diff --git a/docs/images/ollama-keys.png b/docs/images/ollama-keys.png new file mode 100644 index 00000000..119a4bcf Binary files /dev/null and b/docs/images/ollama-keys.png differ diff --git a/docs/images/signup.png b/docs/images/signup.png new file mode 100644 index 00000000..e80bb4e7 Binary files /dev/null and b/docs/images/signup.png differ diff --git a/docs/import.md b/docs/import.md index 82ea9ba5..baf34550 100644 --- a/docs/import.md +++ b/docs/import.md @@ -1,44 +1,129 @@ -# Import +# Importing a model -GGUF models and select Safetensors models can be imported directly into Ollama. +## Table of Contents -## Import GGUF + * [Importing a Safetensors adapter](#Importing-a-fine-tuned-adapter-from-Safetensors-weights) + * [Importing a Safetensors model](#Importing-a-model-from-Safetensors-weights) + * [Importing a GGUF file](#Importing-a-GGUF-based-model-or-adapter) + * [Sharing models on ollama.com](#Sharing-your-model-on-ollama.com) -A binary GGUF file can be imported directly into Ollama through a Modelfile. +## Importing a fine tuned adapter from Safetensors weights + +First, create a `Modelfile` with a `FROM` command pointing at the base model you used for fine tuning, and an `ADAPTER` command which points to the directory with your Safetensors adapter: ```dockerfile -FROM /path/to/file.gguf +FROM +ADAPTER /path/to/safetensors/adapter/directory ``` -## Import Safetensors +Make sure that you use the same base model in the `FROM` command as you used to create the adapter otherwise you will get erratic results. Most frameworks use different quantization methods, so it's best to use non-quantized (i.e. non-QLoRA) adapters. If your adapter is in the same directory as your `Modelfile`, use `ADAPTER .` to specify the adapter path. -If the model being imported is one of these architectures, it can be imported directly into Ollama through a Modelfile: +Now run `ollama create` from the directory where the `Modelfile` was created: - - LlamaForCausalLM - - MistralForCausalLM - - MixtralForCausalLM - - GemmaForCausalLM - - Phi3ForCausalLM +```bash +ollama create my-model +``` + +Lastly, test the model: + +```bash +ollama run my-model +``` + +Ollama supports importing adapters based on several different model architectures including: + + * Llama (including Llama 2, Llama 3, and Llama 3.1); + * Mistral (including Mistral 1, Mistral 2, and Mixtral); and + * Gemma (including Gemma 1 and Gemma 2) + +You can create the adapter using a fine tuning framework or tool which can output adapters in the Safetensors format, such as: + + * Hugging Face [fine tuning framework] (https://huggingface.co/docs/transformers/en/training) + * [Unsloth](https://github.com/unslothai/unsloth) + * [MLX](https://github.com/ml-explore/mlx) + + +## Importing a model from Safetensors weights + +First, create a `Modelfile` with a `FROM` command which points to the directory containing your Safetensors weights: ```dockerfile FROM /path/to/safetensors/directory ``` -For architectures not directly convertable by Ollama, see llama.cpp's [guide](https://github.com/ggerganov/llama.cpp/blob/master/README.md#prepare-and-quantize) on conversion. After conversion, see [Import GGUF](#import-gguf). +If you create the Modelfile in the same directory as the weights, you can use the command `FROM .`. -## Automatic Quantization +Now run the `ollama create` command from the directory where you created the `Modelfile`: -> [!NOTE] -> Automatic quantization requires v0.1.35 or higher. +```shell +ollama create my-model +``` -Ollama is capable of quantizing FP16 or FP32 models to any of the supported quantizations with the `-q/--quantize` flag in `ollama create`. +Lastly, test the model: + +```shell +ollama run my-model +``` + +Ollama supports importing models for several different architectures including: + + * Llama (including Llama 2, Llama 3, and Llama 3.1); + * Mistral (including Mistral 1, Mistral 2, and Mixtral); + * Gemma (including Gemma 1 and Gemma 2); and + * Phi3 + +This includes importing foundation models as well as any fine tuned models which which have been _fused_ with a foundation model. + + +## Importing a GGUF based model or adapter + +If you have a GGUF based model or adapter