commit cade91a9067fb0b5d064ea9fc209d245f0b70950 Author: ModelHub XC Date: Sun Jun 21 12:16:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: shaowenchen/llama-2-7b-langchain-chat-gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..e79ce6a --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +*.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..d8e545b --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +inference: false +language: + - zh + - en +license: other +model_creator: Photolens +model_link: https://huggingface.co/Photolens/llama-2-7b-langchain-chat +model_name: llama-2-7b-langchain-chat +model_type: llama +pipeline_tag: text-generation +quantized_by: shaowenchen +tasks: + - text2text-generation +tags: + - meta + - gguf + - llama + - llama-2 + - chinese + - 7b +--- + +## Provided files + +| Name | Quant method | Size | +| ------------------------------------- | ------------ | ------ | +| llama-2-7b-langchain-chat.Q2_K.gguf | Q2_K | 2.6 GB | +| llama-2-7b-langchain-chat.Q3_K.gguf | Q3_K | 3.1 GB | +| llama-2-7b-langchain-chat.Q3_K_L.gguf | Q3_K_L | 3.3 GB | +| llama-2-7b-langchain-chat.Q3_K_S.gguf | Q3_K_S | 2.7 GB | +| llama-2-7b-langchain-chat.Q4_0.gguf | Q4_0 | 3.6 GB | +| llama-2-7b-langchain-chat.Q4_1.gguf | Q4_1 | 3.9 GB | +| llama-2-7b-langchain-chat.Q4_K.gguf | Q4_K | 3.8 GB | +| llama-2-7b-langchain-chat.Q4_K_S.gguf | Q4_K_S | 3.6 GB | +| llama-2-7b-langchain-chat.Q5_0.gguf | Q5_0 | 4.3 GB | +| llama-2-7b-langchain-chat.Q5_1.gguf | Q5_1 | 4.7 GB | +| llama-2-7b-langchain-chat.Q5_K.gguf | Q5_K | 4.5 GB | +| llama-2-7b-langchain-chat.Q5_K_S.gguf | Q5_K_S | 4.3 GB | +| llama-2-7b-langchain-chat.Q6_K.gguf | Q6_K | 5.1 GB | +| llama-2-7b-langchain-chat.Q8_0.gguf | Q8_0 | 6.7 GB | +| llama-2-7b-langchain-chat.gguf | full | 13 GB | + +Usage: + +``` +docker run --rm -it -p 8000:8000 -v /path/to/models:/models -e MODEL=/models/gguf-model-name.gguf hubimage/llama-cpp-python:latest +``` + +and you can view http://localhost:8000/docs to see the swagger UI. + +## Provided images + +| Name | Quant method | Size | +| ------------------------------------------------- | ------------ | ------- | +| shaowenchen/llama-2-7b-langchain-chat-gguf:Q2_K | Q2_K | 6.72 GB | +| shaowenchen/llama-2-7b-langchain-chat-gguf:Q3_K | Q3_K | 7.64 GB | +| shaowenchen/llama-2-7b-langchain-chat-gguf:Q3_K_L | Q3_K_L | 8.27 GB | +| shaowenchen/llama-2-7b-langchain-chat-gguf:Q3_K_S | Q3_K_S | 6.97 GB | +| shaowenchen/llama-2-7b-langchain-chat-gguf:Q4_0 | Q4_0 | 8.55 GB | +| shaowenchen/llama-2-7b-langchain-chat-gguf:Q4_1 | Q4_1 | 9.41 GB | +| shaowenchen/llama-2-7b-langchain-chat-gguf:Q4_K | Q4_K | 9.17 GB | +| shaowenchen/llama-2-7b-langchain-chat-gguf:Q4_K_S | Q4_K_S | 8.72 GB | +| shaowenchen/llama-2-7b-langchain-chat-gguf:Q5_0 | Q5_0 | 10.4 GB | +| shaowenchen/llama-2-7b-langchain-chat-gguf:Q5_K | Q5_K | 10.6 GB | +| shaowenchen/llama-2-7b-langchain-chat-gguf:Q5_K_S | Q5_K_S | 10.4 GB | + +Usage: + +``` +docker run --rm -p 8000:8000 shaowenchen/llama-2-7b-langchain-chat-gguf:Q2_K +``` + +and you can view http://localhost:8000/docs to see the swagger UI. diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..8ba5d66 --- /dev/null +++ b/configuration.json @@ -0,0 +1,10 @@ +{ + "framework": "pytorch", + "task": "text-generation", + "model": { + "type": "llama2" + }, + "pipeline": { + "type": "llama-2-7b-langchain-chat-text-generation-pipe" + } +} \ No newline at end of file diff --git a/llama-2-7b-langchain-chat.Q2_K.gguf b/llama-2-7b-langchain-chat.Q2_K.gguf new file mode 100644 index 0000000..9ad2e72 --- /dev/null +++ b/llama-2-7b-langchain-chat.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63c999be294da36ee52df97364ecb05fb19347bb4571c25431989708e4d90f18 +size 2825940672 diff --git a/llama-2-7b-langchain-chat.Q3_K.gguf b/llama-2-7b-langchain-chat.Q3_K.gguf new file mode 100644 index 0000000..e720c00 --- /dev/null +++ b/llama-2-7b-langchain-chat.Q3_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afcbca6945929719f0fd3c4ea1c6c3dd87836976283928307d97eb899a976d7c +size 3298004672 diff --git a/llama-2-7b-langchain-chat.Q3_K_L.gguf b/llama-2-7b-langchain-chat.Q3_K_L.gguf new file mode 100644 index 0000000..7a49dfa --- /dev/null +++ b/llama-2-7b-langchain-chat.