commit 6a4e2f98de141f5342f267cc1699936990cd5ae6 Author: ModelHub XC Date: Sat May 16 01:42:29 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: qwp4w3hyb/Llama-3-8B-Instruct-Coder-v2-iMat-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..47e3db1 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,55 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +imat-f16-gmerged.dat filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-f16.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-8b-instruct-coder-v2-imat-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..6348c9e --- /dev/null +++ b/README.md @@ -0,0 +1,52 @@ +--- +language: +- en +license: apache-2.0 +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- trl +- sft +- gguf +- imatrix +- importance matrix +base_model: rombodawg/Llama-3-8B-Instruct-Coder-v2 +--- + +# Quant Infos + +- Quantized with recent bpe pre-tokenizer fixes https://github.com/ggerganov/llama.cpp/pull/6920 +- quants done with an importance matrix for improved quantization loss +- 0, K & IQ quants in basically all variants from Q8 down to IQ1_S +- Quantized with [llama.cpp](https://github.com/ggerganov/llama.cpp) commit [04976db7a819fcf8bfefbfc09a3344210b79dd27](https://github.com/ggerganov/llama.cpp/commit/04976db7a819fcf8bfefbfc09a3344210b79dd27) (master from 2024-05-07) +- Imatrtix generated with [this](https://github.com/ggerganov/llama.cpp/discussions/5263#discussioncomment-8395384) dataset. + ``` + ./imatrix -c 512 -m $model_name-f16.gguf -f $llama_cpp_path/groups_merged.txt -o $out_path/imat-f16-gmerged.dat + ``` + +# Original Model Card +Llama-3-8B-Instruct-Coder-v2 + +![image/jpeg](https://cdn-uploads.huggingface.co/production/uploads/642cc1c253e76b4c2286c58e/0O4cIuv3wNbY68-FP7tak.jpeg) +_________________________________________________________________________ +How is this model diffrent from rombodawg/Llama-3-8B-Instruct-Coder? Well the first model was trained on a dataset that had some major flaws that I originally had missed, with version 2 all of those flaws are fixed, and the model is fully retrained so it performs much better than the previous iteration. +_________________________________________________________________________ +This model is llama-3-8b-instruct from Meta (uploaded by unsloth) trained on the full 150k Code Feedback Filtered Instruction dataset. You can find that dataset linked below. This AI model was trained with the new Qalore method developed by my good friend on Discord and fellow Replete-AI worker walmartbag. + +The Qalore method uses Qlora training along with the methods from Galore for additional reductions in VRAM allowing for llama-3-8b to be loaded on 14.5 GB of VRAM. This allowed this training to be completed on an RTX A5000 24GB in 50 hours for less than $15. + +Dataset used for training this model: + +- https://huggingface.co/datasets/Replete-AI/CodeFeedback-Filtered-Instruction-Simplified-Pairs + +Qalore notebook for training: + +- https://colab.research.google.com/drive/1bX4BsjLcdNJnoAf7lGXmWOgaY8yekg8p?usp=sharing + +Quantizations for easier inference: + +- https://huggingface.co/bartowski/Llama-3-8B-Instruct-Coder-v2-GGUF + +- https://huggingface.co/bartowski/Llama-3-8B-Instruct-Coder-v2-exl2 \ No newline at end of file diff --git a/imat-f16-gmerged.dat b/imat-f16-gmerged.dat new file mode 100644 index 0000000..5ebec6e --- /dev/null +++ b/imat-f16-gmerged.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:380482e799aaeed74d48d70fe8e53796c92c6f78d5b9e2c9ee6fcfcd6003c023 +size 4988185 diff --git a/llama-3-8b-instruct-coder-v2-f16.gguf b/llama-3-8b-instruct-coder-v2-f16.gguf new file mode 100644 index 0000000..9b9d132 --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45667d91e0f038741ba8893e3469d83964cf90d83d66d1253fab87d723a7466a +size 16068890912 diff --git a/llama-3-8b-instruct-coder-v2-imat-IQ1_S.gguf b/llama-3-8b-instruct-coder-v2-imat-IQ1_S.gguf new file mode 100644 index 0000000..7ea5fb1 --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73edcd2abbf18b4391f7fd870d3af36a3648cc114180049d89fc51eed69de6c0 +size 2019627648 diff --git a/llama-3-8b-instruct-coder-v2-imat-IQ2_M.gguf b/llama-3-8b-instruct-coder-v2-imat-IQ2_M.gguf new file mode 100644 index 0000000..3e69353 --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5a1fa82b5be0c23b7764b0a721369825bd6db030d0c46d94f83d9cfc1c64104 +size 2948280960 diff --git a/llama-3-8b-instruct-coder-v2-imat-IQ2_S.gguf b/llama-3-8b-instruct-coder-v2-imat-IQ2_S.gguf new file mode 100644 