it is possible to import it into Ollama. You can obtain a GGUF model or adapter by: + + * converting a Safetensors model with the `convert_hf_to_gguf.py` from Llama.cpp; + * converting a Safetensors adapter with the `convert_lora_to_gguf.py` from Llama.cpp; or + * downloading a model or adapter from a place such as HuggingFace + +To import a GGUF model, create a `Modelfile` containg: + +```dockerfile +FROM /path/to/file.gguf +``` + +For a GGUF adapter, create the `Modelfile` with: + +```dockerfile +FROM +ADAPTER /path/to/file.gguf +``` + +When importing a GGUF adapter, it's important to use the same base model as the base model that the adapter was created with. You can use: + + * a model from Ollama + * a GGUF file + * a Safetensors based model + +Once you have created your `Modelfile`, use the `ollama create` command to build the model. + +```shell +ollama create my-model +``` + +## Quantizing a Model + +Quantizing a model allows you to run models faster and with less memory consumption but at reduced accuracy. This allows you to run a model on more modest hardware. + +Ollama can quantize FP16 and FP32 based models into different quantization levels using the `-q/--quantize` flag with the `ollama create` command. + +First, create a Modelfile with the FP16 or FP32 based model you wish to quantize. ```dockerfile FROM /path/to/my/gemma/f16/model ``` +Use `ollama create` to then create the quantized model. + ```shell -$ ollama create -q Q4_K_M mymodel +$ ollama create --quantize q4_K_M mymodel transferring model data quantizing F16 model to Q4_K_M creating new layer sha256:735e246cc1abfd06e9cdcf95504d6789a6cd1ad7577108a70d9902fef503c1bd @@ -49,42 +134,53 @@ success ### Supported Quantizations -- `Q4_0` -- `Q4_1` -- `Q5_0` -- `Q5_1` -- `Q8_0` +- `q4_0` +- `q4_1` +- `q5_0` +- `q5_1` +- `q8_0` #### K-means Quantizations -- `Q3_K_S` -- `Q3_K_M` -- `Q3_K_L` -- `Q4_K_S` -- `Q4_K_M` -- `Q5_K_S` -- `Q5_K_M` -- `Q6_K` +- `q3_K_S` +- `q3_K_M` +- `q3_K_L` +- `q4_K_S` +- `q4_K_M` +- `q5_K_S` +- `q5_K_M` +- `q6_K` -## Template Detection -> [!NOTE] -> Template detection requires v0.1.42 or higher. +## Sharing your model on ollama.com -Ollama uses model metadata, specifically `tokenizer.chat_template`, to automatically create a template appropriate for the model you're importing. +You can share any model you have created by pushing it to [ollama.com](https://ollama.com) so that other users can try it out. -```dockerfile -FROM /path/to/my/gemma/model -``` +First, use your browser to go to the [Ollama Sign-Up](https://ollama.com/signup) page. If you already have an account, you can skip this step. + +![Sign-Up](images/signup.png) + +The `Username` field will be used as part of your model's name (e.g. `jmorganca/mymodel`), so make sure you are comfortable with the username that you have selected. + +Now that you have created an account and are signed-in, go to the [Ollama Keys Settings](https://ollama.com/settings/keys) page. + +Follow the directions on the page to determine where your Ollama Public Key is located. + +![Ollama Key](images/ollama-keys.png) + +Click on the `Add Ollama Public Key` button, and copy and paste the contents of your Ollama Public Key into the text field. + +To push a model to [ollama.com](https://ollama.com), first make sure that it is named correctly with your username. You may have to use the `ollama cp` command to copy +your model to give it the correct name. Once you're happy with your model's name, use the `ollama push` command to push it to [ollama.com](https://ollama.com). ```shell -$ ollama create mymodel -transferring model data -using autodetected template gemma-instruct -creating new layer sha256:baa2a0edc27d19cc6b7537578a9a7ba1a4e3214dc185ed5ae43692b319af7b84 -creating new layer sha256:ba66c3309914dbef07e5149a648fd1877f030d337a4f240d444ea335008943cb -writing manifest -success +ollama cp mymodel myuser/mymodel +ollama push myuser/mymodel +``` + +Once your model has been pushed, other users can pull and run it by using the command: + +```shell +ollama run myuser/mymodel ``` -Defining a template in the Modelfile will disable this feature which may be useful if you want to use a different template than the autodetected one.