_`.
+
 Then push the model:
 
 ```

docs/linux.md

@@ -105,7 +105,7 @@ sudo chmod +x /usr/bin/ollama
 To view logs of Ollama running as a startup service, run:
 
 ```bash
-journalctl -u ollama
+journalctl -e -u ollama
 ```
 
 ## Uninstall

docs/modelfile.md

@@ -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|>
+
+  {{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|>
 
-  FROM /root/.ollama/models/blobs/sha256:123abc
-  TEMPLATE """[INST] {{ if .System }}<<SYS>>{{ .System }}<</SYS>>
+  {{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|>
 
-  {{ end }}{{ .Prompt }} [/INST] """
-  SYSTEM """"""
-  PARAMETER stop [INST]
-  PARAMETER stop [/INST]
-  PARAMETER stop <<SYS>>
-  PARAMETER stop <</SYS>>
+  {{ .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:

docs/openai.md

@@ -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:

docs/tutorials/langchainjs.md

@@ -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

docs/tutorials/langchainpy.md

@@ -12,15 +12,17 @@ So let's figure out how we can use **LangChain** with Ollama to ask our question
 
 Let's start by asking a simple question that we can get an answer to from the **Llama2** model using **Ollama**. First, we need to install the **LangChain** package:
 
-`pip install langchain`
+`pip install langchain_community`
 
 Then we can create a model and ask the question:
 
 ```python
-from langchain.llms import Ollama
-ollama = Ollama(base_url='http://localhost:11434',
-model="llama2")
-print(ollama("why is the sky blue"))
+from langchain_community.llms import Ollama
+ollama = Ollama(
+    base_url='http://localhost:11434',
+    model="llama3"
+)
+print(ollama.invoke("why is the sky blue"))
 ```
 
 Notice that we are defining the model and the base URL for Ollama.

docs/tutorials/nvidia-jetson.md

 # Running Ollama on NVIDIA Jetson Devices
 
-With some minor configuration, Ollama runs well on [NVIDIA Jetson Devices](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/). The following has been tested on [JetPack 5.1.2](https://developer.nvidia.com/embedded/jetpack).
+Ollama runs well on [NVIDIA Jetson Devices](https://www.nvidia.com/en-us/autonomous-machines/embedded-systems/) and should run out of the box with the standard installation instructions. 
 
-NVIDIA Jetson devices are Linux-based embedded AI computers that are purpose-built for AI applications.
-
-Jetsons have an integrated GPU that is wired directly to the memory controller of the machine. For this reason, the `nvidia-smi` command is unrecognized, and Ollama proceeds to operate in "CPU only"
-mode. This can be verified by using a monitoring tool like jtop.
-
-In order to address this, we simply pass the path to the Jetson's pre-installed CUDA libraries into `ollama serve` (while in a tmux session). We then hardcode the num_gpu parameters into a cloned
-version of our target model.
-
-Prerequisites:
-
-- curl
-- tmux
-
-Here are the steps:
+The following has been tested on [JetPack 5.1.2](https://developer.nvidia.com/embedded/jetpack), but should also work on JetPack 6.0.
 
 - Install Ollama via standard Linux command (ignore the 404 error): `curl https://ollama.com/install.sh | sh`
-- Stop the Ollama service: `sudo systemctl stop ollama`
-- Start Ollama serve in a tmux session called ollama_jetson and reference the CUDA libraries path: `tmux has-session -t ollama_jetson 2>/dev/null || tmux new-session -d -s ollama_jetson 
-'LD_LIBRARY_PATH=/usr/local/cuda/lib64 ollama serve'`
 - Pull the model you want to use (e.g. mistral): `ollama pull mistral`
-- Create a new Modelfile specifically for enabling GPU support on the Jetson: `touch ModelfileMistralJetson`
-- In the ModelfileMistralJetson file, specify the FROM model and the num_gpu PARAMETER as shown below:
-
-```
-FROM mistral
-PARAMETER num_gpu 999
-```
+- Start an interactive session: `ollama run mistral`
 
-- Create a new model from your Modelfile: `ollama create mistral-jetson -f ./ModelfileMistralJetson`
-- Run the new model: `ollama run mistral-jetson`
+And that's it!
