Skip to content

Commit

Permalink
Change cookbook examples: Download model weights in the hub cache fol…
Browse files Browse the repository at this point in the history 
…der (#1097)

Change cookbook examples: Download model weights in the hub cache folder
  • Loading branch information
@alonsosilvaallende
alonsosilvaallende committed Aug 13, 2024
1 parent 90e588c commit ce49ccd
Show file tree
Hide file tree
Showing 4 changed files with 148 additions and 76 deletions.
56 changes: 37 additions & 19 deletions docs/cookbook/chain_of_thought.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -11,30 +11,48 @@ We use [llama.cpp](https://github.com/ggerganov/llama.cpp) using the [llama-cpp-
pip install llama-cpp-python
```

We pull a quantized GGUF model, in this guide we pull [Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF) by [NousResearch](https://nousresearch.com/) from [HuggingFace](https://huggingface.co/):
We download the model weights by passing the name of the repository on the HuggingFace Hub, and the filenames (or glob pattern):
```python
import llama_cpp
from outlines import generate, models

```bash
wget https://hf.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
model = models.llamacpp("NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF",
"Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf",
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B"
),
n_gpu_layers=-1,
flash_attn=True,
n_ctx=8192,
verbose=False)
```

We initialize the model:
??? note "(Optional) Store the model weights in a custom folder"

```python
from llama_cpp import Llama
from outlines import generate, models
By default the model weights are downloaded to the hub cache but if we want so store the weights in a custom folder, we pull a quantized GGUF model [Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF) by [NousResearch](https://nousresearch.com/) from [HuggingFace](https://huggingface.co/):

llm = Llama(
"/path/to/model/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf",
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B"
),
n_gpu_layers=-1,
flash_attn=True,
n_ctx=8192,
verbose=False
)
model = models.LlamaCpp(llm)
```
```bash
wget https://hf.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
```

We initialize the model:

```python
import llama_cpp
from llama_cpp import Llama
from outlines import generate, models

llm = Llama(
"/path/to/model/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf",
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B"
),
n_gpu_layers=-1,
flash_attn=True,
n_ctx=8192,
verbose=False
)
```

## Chain of thought

Expand Down
56 changes: 37 additions & 19 deletions docs/cookbook/knowledge_graph_extraction.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -8,30 +8,48 @@ We will use [llama.cpp](https://github.com/ggerganov/llama.cpp) using the [llama
pip install llama-cpp-python
```

We pull a quantized GGUF model, in this guide we pull [Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF) by [NousResearch](https://nousresearch.com/) from [HuggingFace](https://huggingface.co/):
We download the model weights by passing the name of the repository on the HuggingFace Hub, and the filenames (or glob pattern):
```python
import llama_cpp
from outlines import generate, models

```bash
wget https://hf.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
model = models.llamacpp("NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF",
"Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf",
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B"
),
n_gpu_layers=-1,
flash_attn=True,
n_ctx=8192,
verbose=False)
```

We initialize the model:
??? note "(Optional) Store the model weights in a custom folder"

```python
from llama_cpp import Llama
from outlines import generate, models
By default the model weights are downloaded to the hub cache but if we want so store the weights in a custom folder, we pull a quantized GGUF model [Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF) by [NousResearch](https://nousresearch.com/) from [HuggingFace](https://huggingface.co/):

llm = Llama(
"/path/to/model/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf",
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B"
),
n_gpu_layers=-1,
flash_attn=True,
n_ctx=8192,
verbose=False
)
model = models.LlamaCpp(llm)
```
```bash
wget https://hf.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
```

We initialize the model:

```python
import llama_cpp
from llama_cpp import Llama
from outlines import generate, models

llm = Llama(
"/path/to/model/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf",
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B"
),
n_gpu_layers=-1,
flash_attn=True,
n_ctx=8192,
verbose=False
)
```

