diff --git a/Falcon3-10B-Instruct-IQ2_M.gguf b/Falcon3-10B-Instruct-IQ2_M.gguf index 3ea8e75..17bf39e 100644 --- a/Falcon3-10B-Instruct-IQ2_M.gguf +++ b/Falcon3-10B-Instruct-IQ2_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:338604bfb7d62b2c9d6f5fe1eaca3644697fd779307864fdbda8427c3ff18c32 -size 3592343904 +oid sha256:6bfdb96d85d285fba5cce92e19d5a169fe5007c89402213c326a7bed14a7a98a +size 3592345280 diff --git a/Falcon3-10B-Instruct-IQ3_M.gguf b/Falcon3-10B-Instruct-IQ3_M.gguf index 599d1b1..d6c4b46 100644 --- a/Falcon3-10B-Instruct-IQ3_M.gguf +++ b/Falcon3-10B-Instruct-IQ3_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:8cad36eb51e20406871cb0807c57f2223121ccf3a3c0273666845a1ec79a8eaf -size 4704985440 +oid sha256:de23fb3ab383d7cfc9cdae7b5e56515a9a3ba39da165d8532d4c656640caf981 +size 4704986816 diff --git a/Falcon3-10B-Instruct-IQ3_XS.gguf b/Falcon3-10B-Instruct-IQ3_XS.gguf index 04c98d4..35b3569 100644 --- a/Falcon3-10B-Instruct-IQ3_XS.gguf +++ b/Falcon3-10B-Instruct-IQ3_XS.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:71644650f2cd847f74ec7289baf6e7b8ce1536dd179a13bf6bd8749ed5d5c8f8 -size 4368478560 +oid sha256:233ddddf817da2d2ecbf8938c842466c8a26bddd03539f23bf265219d684eda5 +size 4368479936 diff --git a/Falcon3-10B-Instruct-IQ4_NL.gguf b/Falcon3-10B-Instruct-IQ4_NL.gguf index 9b519e0..7dd4a85 100644 --- a/Falcon3-10B-Instruct-IQ4_NL.gguf +++ b/Falcon3-10B-Instruct-IQ4_NL.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6178ad26bc9393a6309da530f849933c0fc989232da33db074ece60a2d9c42f9 -size 5906346336 +oid sha256:fa5c378fc72ef712351c57d398bd73406ca7d195640859e759b7029e6428dff4 +size 5906347712 diff --git a/Falcon3-10B-Instruct-IQ4_XS.gguf b/Falcon3-10B-Instruct-IQ4_XS.gguf index dfda94f..6bbca8f 100644 --- a/Falcon3-10B-Instruct-IQ4_XS.gguf +++ b/Falcon3-10B-Instruct-IQ4_XS.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:b80226e41f7c89da8cdf5f6d5cd72e1796ee707b6e986f15b00226d3b9b55266 -size 5596885344 +oid sha256:674c4a1abd4f2ba4735fbcf8758d9d261a03c852a8fcb77ee0b173b4ba249470 +size 5596886720 diff --git a/Falcon3-10B-Instruct-Q2_K.gguf b/Falcon3-10B-Instruct-Q2_K.gguf index bc6d62e..777ed08 100644 --- a/Falcon3-10B-Instruct-Q2_K.gguf +++ b/Falcon3-10B-Instruct-Q2_K.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:70ffc9c01582c3d340bf26f9bece33022c0925418db63e63ba214049ee3377d0 -size 3924046176 +oid sha256:c1a557301c2033b0cc382cd0378427339145570b3167696cd5aad1ea3f88598a +size 3924047552 diff --git a/Falcon3-10B-Instruct-Q2_K_L.gguf b/Falcon3-10B-Instruct-Q2_K_L.gguf index 67c6af1..5ae4b3f 100644 --- a/Falcon3-10B-Instruct-Q2_K_L.gguf +++ b/Falcon3-10B-Instruct-Q2_K_L.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:cf8351b8e66dde26af67a696eec53fa21d791991dee329c432cf8fcf9942e938 -size 4317262176 +oid sha256:7de3aee551f7d29e7a5bcd215858a410ac4ce9143e923a89a907219469cd75c2 +size 4317263552 diff --git a/Falcon3-10B-Instruct-Q3_K_L.gguf b/Falcon3-10B-Instruct-Q3_K_L.gguf index f42cabe..c0e4464 100644 --- a/Falcon3-10B-Instruct-Q3_K_L.gguf +++ b/Falcon3-10B-Instruct-Q3_K_L.