commit 2cae99694e538da205cde5f5a172a7b839040e8a Author: ModelHub XC Date: Sun Apr 12 17:40:59 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/IntentRL-Ambig-CoQA-4B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..6a92235 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,47 @@ +*.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 +IntentRL-Ambig-CoQA-4B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +IntentRL-Ambig-CoQA-4B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +IntentRL-Ambig-CoQA-4B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +IntentRL-Ambig-CoQA-4B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +IntentRL-Ambig-CoQA-4B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +IntentRL-Ambig-CoQA-4B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +IntentRL-Ambig-CoQA-4B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +IntentRL-Ambig-CoQA-4B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +IntentRL-Ambig-CoQA-4B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +IntentRL-Ambig-CoQA-4B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +IntentRL-Ambig-CoQA-4B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +IntentRL-Ambig-CoQA-4B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/IntentRL-Ambig-CoQA-4B.IQ4_XS.gguf b/IntentRL-Ambig-CoQA-4B.IQ4_XS.gguf new file mode 100644 index 0000000..1336df2 --- /dev/null +++ b/IntentRL-Ambig-CoQA-4B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fe116022a19dd5d51082378a572f6f6b03f745cc90f31c73ce653f4cade6b6c +size 2492948352 diff --git a/IntentRL-Ambig-CoQA-4B.Q2_K.gguf b/IntentRL-Ambig-CoQA-4B.Q2_K.gguf new file mode 100644 index 0000000..2c1214b --- /dev/null +++ b/IntentRL-Ambig-CoQA-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b0981eaa59a7a2a764967ea842e12b74cec63d16c133900570840e715a93f24 +size 1797124992 diff --git a/IntentRL-Ambig-CoQA-4B.Q3_K_L.gguf b/IntentRL-Ambig-CoQA-4B.Q3_K_L.gguf new file mode 100644 index 0000000..bfdf449 --- /dev/null +++ b/IntentRL-Ambig-CoQA-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a8a7923da4fd73f686a956eb4cb3121547e1087d8a0ae40d7581b4ff789462a +size 2406914432 diff --git a/IntentRL-Ambig-CoQA-4B.Q3_K_M.gguf b/IntentRL-Ambig-CoQA-4B.Q3_K_M.gguf new file mode 100644 index 0000000..843295c --- /dev/null +++ b/IntentRL-Ambig-CoQA-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae17e8fefcaba62e90a63affa51df11d7758fb621bdb257446e42d75175423a +size 2242746752 diff --git a/IntentRL-Ambig-CoQA-4B.Q3_K_S.gguf b/IntentRL-Ambig-CoQA-4B.Q3_K_S.gguf new file mode 100644 index 0000000..703e5f7 --- /dev/null +++ b/IntentRL-Ambig-CoQA-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18e161bc8499e983f3bdb3c17844f769ce3d6064d69800ad7f1ff2ea803c2a5a +size 2054125952 diff --git a/IntentRL-Ambig-CoQA-4B.Q4_K_M.gguf b/IntentRL-Ambig-CoQA-4B.Q4_K_M.gguf new file mode 100644 index 0000000..e219891 --- /dev/null +++ b/IntentRL-Ambig-CoQA-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95dca2590b218665b4cd885ec68c4502cd99c3bbde85a8bf8cfdfdba55ef7881 +size 2716067712 diff --git a/IntentRL-Ambig-CoQA-4B.Q4_K_S.gguf b/IntentRL-Ambig-CoQA-4B.Q4_K_S.gguf new file mode 100644 index 0000000..79679c8 --- /dev/null +++ b/IntentRL-Ambig-CoQA-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f47cd97a780e125dc73f71be19ab8204d24dfc2cb43a41a8e246d3765899c78f +size 2602096512 diff --git a/IntentRL-Ambig-CoQA-4B.Q5_K_M.gguf b/IntentRL-Ambig-CoQA-4B.Q5_K_M.gguf new file mode 100644 index 0000000..2d0f21f --- /dev/null +++ b/IntentRL-Ambig-CoQA-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a49df74f482612101972f1bfa4adc2994a341b0941bc01876a345591bcfe2dc +size 3156920192 diff --git a/IntentRL-Ambig-CoQA-4B.Q5_K_S.gguf b/IntentRL-Ambig-CoQA-4B.Q5_K_S.gguf new file mode 100644 index 0000000..ba9e24f --- /dev/null +++ b/IntentRL-Ambig-CoQA-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39dd81ddc6284a6525326141ac07dd2a260b8b4d280739c5c51b7e00d30fb321 +size 3091117952 diff --git a/IntentRL-Ambig-CoQA-4B.Q6_K.gguf b/IntentRL-Ambig-CoQA-4B.Q6_K.gguf new file mode 100644 index 0000000..0237aa1 --- /dev/null +++ b/IntentRL-Ambig-CoQA-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d1f3033124193698ed715b62f3589675304220f3ffe8e92d1852ff4dd0a4412 +size 3625325952 diff --git a/IntentRL-Ambig-CoQA-4B.Q8_0.gguf b/IntentRL-Ambig-CoQA-4B.Q8_0.gguf new file mode 100644 index 0000000..b5c70d9 --- /dev/null +++ b/IntentRL-Ambig-CoQA-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e80c8841b640c23c5160115763b75312da20d2d41ad303d69c4521eb07751024 +size 4693670272 diff --git a/IntentRL-Ambig-CoQA-4B.f16.gguf b/IntentRL-Ambig-CoQA-4B.f16.gguf new file mode 100644 index 0000000..fc25dc3 --- /dev/null +++ b/IntentRL-Ambig-CoQA-4B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64649a33caf57857621a1f6be3d77aa66283629cc261a7e4179ea8bd6fbf8325 +size 8829196672 diff --git a/README.md b/README.md new file mode 100644 index 0000000..54de115 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: irisaparina/IntentRL-Ambig-CoQA-4B +language: +- en +library_name: transformers +license: mit +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +tags: +- question-answering +- conversational-qa +- ambiguity +- reinforcement-learning +- grpo +--- +## About + + + + + + + + + +static quants of https://huggingface.co/irisaparina/IntentRL-Ambig-CoQA-4B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#IntentRL-Ambig-CoQA-4B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/IntentRL-Ambig-CoQA-4B-i1-GGUF +## 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/IntentRL-Ambig-CoQA-4B-GGUF/resolve/main/IntentRL-Ambig-CoQA-4B.Q2_K.gguf) | Q2_K | 1.9 | | +| [GGUF](https://huggingface.co/mradermacher/IntentRL-Ambig-CoQA-4B-GGUF/resolve/main/IntentRL-Ambig-CoQA-4B.Q3_K_S.gguf) | Q3_K_S | 2.2 | | +| [GGUF](https://huggingface.co/mradermacher/IntentRL-Ambig-CoQA-4B-GGUF/resolve/main/IntentRL-Ambig-CoQA-4B.Q3_K_M.gguf) | Q3_K_M | 2.3 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/IntentRL-Ambig-CoQA-4B-GGUF/resolve/main/IntentRL-Ambig-CoQA-4B.Q3_K_L.gguf) | Q3_K_L | 2.5 | | +| [GGUF](https://huggingface.co/mradermacher/IntentRL-Ambig-CoQA-4B-GGUF/resolve/main/IntentRL-Ambig-CoQA-4B.IQ4_XS.gguf) | IQ4_XS | 2.6 | | +| [GGUF](https://huggingface.co/mradermacher/IntentRL-Ambig-CoQA-4B-GGUF/resolve/main/IntentRL-Ambig-CoQA-4B.Q4_K_S.gguf) | Q4_K_S | 2.7 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/IntentRL-Ambig-CoQA-4B-GGUF/resolve/main/IntentRL-Ambig-CoQA-4B.Q4_K_M.gguf) | Q4_K_M | 2.8 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/IntentRL-Ambig-CoQA-4B-GGUF/resolve/main/IntentRL-Ambig-CoQA-4B.Q5_K_S.gguf) | Q5_K_S | 3.2 | | +| [GGUF](https://huggingface.co/mradermacher/IntentRL-Ambig-CoQA-4B-GGUF/resolve/main/IntentRL-Ambig-CoQA-4B.Q5_K_M.gguf) | Q5_K_M | 3.3 | | +| [GGUF](https://huggingface.co/mradermacher/IntentRL-Ambig-CoQA-4B-GGUF/resolve/main/IntentRL-Ambig-CoQA-4B.Q6_K.gguf) | Q6_K | 3.7 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/IntentRL-Ambig-CoQA-4B-GGUF/resolve/main/IntentRL-Ambig-CoQA-4B.Q8_0.gguf) | Q8_0 | 4.8 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/IntentRL-Ambig-CoQA-4B-GGUF/resolve/main/IntentRL-Ambig-CoQA-4B.f16.gguf) | f16 | 8.9 | 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. + +