## Knowledge Graph Extraction

Expand Down
55 changes: 37 additions & 18 deletions docs/cookbook/qa-with-citations.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -8,29 +8,48 @@ We will use [llama.cpp](https://github.com/ggerganov/llama.cpp) using the [llama
pip install llama-cpp-python
```

We pull a quantized GGUF model [Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF) by [NousResearch](https://nousresearch.com/) from [HuggingFace](https://huggingface.co/):
We download the model weights by passing the name of the repository on the HuggingFace Hub, and the filenames (or glob pattern):
```python
import llama_cpp
from outlines import generate, models

```bash
wget https://hf.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
model = models.llamacpp("NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF",
"Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf",
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B"
),
n_gpu_layers=-1,
flash_attn=True,
n_ctx=8192,
verbose=False)
```

We initialize the model:
??? note "(Optional) Store the model weights in a custom folder"

```python
from llama_cpp import Llama
from outlines import generate, models
By default the model weights are downloaded to the hub cache but if we want so store the weights in a custom folder, we pull a quantized GGUF model [Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF) by [NousResearch](https://nousresearch.com/) from [HuggingFace](https://huggingface.co/):

llm = Llama(
"/path/to/model/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf",
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B"
),
n_gpu_layers=-1,
flash_attn=True,
n_ctx=8192,
verbose=False
)
```
```bash
wget https://hf.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
```

We initialize the model:

```python
import llama_cpp
from llama_cpp import Llama
from outlines import generate, models

llm = Llama(
"/path/to/model/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf",
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B"
),
n_gpu_layers=-1,
flash_attn=True,
n_ctx=8192,
verbose=False
)
```

## Generate Synthetic Data

Expand Down
57 changes: 37 additions & 20 deletions docs/cookbook/react_agent.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -12,32 +12,49 @@ We use [llama.cpp](https://github.com/ggerganov/llama.cpp) using the [llama-cpp-
pip install llama-cpp-python
```

We pull a quantized GGUF model, in this guide we pull [Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF) by [NousResearch](https://nousresearch.com/) from [HuggingFace](https://huggingface.co/):

```bash
wget https://hf.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
```

We initialize the model:

We download the model weights by passing the name of the repository on the HuggingFace Hub, and the filenames (or glob pattern):
```python
import llama_cpp
from llama_cpp import Llama
from outlines import generate, models

llm = Llama(
"/path/to/model/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf",
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B"
),
n_gpu_layers=-1,
flash_attn=True,
n_ctx=8192,
verbose=False
)
model = models.LlamaCpp(llm)
model = models.llamacpp("NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF",
"Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf",
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B"
),
n_gpu_layers=-1,
flash_attn=True,
n_ctx=8192,
verbose=False)
```

??? note "(Optional) Store the model weights in a custom folder"

By default the model weights are downloaded to the hub cache but if we want so store the weights in a custom folder, we pull a quantized GGUF model [Hermes-2-Pro-Llama-3-8B](https://huggingface.co/NousResearch/Hermes-2-Theta-Llama-3-8B-GGUF) by [NousResearch](https://nousresearch.com/) from [HuggingFace](https://huggingface.co/):

```bash
wget https://hf.co/NousResearch/Hermes-2-Pro-Llama-3-8B-GGUF/resolve/main/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf
```

We initialize the model:

```python
import llama_cpp
from llama_cpp import Llama
from outlines import generate, models

llm = Llama(
"/path/to/model/Hermes-2-Pro-Llama-3-8B-Q4_K_M.gguf",
tokenizer=llama_cpp.llama_tokenizer.LlamaHFTokenizer.from_pretrained(
"NousResearch/Hermes-2-Pro-Llama-3-8B"
),
n_gpu_layers=-1,
flash_attn=True,
n_ctx=8192,
verbose=False
)
```

## Build a ReAct agent

In this example, we use two tools:
Expand Down

0 comments on commit ce49ccd

Please sign in to comment.