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:ed0020ab55f571aaed11f1cc78c404bec9ca41a815cc69eb6ce805763fd0e93c -size 5450805600 +oid sha256:d98144e6c0029150b9380432fc5fcf4ac7645c48f5a410778e85f6e269554c00 +size 5450806976 diff --git a/Falcon3-10B-Instruct-Q3_K_M.gguf b/Falcon3-10B-Instruct-Q3_K_M.gguf index 3135b7b..64feaae 100644 --- a/Falcon3-10B-Instruct-Q3_K_M.gguf +++ b/Falcon3-10B-Instruct-Q3_K_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0d2a6502eb596e228722b7198674c23303dba1b75118ff22a385f23551a22284 -size 5052477792 +oid sha256:9cd54148a18fed7218248f1b061da28eb17b6c211a4dd104eefadaab78163df5 +size 5052479168 diff --git a/Falcon3-10B-Instruct-Q3_K_S.gguf b/Falcon3-10B-Instruct-Q3_K_S.gguf index cc21ad9..54f36d1 100644 --- a/Falcon3-10B-Instruct-Q3_K_S.gguf +++ b/Falcon3-10B-Instruct-Q3_K_S.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7fb30ebfc8c7c089bed413e01a7eeb0dee10c8d313d580ee7e1affdf051cafcc -size 4591137120 +oid sha256:c2415a25684c23ab46f1487921c2283e6df240a4b24665d8a17f563139702081 +size 4591138496 diff --git a/Falcon3-10B-Instruct-Q3_K_XL.gguf b/Falcon3-10B-Instruct-Q3_K_XL.gguf index acf6b46..742bb34 100644 --- a/Falcon3-10B-Instruct-Q3_K_XL.gguf +++ b/Falcon3-10B-Instruct-Q3_K_XL.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:39d17d242f70dbc6391acf247f90036bee105798ec6d9ec2a8cb445c76e61a0d -size 5803127136 +oid sha256:39a4b5c7eade80af8d5995accd7264b8da8fe77d0857e466a49a1ec2e8039b72 +size 5803128512 diff --git a/Falcon3-10B-Instruct-Q4_0.gguf b/Falcon3-10B-Instruct-Q4_0.gguf index 814b244..994c9f6 100644 --- a/Falcon3-10B-Instruct-Q4_0.gguf +++ b/Falcon3-10B-Instruct-Q4_0.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:38e78c65a0b177930751b9fa952c07cb5ea9dc452115551b115ed73f8ab20773 -size 5928464736 +oid sha256:3fc9b922fa977d4c9a668259392b85d3debc9c0090c8ab69c7fd75e48c74c1aa +size 5928466112 diff --git a/Falcon3-10B-Instruct-Q4_K_L.gguf b/Falcon3-10B-Instruct-Q4_K_L.gguf index 4390218..b07ed02 100644 --- a/Falcon3-10B-Instruct-Q4_K_L.gguf +++ b/Falcon3-10B-Instruct-Q4_K_L.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:fe1121611ab643dadab522d5dded26da60f96b457e71f37e81b63741694f114d -size 6586364256 +oid sha256:5bba0ab10458d9157ab2cce73cb5b80472d51c3abb30a8c30ce8c96f0f6cbac8 +size 6586365632 diff --git a/Falcon3-10B-Instruct-Q4_K_M.gguf b/Falcon3-10B-Instruct-Q4_K_M.gguf index 3db5d4f..01f5e3a 100644 --- a/Falcon3-10B-Instruct-Q4_K_M.gguf +++ b/Falcon3-10B-Instruct-Q4_K_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:6d54a35d740a616061d6c7d7740d64f4339410e58aaba985aa9e1ea79c7e882a -size 6287520096 +oid sha256:0a33327bd71e1788a8e9f17889824a17a65efd3f96a4b2a5e2bc6ff2f39b8241 +size 6287521472 diff --git a/Falcon3-10B-Instruct-Q4_K_S.gguf b/Falcon3-10B-Instruct-Q4_K_S.gguf index e4ce72d..972e22d 100644 --- a/Falcon3-10B-Instruct-Q4_K_S.gguf +++ b/Falcon3-10B-Instruct-Q4_K_S.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:703cfbde06e7b7916fc22eb6d3fe98a5834a9cacf04a88fbabbbe4a7e4821e1a -size 5952156000 +oid sha256:0ee5cd9a6ca5229a1128efca439eb5a819de60494716701d2e8cf1f1fc4204d7 +size 5952157376 diff --git a/Falcon3-10B-Instruct-Q5_K_L.gguf b/Falcon3-10B-Instruct-Q5_K_L.gguf index f5b364c..859f28e 100644 --- a/Falcon3-10B-Instruct-Q5_K_L.gguf +++ b/Falcon3-10B-Instruct-Q5_K_L.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:e0574ced7e6705358de7b26de93faf02043af4c0b8d82a2d869e4fb0fbebc519 -size 7589065056 +oid sha256:6a08593991072df35c06985421e35958a622756a239beaa47eabb97425c2ca4e +size 7589066432 diff --git a/Falcon3-10B-Instruct-Q5_K_M.gguf b/Falcon3-10B-Instruct-Q5_K_M.gguf index 04a0f8b..39b689d 100644 --- a/Falcon3-10B-Instruct-Q5_K_M.gguf +++ b/Falcon3-10B-Instruct-Q5_K_M.