Pleais-Nano-MLX

[!IMPORTANT] Original Model Link : https://huggingface.co/PleIAs/Pleias-Nano

name: Pleias-Nano-MLX
base_model: Pleias-nano-1.2b-Preview
license: apache-2.0
pipeline_tag: text-generation
tasks :
 - text-generation
 - text2text-generation
 - retrieval-augmented-generation
 - text-to-text
language :
 - en
 - fr
 - de
 - es
 - it
 - nl
 - la
 - pt
datasets: PleIAs/common_corpus
funded_by :
 - Mozilla Foundation
 - TractoAI
hardware_type: ISEG GPU Cluster
cloud_provider :
 - TractoAI
 - Nebius AI
co2_emitted: 4 tons CO2eq
get_started_code: see below

Pleias-Nano-MLX

Pleias-Nano-MLX is a language model specialized for Retrieval-Augmented-Generation tasks and trained exclusively on public domain and licensed data. This repo contains unquantized MLX format weights of the model for Apple devices.

Please note that ALL prompts must begin with this token structure:

<|query_start|>  <|query_end|>
<|source_start|><|source_id_start|><|source_id_end|><|source_end|>
<|source_start|><|source_id_start|><|source_id_end|><|source_end|>
<|source_start|><|source_id_start|><|source_id_end|><|source_end|>
<|source_analysis_start|>

Where query is the user prompt, source_id is the hash of the information, and immediately following the source_id_end tag is the textual content of the source.

[!WARNING] MLX is a framework for METAL graphics supported by Apple computers with ARM M-series processors (M1/M2/M3/M4)

[!NOTE] Generation using uv https://docs.astral.sh/uv/**:

uvx --from mlx-lm mlx_lm.generate --model  --model darkshapes/Pleias-Nano-MLX --prompt '<|query_start|>Is Wikipedia reliable?<|query_end|>\n<|source_start|><|source_id_start|>ebea70a3502acfbd<|source_id_end|>Articles for traditional encyclopedias such as Encyclopædia Britannica are written by experts, lending such encyclopedias a reputation for accuracy.[144] However, a peer review in 2005 of forty-two scientific entries on both Wikipedia and Encyclopædia Britannica by the science journal Nature found few differences in accuracy, and concluded that "the average science entry in Wikipedia contained around four inaccuracies; Britannica, about three."[145] Joseph Reagle suggested that while the study reflects "a topical strength of Wikipedia contributors" in science articles, "Wikipedia may not have fared so well using a random sampling of articles or on humanities subjects."<|source_end|>\n<|source_start|><|source_id_start|>5f862e733d38288e<|source_id_end|>As a consequence of the open structure, Wikipedia "makes no guarantee of validity" of its content, since no one is ultimately responsible for any claims appearing in it.[W 54] Concerns have been raised by PC World in 2009 regarding the lack of accountability that results from users\' anonymity, the insertion of false information,[152] vandalism, and similar problems. Legal Research in a Nutshell (2011), cites Wikipedia as a "general source" that "can be a real boon" in "coming up to speed in the law governing a situation" and, "while not authoritative, can provide basic facts as well as leads to more in-depth resources".<|source_end|>\n<|source_start|><|source_id_start|>354fa4908152b336<|source_id_end|>Wikipedia\'s open structure inherently makes it an easy target for Internet trolls, spammers, and various forms of paid advocacy seen as counterproductive to the maintenance of a neutral and verifiable online encyclopedia.[70][W 55] In response to paid advocacy editing and undisclosed editing issues, Wikipedia was reported in an article in The Wall Street Journal to have strengthened its rules and laws against undisclosed editing.[162] The article stated that: "Beginning Monday [from the date of the article, June 16, 2014], changes in Wikipedia\'s terms of use will require anyone paid to edit articles to disclose that arrangement. Katherine Maher, the nonprofit Wikimedia Foundation\'s chief communications officer, said the changes address a sentiment among volunteer editors that "we\'re not an advertising service; we\'re an encyclopedia.""<|source_end|>\n<|source_analysis_start|>'

[!NOTE] Generation using pip:

pipx --from mlx-lm mlx_lm.generate --model  --model darkshapes/Pleias-Nano-MLX --prompt  '<|query_start|>Is Wikipedia reliable?<|query_end|>\n<|source_start|><|source_id_start|>ebea70a3502acfbd<|source_id_end|>Articles for traditional encyclopedias such as Encyclopædia Britannica are written by experts, lending such encyclopedias a reputation for accuracy.[144] However, a peer review in 2005 of forty-two scientific entries on both Wikipedia and Encyclopædia Britannica by the science journal Nature found few differences in accuracy, and concluded that "the average science entry in Wikipedia contained around four inaccuracies; Britannica, about three."[145] Joseph Reagle suggested that while the study reflects "a topical strength of Wikipedia contributors" in science articles, "Wikipedia may not have fared so well using a random sampling of articles or on humanities subjects."<|source_end|>\n<|source_start|><|source_id_start|>5f862e733d38288e<|source_id_end|>As a consequence of the open structure, Wikipedia "makes no guarantee of validity" of its content, since no one is ultimately responsible for any claims appearing in it.[W 54] Concerns have been raised by PC World in 2009 regarding the lack of accountability that results from users\' anonymity, the insertion of false information,[152] vandalism, and similar problems. Legal Research in a Nutshell (2011), cites Wikipedia as a "general source" that "can be a real boon" in "coming up to speed in the law governing a situation" and, "while not authoritative, can provide basic facts as well as leads to more in-depth resources".<|source_end|>\n<|source_start|><|source_id_start|>354fa4908152b336<|source_id_end|>Wikipedia\'s open structure inherently makes it an easy target for Internet trolls, spammers, and various forms of paid advocacy seen as counterproductive to the maintenance of a neutral and verifiable online encyclopedia.[70][W 55] In response to paid advocacy editing and undisclosed editing issues, Wikipedia was reported in an article in The Wall Street Journal to have strengthened its rules and laws against undisclosed editing.[162] The article stated that: "Beginning Monday [from the date of the article, June 16, 2014], changes in Wikipedia\'s terms of use will require anyone paid to edit articles to disclose that arrangement. Katherine Maher, the nonprofit Wikimedia Foundation\'s chief communications officer, said the changes address a sentiment among volunteer editors that "we\'re not an advertising service; we\'re an encyclopedia.""<|source_end|>\n<|source_analysis_start|>'