Skip to content

armgit / txtai

Public Imported from GitHub
0

💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows

Update recommended models, closes #573

davidmezzetti2ba32af615e9
diff --git a/README.md b/README.md
index 0579b33e..ed3bd3d5 100644
--- a/README.md
+++ b/README.md
@@ -161,7 +161,7 @@ See the table below for the current recommended models. These models all allow c
| [Labels - Zero Shot](https://neuml.github.io/txtai/pipeline/text/labels) | [BART-Large-MNLI](https://hf.co/facebook/bart-large) |
| [Labels - Fixed](https://neuml.github.io/txtai/pipeline/text/labels) | Fine-tune with [training pipeline](https://neuml.github.io/txtai/pipeline/train/trainer) |
| [Large Language Model (LLM)](https://neuml.github.io/txtai/pipeline/text/llm) | [Flan T5 XL](https://hf.co/google/flan-t5-xl) |
-| | [Falcon 7B Instruct](https://hf.co/tiiuae/falcon-7b-instruct) |
+| | [Mistral 7B OpenOrca](https://hf.co/Open-Orca/Mistral-7B-OpenOrca) |
| [Summarization](https://neuml.github.io/txtai/pipeline/text/summary) | [DistilBART](https://hf.co/sshleifer/distilbart-cnn-12-6) |
| [Text-to-Speech](https://neuml.github.io/txtai/pipeline/audio/texttospeech) | [ESPnet JETS](https://hf.co/NeuML/ljspeech-jets-onnx) |
| [Transcription](https://neuml.github.io/txtai/pipeline/audio/transcription) | [Whisper](https://hf.co/openai/whisper-base) |
@@ -173,7 +173,7 @@ See the following links to learn more.
- [Hugging Face Tasks](https://hf.co/tasks)
- [Hugging Face Model Hub](https://hf.co/models)
-- [MTSB Leaderboard](https://hf.co/spaces/mteb/leaderboard)
+- [MTEB Leaderboard](https://hf.co/spaces/mteb/leaderboard)
- [Open LLM Leaderboard](https://hf.co/spaces/HuggingFaceH4/open_llm_leaderboard)
## Powered by txtai
diff --git a/docs/faq.md b/docs/faq.md
index 9284dd73..52bf3017 100644
--- a/docs/faq.md
+++ b/docs/faq.md
@@ -56,12 +56,11 @@ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from txtai.pipeline import LLM
-# Load Falcon-7B-Instruct
-path = "tiiuae/falcon-7b-instruct"
+# Load Mistral-7B-OpenOrca
+path = "Open-Orca/Mistral-7B-OpenOrca"
model = AutoModelForCausalLM.from_pretrained(
path,
torch_dtype=torch.bfloat16,
- trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(path)
diff --git a/docs/models.md b/docs/models.md
index 9ad6f5f1..c0d5b323 100644
--- a/docs/models.md
+++ b/docs/models.md
@@ -12,7 +12,7 @@ See the table below for the current recommended models. These models all allow c
| [Labels - Zero Shot](./pipeline/text/labels.md) | [BART-Large-MNLI](https://hf.co/facebook/bart-large) |
| [Labels - Fixed](./pipeline/text/labels.md) | Fine-tune with [training pipeline](./pipeline/train/trainer.md) |
| [Large Language Model (LLM)](./pipeline/text/llm.md) | [Flan T5 XL](https://hf.co/google/flan-t5-xl) |
-| | [Falcon 7B Instruct](https://hf.co/tiiuae/falcon-7b-instruct) |
+| | [Mistral 7B OpenOrca](https://hf.co/Open-Orca/Mistral-7B-OpenOrca) |
| [Summarization](./pipeline/text/summary.md) | [DistilBART](https://hf.co/sshleifer/distilbart-cnn-12-6) |
| [Text-to-Speech](./pipeline/audio/texttospeech.md) | [ESPnet JETS](https://hf.co/NeuML/ljspeech-jets-onnx) |
| [Transcription](./pipeline/audio/transcription.md) | [Whisper](https://hf.co/openai/whisper-base) |
@@ -24,5 +24,5 @@ See the following links to learn more.
- [Hugging Face Tasks](https://hf.co/tasks)
- [Hugging Face Model Hub](https://hf.co/models)
-- [MTSB Leaderboard](https://hf.co/spaces/mteb/leaderboard)
+- [MTEB Leaderboard](https://hf.co/spaces/mteb/leaderboard)
- [Open LLM Leaderboard](https://hf.co/spaces/HuggingFaceH4/open_llm_leaderboard)
diff --git a/docs/pipeline/text/llm.md b/docs/pipeline/text/llm.md
index 06b05fb6..8d6dd31a 100644
--- a/docs/pipeline/text/llm.md
+++ b/docs/pipeline/text/llm.md
@@ -54,12 +54,11 @@ import torch
from transformers import AutoModelForCausalLM, AutoTokenizer
from txtai.pipeline import LLM
-# Load Falcon-7B-Instruct
-path = "tiiuae/falcon-7b-instruct"
+# Load Mistral-7B-OpenOrca
+path = "Open-Orca/Mistral-7B-OpenOrca"
model = AutoModelForCausalLM.from_pretrained(
path,
torch_dtype=torch.bfloat16,
- trust_remote_code=True
)
tokenizer = AutoTokenizer.from_pretrained(path)
@@ -94,9 +93,8 @@ Similar to the Python example above, the underlying [Hugging Face pipeline param
```yaml
llm:
- path: tiiuae/falcon-7b-instruct
+ path: Open-Orca/Mistral-7B-OpenOrca
torch_dtype: torch.bfloat16
- trust_remote_code: True
```
### Run with Workflows