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:536489b6ec6159beebc74e245b4b2d9f84b80fed4162fea6f50d604cb728858f -size 7340552544 +oid sha256:b517e3bb0c5cea162dc78d3ec6faf3050070b831dc62fc043185ee1a13d25b87 +size 7340553920 diff --git a/Falcon3-10B-Instruct-Q5_K_S.gguf b/Falcon3-10B-Instruct-Q5_K_S.gguf index 89ae420..5303220 100644 --- a/Falcon3-10B-Instruct-Q5_K_S.gguf +++ b/Falcon3-10B-Instruct-Q5_K_S.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:7f04a35603029bd1972fa8816405e95c3dc4e6fda9f25e8fc8bd2a5c8fc0d6d0 -size 7144190304 +oid sha256:dc746e634a575d4408963c058518f76a919f8ff53e849eb932541cfd252bed43 +size 7144191680 diff --git a/Falcon3-10B-Instruct-Q6_K.gguf b/Falcon3-10B-Instruct-Q6_K.gguf index 5fa54b0..5abb563 100644 --- a/Falcon3-10B-Instruct-Q6_K.gguf +++ b/Falcon3-10B-Instruct-Q6_K.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:44496b253716f229de0e9b33cffb748b2509afc53495b0c2e5eef3b32e8274c6 -size 8459399520 +oid sha256:18238ce1f254925d523a5dc4a1368325cd281b6921058e888218177344abdb9a +size 8459400896 diff --git a/Falcon3-10B-Instruct-Q6_K_L.gguf b/Falcon3-10B-Instruct-Q6_K_L.gguf index 18b5952..dde8c22 100644 --- a/Falcon3-10B-Instruct-Q6_K_L.gguf +++ b/Falcon3-10B-Instruct-Q6_K_L.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:88ff637ab1830664765d7da62f947c6fa4c24a3b7d38d4357cfb12dcc985af55 -size 8654434656 +oid sha256:a02adea7b8006cc89d1e9f5a7987267a1c051db1ddacae82d11a5ca17e29396c +size 8654436032 diff --git a/Falcon3-10B-Instruct-Q8_0.gguf b/Falcon3-10B-Instruct-Q8_0.gguf index 57e8fcf..48dee56 100644 --- a/Falcon3-10B-Instruct-Q8_0.gguf +++ b/Falcon3-10B-Instruct-Q8_0.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:98892efdf8233741cbaaa5f14a11b441a20fe8bd5962762bb2f3c3fa657b22b0 -size 10955239776 +oid sha256:e3f8f52d40f6e7fac068f7e99ce0ab3fe87fad927b13ef4bec14c1c2a451b363 +size 10955241152 diff --git a/Falcon3-10B-Instruct-f16.gguf b/Falcon3-10B-Instruct-f16.gguf index c512028..c70b9dc 100644 --- a/Falcon3-10B-Instruct-f16.gguf +++ b/Falcon3-10B-Instruct-f16.gguf @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:0bd98a38cbb5319d42b9d0b1e0880972e95e54c03c251989096931af6c85266e -size 20616556896 +oid sha256:68f5dfc8589711205d954f2d281324c793fb6c8bd4ecf37711b89be1cdc4377d +size 20616557984 diff --git a/Falcon3-10B-Instruct-f32.gguf b/Falcon3-10B-Instruct-f32.gguf deleted file mode 100644 index 85ee0f5..0000000 --- a/Falcon3-10B-Instruct-f32.gguf +++ /dev/null @@ -1,3 +0,0 @@ -version https://git-lfs.github.com/spec/v1 -oid sha256:efae50128b34ba1d339a8364401e9977df973bf878fab1afe6f26a14c2407cd7 -size 41227366464 diff --git a/Falcon3-10B-Instruct.imatrix b/Falcon3-10B-Instruct.imatrix index 24459e1..7e421fb 100644 --- a/Falcon3-10B-Instruct.imatrix +++ b/Falcon3-10B-Instruct.imatrix @@ -1,3 +1,3 @@ version https://git-lfs.github.com/spec/v1 -oid sha256:aa5e0f3b3fe2c742dc66d0b1d6139e82dbda6d5ace7274af9979f7e071c984b7 +oid sha256:edcc3047e032777ac26b4d4de5dee85e67f2731a99e658f7f015931a7ac1c0c0 size 6644818 diff --git a/README.md b/README.md index 83faf52..e7baca7 100644 --- a/README.md +++ b/README.md @@ -1,17 +1,112 @@ --- quantized_by: bartowski pipeline_tag: text-generation +license_name: falcon-llm-license tags: - falcon3 +license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html license: other base_model: tiiuae/Falcon3-10B-Instruct -license_name: falcon-llm-license -license_link: https://falconllm.tii.ae/falcon-terms-and-conditions.html +model-index: +- name: Falcon3-10B-Instruct + results: + - task: + type: text-generation + name: Text Generation + dataset: + name: IFEval (0-Shot) + type: HuggingFaceH4/ifeval + args: + num_few_shot: 0 + metrics: + - type: inst_level_strict_acc and prompt_level_strict_acc + value: 78.17 + name: strict accuracy + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Instruct + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: BBH (3-Shot) + type: BBH + args: + num_few_shot: 3 + metrics: + - type: acc_norm + value: 44.82 + name: normalized accuracy + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Instruct + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MATH Lvl 5 (4-Shot) + type: hendrycks/competition_math + args: + num_few_shot: 4 + metrics: + - type: exact_match + value: 25.91 + name: exact match + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Instruct + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: GPQA (0-shot) + type: Idavidrein/gpqa + args: + num_few_shot: 0 + metrics: + - type: acc_norm + value: 10.51 + name: acc_norm + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Instruct + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MuSR (0-shot) + type: TAUR-Lab/MuSR + args: + num_few_shot: 0 + metrics: + - type: acc_norm + value: 13.61 + name: acc_norm + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Instruct + name: Open LLM Leaderboard + - task: + type: text-generation + name: Text Generation + dataset: + name: MMLU-PRO (5-shot) + type: TIGER-Lab/MMLU-Pro + config: main + split: test + args: + num_few_shot: 5 + metrics: + - type: acc + value: 38.1 + name: accuracy + source: + url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=tiiuae/Falcon3-10B-Instruct + name: Open LLM Leaderboard --- ## Llamacpp imatrix Quantizations of Falcon3-10B-Instruct -Using llama.cpp release b4341 for quantization. +Using llama.cpp release b4381 for quantization. Original model: https://huggingface.co/tiiuae/Falcon3-10B-Instruct @@ -29,11 +124,14 @@ Run them in [LM Studio](https://lmstudio.ai/) <|assistant|> ``` +## What's new: + +Fix tokenizer + ## Download a file (not the whole branch) from below: | Filename | Quant type | File Size | Split | Description | | -------- | ---------- | --------- | ----- | ----------- | -| [Falcon3-10B-Instruct-f32.gguf](https://huggingface.co/bartowski/Falcon3-10B-Instruct-GGUF/blob/main/Falcon3-10B-Instruct-f32.gguf) | f32 | 41.23GB | false | Full F32 weights. | | [Falcon3-10B-Instruct-f16.gguf](https://huggingface.co/bartowski/Falcon3-10B-Instruct-GGUF/blob/main/Falcon3-10B-Instruct-f16.gguf) | f16 | 20.62GB | false | Full F16 weights. | | [Falcon3-10B-Instruct-Q8_0.gguf](https://huggingface.co/bartowski/Falcon3-10B-Instruct-GGUF/blob/main/Falcon3-10B-Instruct-Q8_0.gguf) | Q8_0 | 10.96GB | false | Extremely high quality, generally unneeded but max available quant. | | [Falcon3-10B-Instruct-Q6_K_L.gguf](https://huggingface.co/bartowski/Falcon3-10B-Instruct-GGUF/blob/main/Falcon3-10B-Instruct-Q6_K_L.gguf) | Q6_K_L | 8.65GB | false | Uses Q8_0 for embed and output weights. Very high quality, near perfect, *recommended*. |