index 0000000..39d488a --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0930c3c20b34dc64fac02c88515fdd3a6f631bfa27e0f25dc676d858f63e430d +size 2758488704 diff --git a/llama-3-8b-instruct-coder-v2-imat-IQ2_XS.gguf b/llama-3-8b-instruct-coder-v2-imat-IQ2_XS.gguf new file mode 100644 index 0000000..1a2e641 --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a245ce9dfad3b74298a50b58d39f8d12a7bb84927d9a884bb4a901b093564f8 +size 2605781632 diff --git a/llama-3-8b-instruct-coder-v2-imat-IQ2_XXS.gguf b/llama-3-8b-instruct-coder-v2-imat-IQ2_XXS.gguf new file mode 100644 index 0000000..b17991f --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f24467deda5a6aebca5d31005b6e1ca228fd2d7ca10af7eb6fb48f1ecc29b819 +size 2399212160 diff --git a/llama-3-8b-instruct-coder-v2-imat-IQ3_M.gguf b/llama-3-8b-instruct-coder-v2-imat-IQ3_M.gguf new file mode 100644 index 0000000..24a0f5c --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c533453a52c0b59f5d7911e0f9ec2996f0b3103a8057e0d77ace64c322203e4 +size 3784823424 diff --git a/llama-3-8b-instruct-coder-v2-imat-IQ3_S.gguf b/llama-3-8b-instruct-coder-v2-imat-IQ3_S.gguf new file mode 100644 index 0000000..3a38630 --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5328b084f313aa505fa5aa3591c1cffcd3684d18b2c162ff3cf735823e862e99 +size 3682325120 diff --git a/llama-3-8b-instruct-coder-v2-imat-IQ3_XS.gguf b/llama-3-8b-instruct-coder-v2-imat-IQ3_XS.gguf new file mode 100644 index 0000000..8e0a5f8 --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16f75fc721478bfadc262b70c1dc3a81a9c6995422578419eae05d06f066d185 +size 3518747264 diff --git a/llama-3-8b-instruct-coder-v2-imat-IQ3_XXS.gguf b/llama-3-8b-instruct-coder-v2-imat-IQ3_XXS.gguf new file mode 100644 index 0000000..dd84ba0 --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa69e05323159cccbc9e47f5114853566aece40165e81268220cef70084ab048 +size 3274912384 diff --git a/llama-3-8b-instruct-coder-v2-imat-IQ4_NL.gguf b/llama-3-8b-instruct-coder-v2-imat-IQ4_NL.gguf new file mode 100644 index 0000000..05413b2 --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea1b6ae810e994b6bfc6f186c7bf42a4dce01108092ad28e4866ac1653ae90b +size 4677988992 diff --git a/llama-3-8b-instruct-coder-v2-imat-IQ4_XS.gguf b/llama-3-8b-instruct-coder-v2-imat-IQ4_XS.gguf new file mode 100644 index 0000000..1d4351d --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30cb11611c9be4f476237e2677d63bbadf5fc5615132773ac229f5133a4be25d +size 4447662720 diff --git a/llama-3-8b-instruct-coder-v2-imat-Q4_0.gguf b/llama-3-8b-instruct-coder-v2-imat-Q4_0.gguf new file mode 100644 index 0000000..84fea8a --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3df55e82c4a87ed44dfdff6a7125f99568d1a85094c720de91d375544f14e16 +size 4675891840 diff --git a/llama-3-8b-instruct-coder-v2-imat-Q4_K_M.gguf b/llama-3-8b-instruct-coder-v2-imat-Q4_K_M.gguf new file mode 100644 index 0000000..81fcfe6 --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5c992be83ba7bae01cd8c992d0cd426638226ff32c8bf02d1a4f4f5b9ecddee +size 4920734336 diff --git a/llama-3-8b-instruct-coder-v2-imat-Q4_K_S.gguf b/llama-3-8b-instruct-coder-v2-imat-Q4_K_S.gguf new file mode 100644 index 0000000..6bb8d23 --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74a9d0a6b3a0923360eb8711e7da47c47e956809e5f29157b8b8d117427c7c1e +size 4692669056 diff --git a/llama-3-8b-instruct-coder-v2-imat-Q5_K_M.gguf b/llama-3-8b-instruct-coder-v2-imat-Q5_K_M.gguf new file mode 100644 index 0000000..5fd52b8 --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e49c74fa5162c03796c2c8ef0f739d989bf8e3e63d107450f6400b2f4dd9e65 +size 5732987520 diff --git a/llama-3-8b-instruct-coder-v2-imat-Q5_K_S.gguf b/llama-3-8b-instruct-coder-v2-imat-Q5_K_S.gguf new file mode 100644 index 0000000..733dc6d --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d9f949737bd447d4dbccbf719bfc509d3e82d4f81c54665371b1530c482887c +size 5599294080 diff --git a/llama-3-8b-instruct-coder-v2-imat-Q6_K.gguf b/llama-3-8b-instruct-coder-v2-imat-Q6_K.gguf new file mode 100644 index 0000000..4b7b5b5 --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6af469b2ca85067a4e45932ace670f57bc577375c7af2e2557a89abbf3e4eeb7 +size 6596006528 diff --git a/llama-3-8b-instruct-coder-v2-imat-Q8_0.gguf b/llama-3-8b-instruct-coder-v2-imat-Q8_0.gguf new file mode 100644 index 0000000..4561498 --- /dev/null +++ b/llama-3-8b-instruct-coder-v2-imat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0b1e5df82a568385c38708134fbd5e349612d7aed7260bfe10742f9e9a8eebb +size 8540770944