commit a96880a6e0f1966e4255150f6fed0de6af4e86e1 Author: ModelHub XC Date: Sun Jun 21 12:29:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: QuantFactory/llama-3-chinese-8b-instruct-v2-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..239aa46 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,49 @@ +*.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 +llama-3-chinese-8b-instruct-v2.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-chinese-8b-instruct-v2.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-chinese-8b-instruct-v2.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-chinese-8b-instruct-v2.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-chinese-8b-instruct-v2.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-chinese-8b-instruct-v2.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-chinese-8b-instruct-v2.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-chinese-8b-instruct-v2.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-chinese-8b-instruct-v2.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-chinese-8b-instruct-v2.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-chinese-8b-instruct-v2.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-chinese-8b-instruct-v2.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-chinese-8b-instruct-v2.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +llama-3-chinese-8b-instruct-v2.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..689d48c --- /dev/null +++ b/README.md @@ -0,0 +1,23 @@ +--- +library_name: transformers +base_model: hfl/llama-3-chinese-8b-instruct-v2 +language: +- en +- zh +pipeline_tag: text-generation +tags: +- llama +- conversational +--- + +# QuantFactory/llama-3-chinese-8b-instruct-v2-GGUF +This is quantized version of [hfl/llama-3-chinese-8b-instruct-v2](https://huggingface.co/hfl/llama-3-chinese-8b-instruct-v2) created using llama.cpp + + +# Model Description + +This repository contains Llama-3-Chinese-8B-Instruct-v2, which is directly tuned with 5M instruction data on Meta-Llama-3-8B-Instruct. + +Note: This is an instruction (chat) model, which can be used for conversation, QA, etc. + +Further details (performance, usage, etc.) should refer to GitHub project page: https://github.com/ymcui/Chinese-LLaMA-Alpaca-3 \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..bbeeda1 --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "text-generation", "allow_remote": true} \ No newline at end of file diff --git a/llama-3-chinese-8b-instruct-v2.Q2_K.gguf b/llama-3-chinese-8b-instruct-v2.Q2_K.gguf new file mode 100644 index 0000000..3e135ec --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e615380579aa146a76203d4b4ce1af14d3cda559e7413261fcdb30ed9ea0b5ed +size 3179131136 diff --git a/llama-3-chinese-8b-instruct-v2.Q3_K_L.gguf b/llama-3-chinese-8b-instruct-v2.Q3_K_L.gguf new file mode 100644 index 0000000..33baac2 --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14edeafcde4949fee93e97fdcf8686d22189cab0cbf975adec034d1f18285706 +size 4321956096 diff --git a/llama-3-chinese-8b-instruct-v2.Q3_K_M.gguf b/llama-3-chinese-8b-instruct-v2.Q3_K_M.gguf new file mode 100644 index 0000000..c9b2c66 --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:854dd6c3278c645ec7bfb20ba99f680f53e78e370f55d21ede49728173db6711 +size 4018917632 diff --git a/llama-3-chinese-8b-instruct-v2.Q3_K_S.gguf b/llama-3-chinese-8b-instruct-v2.Q3_K_S.gguf new file mode 100644 index 0000000..59c501a --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d9c83f2e205bab4554fc5dbb9a04a86f9b58d7bc8a3265e5aab13b6d26845de +size 3664498944 diff --git a/llama-3-chinese-8b-instruct-v2.Q4_0.gguf b/llama-3-chinese-8b-instruct-v2.Q4_0.gguf new file mode 100644 index 0000000..7b8f78a --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:330d88e75ff1e8dd7fc0e3c06ad45ce6dc6aae2b70c65bdfa2ee9901470428ab +size 4661211392 diff --git a/llama-3-chinese-8b-instruct-v2.Q4_1.gguf b/llama-3-chinese-8b-instruct-v2.Q4_1.gguf new file mode 100644 index 0000000..8f70382 --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:484143a90fde2503c754dca03e7aa8d99478bf38be83a032f04db2a92bac5b7c +size 5130252544 diff --git a/llama-3-chinese-8b-instruct-v2.Q4_K_M.gguf b/llama-3-chinese-8b-instruct-v2.Q4_K_M.gguf new file mode 100644 index 0000000..1eccdf8 --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4adffb336b39eb841740eec503046122683d18380fe58db28eb2460c668ee1e8 +size 4920733952 diff --git a/llama-3-chinese-8b-instruct-v2.Q4_K_S.gguf b/llama-3-chinese-8b-instruct-v2.Q4_K_S.gguf new file mode 100644 index 0000000..6a04e1c --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c648f65799fd4facf8302268d75034035d1f5e3d89e2c53e46994f7c088185e +size 4692668672 diff --git a/llama-3-chinese-8b-instruct-v2.Q5_0.gguf b/llama-3-chinese-8b-instruct-v2.Q5_0.gguf new file mode 100644 index 0000000..4cb938b --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5a2b6fe5b904f41fb5320e017bc43cd58c1790ff5f6514a392f792f096957be +size 5599293696 diff --git a/llama-3-chinese-8b-instruct-v2.Q5_1.gguf b/llama-3-chinese-8b-instruct-v2.Q5_1.gguf new file mode 100644 index 0000000..8ec4f4b --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0160bf22cb70ae0415c3fc05b40ecbf3a33a39a3e1a780972a2f760608e06cf +size 6068334848 diff --git a/llama-3-chinese-8b-instruct-v2.Q5_K_M.gguf b/llama-3-chinese-8b-instruct-v2.Q5_K_M.gguf new file mode 100644 index 0000000..1e8dffd --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3971cbf4377f1a23dd4b5900edf5876edb8c790a27314909050d1971de37e81e +size 5732987136 diff --git a/llama-3-chinese-8b-instruct-v2.Q5_K_S.gguf b/llama-3-chinese-8b-instruct-v2.Q5_K_S.gguf new file mode 100644 index 0000000..1915722 --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:68036178b8f7d13288294b8355493e46c48e3252805e67dd12046e54ea1eb6b0 +size 5599293696 diff --git a/llama-3-chinese-8b-instruct-v2.Q6_K.gguf b/llama-3-chinese-8b-instruct-v2.Q6_K.gguf new file mode 100644 index 0000000..cec2df0 --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46311b2c118f6cdde2dddfad4b4c054ea3a05775e7af05d866e640614184f45f +size 6596006144 diff --git a/llama-3-chinese-8b-instruct-v2.Q8_0.gguf b/llama-3-chinese-8b-instruct-v2.Q8_0.gguf new file mode 100644 index 0000000..3f29443 --- /dev/null +++ b/llama-3-chinese-8b-instruct-v2.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0424880b32876c60bc5622accee70325eec5c0518ba2f28079e45020139f13b0 +size 8540770560