commit 8533d06be173443a2bd9e6097305df8b984af368 Author: ModelHub XC Date: Mon Jul 20 03:00:10 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/Qwen2VL-2B-Instruct-fire-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..b57341a --- /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 +Qwen2VL-2B-Instruct-fire.mmproj-f16.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-2B-Instruct-fire.mmproj-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-2B-Instruct-fire.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-2B-Instruct-fire.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-2B-Instruct-fire.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-2B-Instruct-fire.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-2B-Instruct-fire.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-2B-Instruct-fire.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-2B-Instruct-fire.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-2B-Instruct-fire.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-2B-Instruct-fire.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-2B-Instruct-fire.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-2B-Instruct-fire.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Qwen2VL-2B-Instruct-fire.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Qwen2VL-2B-Instruct-fire.IQ4_XS.gguf b/Qwen2VL-2B-Instruct-fire.IQ4_XS.gguf new file mode 100644 index 0000000..5c57158 --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3c1efddef22235de098ef22059404c23c02e0df65b23dde3c07140af760c8e0 +size 902181920 diff --git a/Qwen2VL-2B-Instruct-fire.Q2_K.gguf b/Qwen2VL-2B-Instruct-fire.Q2_K.gguf new file mode 100644 index 0000000..54d76c9 --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0e98e906dce00dd576ea44b78a0b96cbbcfec67ab8da51814d720d8f4ea4ffd +size 676303904 diff --git a/Qwen2VL-2B-Instruct-fire.Q3_K_L.gguf b/Qwen2VL-2B-Instruct-fire.Q3_K_L.gguf new file mode 100644 index 0000000..147208e --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03b916497e671513049dbd6a7de9a27aa09076bc158c409bca6700cde0c11a1d +size 880161824 diff --git a/Qwen2VL-2B-Instruct-fire.Q3_K_M.gguf b/Qwen2VL-2B-Instruct-fire.Q3_K_M.gguf new file mode 100644 index 0000000..56b5243 --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24db7e416a13e1c6d63e444ecb7a5cddb854a491cba7b25e994db5f83b44d528 +size 824177696 diff --git a/Qwen2VL-2B-Instruct-fire.Q3_K_S.gguf b/Qwen2VL-2B-Instruct-fire.Q3_K_S.gguf new file mode 100644 index 0000000..54d8dd8 --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7322b91f4b8586511c3b5931b598e0a5df88acc5f0e3ff396f4b0782859c0010 +size 760943648 diff --git a/Qwen2VL-2B-Instruct-fire.Q4_K_M.gguf b/Qwen2VL-2B-Instruct-fire.Q4_K_M.gguf new file mode 100644 index 0000000..9a5e244 --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c946b7327a3eec4b86d457c6d1e60d4c632b43b54c5b5a0c2ef60cc39cf65830 +size 986047520 diff --git a/Qwen2VL-2B-Instruct-fire.Q4_K_S.gguf b/Qwen2VL-2B-Instruct-fire.Q4_K_S.gguf new file mode 100644 index 0000000..5356a52 --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c098d768fb041c8366faffe61d8ccb6482b8589909049191db8893bc91e403c +size 940311584 diff --git a/Qwen2VL-2B-Instruct-fire.Q5_K_M.gguf b/Qwen2VL-2B-Instruct-fire.Q5_K_M.gguf new file mode 100644 index 0000000..562a6b3 --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:643f2d9e554479ff22777d7a4b0f5a614e575bd81876f807a2f0321ce964e924 +size 1125049376 diff --git a/Qwen2VL-2B-Instruct-fire.Q5_K_S.gguf b/Qwen2VL-2B-Instruct-fire.Q5_K_S.gguf new file mode 100644 index 0000000..8f7b234 --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f8867bc3185a776bcb92a31dbf37b5b06051d4ebafffa8ebcab27779d0c3233 +size 1098728480 diff --git a/Qwen2VL-2B-Instruct-fire.Q6_K.gguf b/Qwen2VL-2B-Instruct-fire.Q6_K.gguf new file mode 100644 index 0000000..e813852 --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5e42ae5afd7bd70280838dedc4c061a25718665aeedc87dd7ee7216d18ac53b +size 1272738848 diff --git a/Qwen2VL-2B-Instruct-fire.Q8_0.gguf b/Qwen2VL-2B-Instruct-fire.Q8_0.gguf new file mode 100644 index 0000000..924edc3 --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f14653a3ba5205f6c0694a150570c7158b4e76c1039076ca71c814f0ba14d9e +size 1646572064 diff --git a/Qwen2VL-2B-Instruct-fire.f16.gguf b/Qwen2VL-2B-Instruct-fire.f16.gguf new file mode 100644 index 0000000..0eab9aa --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35454b4f7c4e499a5ee406598227b4cd4e95c45a0cef5fa4cd1576794f3b6552 +size 3093668384 diff --git a/Qwen2VL-2B-Instruct-fire.mmproj-Q8_0.gguf b/Qwen2VL-2B-Instruct-fire.mmproj-Q8_0.gguf new file mode 100644 index 0000000..d91784f --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.mmproj-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79939518e62ad6dcb3624da5e129c777ddcdda209f2ce36ddc70aa2e4dfe1ce5 +size 712894048 diff --git a/Qwen2VL-2B-Instruct-fire.mmproj-f16.gguf b/Qwen2VL-2B-Instruct-fire.mmproj-f16.gguf new file mode 100644 index 0000000..52db417 --- /dev/null +++ b/Qwen2VL-2B-Instruct-fire.mmproj-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:10c28350653014b4bedea5874b5806b8aabce54fb245ce2df006c323f555ef88 +size 1331656288 diff --git a/README.md b/README.md new file mode 100644 index 0000000..e2a44ef --- /dev/null +++ b/README.md @@ -0,0 +1,74 @@ +--- +base_model: gaoqie/Qwen2VL-2B-Instruct-fire +language: +- zh +library_name: transformers +license: apache-2.0 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + + + + +static quants of https://huggingface.co/gaoqie/Qwen2VL-2B-Instruct-fire + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#Qwen2VL-2B-Instruct-fire-GGUF).*** + +weighted/imatrix quants seem not to be available (by me) at this time. If they do not show up a week or so after the static ones, I have probably not planned for them. Feel free to request them by opening a Community Discussion. +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.Q2_K.gguf) | Q2_K | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.8 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.Q3_K_S.gguf) | Q3_K_S | 0.9 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.Q3_K_M.gguf) | Q3_K_M | 0.9 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.Q3_K_L.gguf) | Q3_K_L | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.IQ4_XS.gguf) | IQ4_XS | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.Q4_K_S.gguf) | Q4_K_S | 1.0 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.Q4_K_M.gguf) | Q4_K_M | 1.1 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.Q5_K_S.gguf) | Q5_K_S | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.Q5_K_M.gguf) | Q5_K_M | 1.2 | | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.Q6_K.gguf) | Q6_K | 1.4 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.mmproj-f16.gguf) | mmproj-f16 | 1.4 | multi-modal supplement | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.Q8_0.gguf) | Q8_0 | 1.7 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/Qwen2VL-2B-Instruct-fire-GGUF/resolve/main/Qwen2VL-2B-Instruct-fire.f16.gguf) | f16 | 3.2 | 16 bpw, overkill | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. + +