Papers › Mistral 7B

Mistral 7B

10 Oct 2023arXiv:2310.06825archive 2025-07-28

Albert Q. Jiang, Alexandre Sablayrolles, Arthur Mensch, Chris Bamford, Devendra Singh Chaplot, Diego de Las Casas, Florian Bressand, Gianna Lengyel, Guillaume Lample, Lucile Saulnier, Lélio Renard Lavaud, Marie-Anne Lachaux, Pierre Stock, Teven Le Scao, Thibaut Lavril, Thomas Wang, Timothée Lacroix, William El Sayed

We introduce Mistral 7B v0.1, a 7-billion-parameter language model engineered for superior performance and efficiency. Mistral 7B outperforms Llama 2 13B across all evaluated benchmarks, and Llama 1 34B in reasoning, mathematics, and code generation. Our model leverages grouped-query attention (GQA) for faster inference, coupled with sliding window attention (SWA) to effectively handle sequences of arbitrary length with a reduced inference cost. We also provide a model fine-tuned to follow instructions, Mistral 7B -- Instruct, that surpasses the Llama 2 13B -- Chat model both on human and automated benchmarks. Our models are released under the Apache 2.0 license.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 11 code samples harvested from 2 repositories linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 2 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

mistralai/mistral-src officialmentioned in paperpytorchApache-2.0Syntology: 10 samples, 9 ran (0 instrument-failed) · 1 unverified report
facebookresearch/fairseq2 mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
knowlab/bi-weekly-paper-presentation mentioned on GitHubSyntology: not harvested report
mgmalek/efficient_cross_entropy mentioned on GitHubpytorchMITSyntology: not harvested report
ninglab/ecellm mentioned on GitHubpytorchCC-BY-4.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to eCeLLM: Generalizing Large Language Models for E-commerce from Large-scale,... (arXiv:2402.08831; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

11 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

10ran
1unverified

Licence: 2 of the 11 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

mistralai/mistral-src official repository 10 samples, 9 ran (0 instrument-failed) · 1 unverified
get_cache_sizes src/mistral_inference/cache.py ran Apache-2.0 (permissive) · ef46cbe416befd2d · report fixture: signature n_layers:int/0/int, max_seq_len:int/0/int, sliding_window:NoneType/0/? · returned list · level recorded 2026-09-24
get_sub_grids src/mistral_inference/vision_encoder.py ran Apache-2.0 (permissive) · b5c578acc311d56e · report fixture: signature x:Tensor/2/float, image_sizes:list/1/tuple, spatial_merge_size:int/0/int · returned list · level recorded 2026-09-24
interleave_list src/mistral_inference/cache.py ran fingerprinted Apache-2.0 (permissive) · c7a274c6f99bd04a · report fixture: signature l1:list/1/Tensor, l2:list/1/Tensor · returned list · level recorded 2026-09-24
position_meshgrid src/mistral_inference/vision_encoder.py ran Apache-2.0 (permissive) · 61a59ec493b9ba5a · report fixture: signature patch_embeds_list:list/1/Tensor · returned Tensor · level recorded 2026-09-24
precompute_freqs_cis in 112 papers src/mistral_inference/rope.py ran Apache-2.0 (permissive) here; the stored copy is pointer only · 99e0ca21ba709107 · report fixture: signature dim:int/0/int, end:int/0/int, theta:float/0/float · returned Tensor · level recorded 2026-09-24
precompute_freqs_cis_2d in 13 papers src/mistral_inference/rope.py ran Apache-2.0 (permissive) · acf80db8b8e014ad · report fixture: signature dim:int/0/int, height:int/0/int, width:int/0/int, theta:float/0/float · returned Tensor · level recorded 2026-09-24
repeat_kv in 244 papers
census: 15 implementations from 60 papers, 2 distinct outputs on one shared input
src/mistral_inference/transformer_layers.py ran Apache-2.0 (permissive) · a034294fb9d68dfa · report fixture: signature keys:Tensor/3/float, values:Tensor/3/float, repeats:int/0/int, dim:int/0/int · returned tuple · level recorded 2026-09-24
sample in 167 papers
census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
src/mistral_inference/generate.py ran Apache-2.0 (permissive) · 8e0352e68edf6866 · report fixture: signature logits:Tensor/2/float, temperature:float/0/float, top_p:float/0/float · returned Tensor · level recorded 2026-09-24
unrotate src/mistral_inference/cache.py ran fingerprinted Apache-2.0 (permissive) · 231f8bcb0c0c8bab · report fixture: signature cache:Tensor/3/float, seqlen:int/0/int · returned Tensor · level recorded 2026-09-24
apply_rotary_emb in 121 papers src/mistral_inference/rope.py unverified Apache-2.0 (permissive) · 0539a5035c30fa83 · report
facebookresearch/fairseq2 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
get_log_writer src/fairseq2/logging.py ran MIT recorded; this copy not marked cleared · pointer only · 29195f3023e17f2d · report fixture: signature name:str/0/str · returned LogWriter · level recorded 2026-09-24