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94d27df5c6dba24d51e1531ef0e021a89c1f2d861ab92de387986d1b78f9ef68 +size 3597110976 diff --git a/llama-2-7b-langchain-chat.Q3_K_S.gguf b/llama-2-7b-langchain-chat.Q3_K_S.gguf new file mode 100644 index 0000000..7f8744a --- /dev/null +++ b/llama-2-7b-langchain-chat.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:599007a41fc29ed2c5260edc1665911f59a072c0212009a1e1665884c889a70e +size 2948304576 diff --git a/llama-2-7b-langchain-chat.Q4_0.gguf b/llama-2-7b-langchain-chat.Q4_0.gguf new file mode 100644 index 0000000..44f00ca --- /dev/null +++ b/llama-2-7b-langchain-chat.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c70775c9f5d5041141d01d4a9d48038964ad25bc169c7996c340293ee3da2c72 +size 3825807040 diff --git a/llama-2-7b-langchain-chat.Q4_1.gguf b/llama-2-7b-langchain-chat.Q4_1.gguf new file mode 100644 index 0000000..dc85b71 --- /dev/null +++ b/llama-2-7b-langchain-chat.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84781a2e90d22da3d681d94ee38c9b54bf5d7afc655a6357797cbacff6523f1d +size 4238749376 diff --git a/llama-2-7b-langchain-chat.Q4_K.gguf b/llama-2-7b-langchain-chat.Q4_K.gguf new file mode 100644 index 0000000..4d0ab97 --- /dev/null +++ b/llama-2-7b-langchain-chat.Q4_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:750e96efc7b6220462eabd02938ba1410c991773896acca1317e6da51b623a3e +size 4081004224 diff --git a/llama-2-7b-langchain-chat.Q4_K_S.gguf b/llama-2-7b-langchain-chat.Q4_K_S.gguf new file mode 100644 index 0000000..4824622 --- /dev/null +++ b/llama-2-7b-langchain-chat.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd52d07f82182e3748a2150abc9c17c619e650debac90b8d8649e66917736e0 +size 3856740032 diff --git a/llama-2-7b-langchain-chat.Q5_0.gguf b/llama-2-7b-langchain-chat.Q5_0.gguf new file mode 100644 index 0000000..0146633 --- /dev/null +++ b/llama-2-7b-langchain-chat.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de480a2674ca0d1656888700d2853ae39a20f0dcd21f092243393d7001c0e0f8 +size 4651691712 diff --git a/llama-2-7b-langchain-chat.Q5_1.gguf b/llama-2-7b-langchain-chat.Q5_1.gguf new file mode 100644 index 0000000..6b13929 --- /dev/null +++ b/llama-2-7b-langchain-chat.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b024062fde85c7ece0efdf38d4bd8f99b0a7eb821bb1a2544d26771834963631 +size 5064634048 diff --git a/llama-2-7b-langchain-chat.Q5_K.gguf b/llama-2-7b-langchain-chat.Q5_K.gguf new file mode 100644 index 0000000..55e6b0c --- /dev/null +++ b/llama-2-7b-langchain-chat.Q5_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00c1c6129bccc237cdb85b065a25b8826f96464c94946a4f28a11313f10f0362 +size 4783156928 diff --git a/llama-2-7b-langchain-chat.Q5_K_S.gguf b/llama-2-7b-langchain-chat.Q5_K_S.gguf new file mode 100644 index 0000000..d472259 --- /dev/null +++ b/llama-2-7b-langchain-chat.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e82d7cc1a7c64e17dd48e5eb1488b8065421c7271d47810b36da33df065b939 +size 4651691712 diff --git a/llama-2-7b-langchain-chat.Q6_K.gguf b/llama-2-7b-langchain-chat.Q6_K.gguf new file mode 100644 index 0000000..bd60f87 --- /dev/null +++ b/llama-2-7b-langchain-chat.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a625393ec6f72b60c3c0c7cd7db547b875c9becb6a8d43288036c73f8c4f7b7 +size 5529194176 diff --git a/llama-2-7b-langchain-chat.Q8_0.gguf b/llama-2-7b-langchain-chat.Q8_0.gguf new file mode 100644 index 0000000..6f7d6aa --- /dev/null +++ b/llama-2-7b-langchain-chat.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84c321bc9173ded1e14d5a4139f524c4f809eb06c9c5ebe68a8dfd4deb43dc27 +size 7161089728 diff --git a/llama-2-7b-langchain-chat.gguf b/llama-2-7b-langchain-chat.gguf new file mode 100644 index 0000000..8484aba --- /dev/null +++ b/llama-2-7b-langchain-chat.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db3dc1820636e9db9a694b4633c743216726c03067ae1c7d1d5aeaacd5ddceec +size 13478104736