 
-If you run a monitoring tool like jtop you should now see that Ollama is using the Jetson's integrated GPU.
+# Running Ollama in Docker
 
-And that's it!
+When running GPU accelerated applications in Docker, it is highly recommended to use [dusty-nv jetson-containers repo](https://github.com/dusty-nv/jetson-containers).
\ No newline at end of file

docs/windows.md

@@ -14,7 +14,7 @@ As this is a preview release, you should expect a few bugs here and there.  If
 you run into a problem you can reach out on
 [Discord](https://discord.gg/ollama), or file an
 [issue](https://github.com/ollama/ollama/issues).
-Logs will often be helpful in dianosing the problem (see
+Logs will often be helpful in diagnosing the problem (see
 [Troubleshooting](#troubleshooting) below)
 
 ## System Requirements
@@ -27,7 +27,7 @@ Logs will often be helpful in dianosing 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
@@ -45,3 +45,17 @@ the explorer window by hitting `<cmd>+R` and type in:
 - `explorer %LOCALAPPDATA%\Programs\Ollama` contains the binaries (The installer adds this to your user PATH)
 - `explorer %HOMEPATH%\.ollama` contains models and configuration
 - `explorer %TEMP%` contains temporary executable files in one or more `ollama*` directories
+
+
+## Standalone CLI
+
+The easiest way to install Ollama on Windows is to use the `OllamaSetup.exe`
+installer. It installs in your account without requiring Administrator rights.
+We update Ollama regularly to support the latest models, and this installer will
+help you keep up to date.
+
+If you'd like to install or integrate Ollama as a service, a standalone
+`ollama-windows-amd64.zip` zip file is available containing only the Ollama CLI
+and GPU library dependencies for Nvidia and AMD. This allows for embedding
+Ollama in existing applications, or running it as a system service via `ollama
+serve` with tools such as [NSSM](https://nssm.cc/).

examples/bash-comparemodels/README.md

@@ -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.
 

examples/flyio/.gitignore

+fly.toml

examples/flyio/README.md

+# Deploy Ollama to Fly.io
+
+> Note: this example exposes a public endpoint and does not configure authentication. Use with care.
+
+## Prerequisites
+
+- Ollama: https://ollama.com/download
+- Fly.io account. Sign up for a free account: https://fly.io/app/sign-up
+
+## Steps
+
+1. Login to Fly.io
+
+    ```bash
+    fly auth login
+    ```
+
+1. Create a new Fly app
+
+    ```bash
+    fly launch --name <name> --image ollama/ollama --internal-port 11434 --vm-size shared-cpu-8x --now
+    ```
+
+1. Pull and run `orca-mini:3b`
+
+    ```bash
+    OLLAMA_HOST=https://<name>.fly.dev ollama run orca-mini:3b
+    ```
+
+`shared-cpu-8x` is a free-tier eligible machine type. For better performance, switch to a `performance` or `dedicated` machine type or attach a GPU for hardware acceleration (see below).
+
+## (Optional) Persistent Volume
+
+By default Fly Machines use ephemeral storage which is problematic if you want to use the same model across restarts without pulling it again. Create and attach a persistent volume to store the downloaded models:
+
+1. Create the Fly Volume
+
+    ```bash
+    fly volume create ollama
+    ```
+
+1. Update `fly.toml` and add `[mounts]`
+
+    ```toml
+    [mounts]
+      source = "ollama"
+      destination = "/mnt/ollama/models"
+    ```
+
+1. Update `fly.toml` and add `[env]`
+
+    ```toml
+    [env]
+      OLLAMA_MODELS = "/mnt/ollama/models"
+    ```
+
+1. Deploy your app
+
+    ```bash
+    fly deploy
+    ```
+
+## (Optional) Hardware Acceleration
+
+Fly.io GPU is currently in waitlist. Sign up for the waitlist: https://fly.io/gpu
+
+Once you've been accepted, create the app with the additional flags `--vm-gpu-kind a100-pcie-40gb` or `--vm-gpu-kind a100-pcie-80gb`.

examples/go-chat/main.go

@@ -35,7 +35,7 @@ func main() {
 
 	ctx := context.Background()
 	req := &api.ChatRequest{
-		Model:    "llama2",
+		Model:    "llama3",
 		Messages: messages,
 	}