Tasks

Arithmetic ReasoningChatbotCode GenerationCommon Sense ReasoningLanguage ModelingLanguage ModellingMathMath Word Problem SolvingMathematical ReasoningMulti-task Language UnderstandingQuestion AnsweringSentence CompletionWorld KnowledgeZero-Shot Video Question Answeranswerability prediction

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Arithmetic Reasoning GSM8K Mistral 7B (maj@8) Accuracy 52.2 #131 of 164 Archive leaderboard report
Arithmetic Reasoning GSM8K Mistral 7B (maj@8) Parameters (Billion) 7 #131 of 164 Archive leaderboard report
Code Generation MBPP Mistral 7B (3-shot) Accuracy 47.5 #68 of 99 Archive leaderboard report
Common Sense Reasoning ARC (Challenge) Mistral 7B (0-shot) Accuracy 55.5 #30 of 54 Archive leaderboard report
Common Sense Reasoning ARC (Easy) Mistral 7B (0-shot) Accuracy 80.0 #16 of 47 Archive leaderboard report
Common Sense Reasoning WinoGrande Mistral 7B (0-shot) Accuracy 75.3 #26 of 77 Archive leaderboard report
Math Word Problem Solving MATH Mistral 7B (maj@4) Accuracy 13.1 #111 of 135 Archive leaderboard report
Math Word Problem Solving MATH Mistral 7B (maj@4) Parameters (Billions) 7 #111 of 135 Archive leaderboard report
Multi-task Language Understanding MML Mistral 7B (5-shot) Average (%) 60.1 #18 of 44 Archive leaderboard report
Question Answering Natural Questions Mistral 7B (5-shot) EM 28.8 #37 of 47 Archive leaderboard report
Question Answering PIQA Mistral 7B (0-shot) Accuracy 83.0 #16 of 67 Archive leaderboard report
Question Answering PeerQA Mistral-v02-7B-32k AlignScore 0.0827 #2 of 6 Archive leaderboard report
Question Answering PeerQA Mistral-v02-7B-32k Prometheus-2 Answer Correctness 3.4245 #2 of 6 Archive leaderboard report
Question Answering PeerQA Mistral-v02-7B-32k Rouge-L 0.1922 #2 of 6 Archive leaderboard report
Question Answering TriviaQA Mistral 7B (5-shot) EM 69.9 #32 of 56 Archive leaderboard report
Sentence Completion HellaSwag Mistral 7B (0-shot) Accuracy 81.3 #41 of 89 Archive leaderboard report
Zero-Shot Video Question Answer IntentQA Mistral (7B) Accuracy 50.4 #12 of 13 Archive leaderboard report
Zero-Shot Video Question Answer NExT-GQA Mistral (7B) Acc@GQA 9.2 #9 of 9 Archive leaderboard report
Zero-Shot Video Question Answer NExT-QA Mistral (7B) Accuracy 51.1 #27 of 27 Archive leaderboard report
answerability prediction PeerQA Mistral-IT-v02-7B-32k Macro F1 0.4703 #1 of 6 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

AttentionDense ConnectionsFeedforward NetworkGrouped-query attentionSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections