commit 7a885a1f943488e475cfa6c67e270ea485545c3f Author: ModelHub XC Date: Wed Apr 22 12:32:40 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: mradermacher/HumanLlama-3.2-1B-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..da23a24 --- /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 +HumanLlama-3.2-1B.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +HumanLlama-3.2-1B.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +HumanLlama-3.2-1B.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +HumanLlama-3.2-1B.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HumanLlama-3.2-1B.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HumanLlama-3.2-1B.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HumanLlama-3.2-1B.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HumanLlama-3.2-1B.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +HumanLlama-3.2-1B.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +HumanLlama-3.2-1B.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +HumanLlama-3.2-1B.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +HumanLlama-3.2-1B.f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/HumanLlama-3.2-1B.IQ4_XS.gguf b/HumanLlama-3.2-1B.IQ4_XS.gguf new file mode 100644 index 0000000..8fa4f93 --- /dev/null +++ b/HumanLlama-3.2-1B.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d436c2aa1c9de51c6dcc210bbd60214c6336dd1dff0c4291f2c66ae2009de84 +size 748384192 diff --git a/HumanLlama-3.2-1B.Q2_K.gguf b/HumanLlama-3.2-1B.Q2_K.gguf new file mode 100644 index 0000000..3e9adef --- /dev/null +++ b/HumanLlama-3.2-1B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:deb96d8160559f7306aebf1e145c654738e9391e5564aa7b989858154cc02b98 +size 580874176 diff --git a/HumanLlama-3.2-1B.Q3_K_L.gguf b/HumanLlama-3.2-1B.Q3_K_L.gguf new file mode 100644 index 0000000..e8842fc --- /dev/null +++ b/HumanLlama-3.2-1B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c189144e50bc82ab6a8d363abf4021b9f9fc5dc394b4cb1b66945d38bfb74f6d +size 732524480 diff --git a/HumanLlama-3.2-1B.Q3_K_M.gguf b/HumanLlama-3.2-1B.Q3_K_M.gguf new file mode 100644 index 0000000..363c977 --- /dev/null +++ b/HumanLlama-3.2-1B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac32068a87a0440b968677878ebdc47be121ba45cb2f0dffc6543b78777d130a +size 690843584 diff --git a/HumanLlama-3.2-1B.Q3_K_S.gguf b/HumanLlama-3.2-1B.Q3_K_S.gguf new file mode 100644 index 0000000..c00a4e3 --- /dev/null +++ b/HumanLlama-3.2-1B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a9e6d87b5571887fe072c96b6b9650f2ecbf6892a07da3729f3cd1964a8a917 +size 641691584 diff --git a/HumanLlama-3.2-1B.Q4_K_M.gguf b/HumanLlama-3.2-1B.Q4_K_M.gguf new file mode 100644 index 0000000..9aa8f05 --- /dev/null +++ b/HumanLlama-3.2-1B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8c340c9c4ea73f20083c7c246649c14e728f560c3d869d3260f659844da4691 +size 807694272 diff --git a/HumanLlama-3.2-1B.Q4_K_S.gguf b/HumanLlama-3.2-1B.Q4_K_S.gguf new file mode 100644 index 0000000..c3a14da --- /dev/null +++ b/HumanLlama-3.2-1B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97153d0d3d3db2e98d9dd90c7a8669c610d4587133544437e059e317ce417f79 +size 775647168 diff --git a/HumanLlama-3.2-1B.Q5_K_M.gguf b/HumanLlama-3.2-1B.Q5_K_M.gguf new file mode 100644 index 0000000..c75ae6d --- /dev/null +++ b/HumanLlama-3.2-1B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ce9460cf0580e677458c08c112626f02ab240f45c2e128c2e85f290c4714091 +size 911503296 diff --git a/HumanLlama-3.2-1B.Q5_K_S.gguf b/HumanLlama-3.2-1B.Q5_K_S.gguf new file mode 100644 index 0000000..54e1c1b --- /dev/null +++ b/HumanLlama-3.2-1B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e458536cb02c950c7c1061de85b2e7138c8357ee8169b757e72bbd659533760 +size 892563392 diff --git a/HumanLlama-3.2-1B.Q6_K.gguf b/HumanLlama-3.2-1B.Q6_K.gguf new file mode 100644 index 0000000..75cabfd --- /dev/null +++ b/HumanLlama-3.2-1B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b87ca8250fc2e512451a674ebd20dc31c0453ec2cfcb312530b8b8b6c399ad5d +size 1021800384 diff --git a/HumanLlama-3.2-1B.Q8_0.gguf b/HumanLlama-3.2-1B.Q8_0.gguf new file mode 100644 index 0000000..b9ef5db --- /dev/null +++ b/HumanLlama-3.2-1B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9ca3ba54f9f6e867496aac02888081534c3de0f14dd35b8cd9ad5f4cf5f62e3 +size 1321082816 diff --git a/HumanLlama-3.2-1B.f16.gguf b/HumanLlama-3.2-1B.f16.gguf new file mode 100644 index 0000000..bb707a5 --- /dev/null +++ b/HumanLlama-3.2-1B.f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc2c417e9610436866d19da3ac5bcb080715513f56129c80461dcf873018f7c8 +size 2479595456 diff --git a/README.md b/README.md new file mode 100644 index 0000000..be0f6bb --- /dev/null +++ b/README.md @@ -0,0 +1,71 @@ +--- +base_model: nbeerbower/HumanLlama-3.2-1B +datasets: +- HumanLLMs/Human-Like-DPO-Dataset +language: +- en +library_name: transformers +license: llama3.2 +mradermacher: + readme_rev: 1 +quantized_by: mradermacher +--- +## About + + + + + + +static quants of https://huggingface.co/nbeerbower/HumanLlama-3.2-1B + + + +***For a convenient overview and download list, visit our [model page for this model](https://hf.tst.eu/model#HumanLlama-3.2-1B-GGUF).*** + +weighted/imatrix quants are available at https://huggingface.co/mradermacher/HumanLlama-3.2-1B-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/HumanLlama-3.2-1B-GGUF/resolve/main/HumanLlama-3.2-1B.Q2_K.gguf) | Q2_K | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/HumanLlama-3.2-1B-GGUF/resolve/main/HumanLlama-3.2-1B.Q3_K_S.gguf) | Q3_K_S | 0.7 | | +| [GGUF](https://huggingface.co/mradermacher/HumanLlama-3.2-1B-GGUF/resolve/main/HumanLlama-3.2-1B.Q3_K_M.gguf) | Q3_K_M | 0.8 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/HumanLlama-3.2-1B-GGUF/resolve/main/HumanLlama-3.2-1B.Q3_K_L.gguf) | Q3_K_L | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/HumanLlama-3.2-1B-GGUF/resolve/main/HumanLlama-3.2-1B.IQ4_XS.gguf) | IQ4_XS | 0.8 | | +| [GGUF](https://huggingface.co/mradermacher/HumanLlama-3.2-1B-GGUF/resolve/main/HumanLlama-3.2-1B.Q4_K_S.gguf) | Q4_K_S | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HumanLlama-3.2-1B-GGUF/resolve/main/HumanLlama-3.2-1B.Q4_K_M.gguf) | Q4_K_M | 0.9 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/HumanLlama-3.2-1B-GGUF/resolve/main/HumanLlama-3.2-1B.Q5_K_S.gguf) | Q5_K_S | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/HumanLlama-3.2-1B-GGUF/resolve/main/HumanLlama-3.2-1B.Q5_K_M.gguf) | Q5_K_M | 1.0 | | +| [GGUF](https://huggingface.co/mradermacher/HumanLlama-3.2-1B-GGUF/resolve/main/HumanLlama-3.2-1B.Q6_K.gguf) | Q6_K | 1.1 | very good quality | +| [GGUF](https://huggingface.co/mradermacher/HumanLlama-3.2-1B-GGUF/resolve/main/HumanLlama-3.2-1B.Q8_0.gguf) | Q8_0 | 1.4 | fast, best quality | +| [GGUF](https://huggingface.co/mradermacher/HumanLlama-3.2-1B-GGUF/resolve/main/HumanLlama-3.2-1B.f16.gguf) | f16 | 2.6 | 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. + +