commit c17ea0d85ff965f0e7bb478637aa036ee13b7f19 Author: ModelHub XC Date: Mon Oct 26 10:20:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/Hermes-3-Llama-3.2-3B-f32-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..53d7257 --- /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 +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.gguf* filter=lfs diff=lfs merge=lfs -text +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/Hermes-3-Llama-3.2-3B.BF16.gguf b/Hermes-3-Llama-3.2-3B.BF16.gguf new file mode 100644 index 0000000..5ed6e23 --- /dev/null +++ b/Hermes-3-Llama-3.2-3B.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1194684c2039573b60ad817b793ec8bc0b7d29ae98c2817a7024e1249e53ae89 +size 6433683488 diff --git a/Hermes-3-Llama-3.2-3B.F16.gguf b/Hermes-3-Llama-3.2-3B.F16.gguf new file mode 100644 index 0000000..128bcf6 --- /dev/null +++ b/Hermes-3-Llama-3.2-3B.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f8520c5189f5f8267d2ec94d5efb533a1d53a128deedde32a44863a8b807a96 +size 6433683488 diff --git a/Hermes-3-Llama-3.2-3B.F32.gguf b/Hermes-3-Llama-3.2-3B.F32.gguf new file mode 100644 index 0000000..669024c --- /dev/null +++ b/Hermes-3-Llama-3.2-3B.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18e5ad73a8bd1062562760d4808f73111e9f200b1d37f1cd0fa85d5a28c4ef93 +size 12858832928 diff --git a/Hermes-3-Llama-3.2-3B.Q2_K.gguf b/Hermes-3-Llama-3.2-3B.Q2_K.gguf new file mode 100644 index 0000000..7ed0023 --- /dev/null +++ b/Hermes-3-Llama-3.2-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfdeee603da6c06baefcc4da0e2d6dd41745079e4c00724c120548e7f08b69a5 +size 1363931168 diff --git a/Hermes-3-Llama-3.2-3B.Q3_K_L.gguf b/Hermes-3-Llama-3.2-3B.Q3_K_L.gguf new file mode 100644 index 0000000..ae2958a --- /dev/null +++ b/Hermes-3-Llama-3.2-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b7c755f0b2c6774a5efadeb25130fe28eef2b840279d77cbd1bc1e3eacb740a +size 1815343136 diff --git a/Hermes-3-Llama-3.2-3B.Q3_K_M.gguf b/Hermes-3-Llama-3.2-3B.Q3_K_M.gguf new file mode 100644 index 0000000..4bbf913 --- /dev/null +++ b/Hermes-3-Llama-3.2-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc63b69706ae89f72be68b605581bd1cc3876ceaafaa31051755a9da8a370d4d +size 1687154720 diff --git a/Hermes-3-Llama-3.2-3B.Q3_K_S.gguf b/Hermes-3-Llama-3.2-3B.Q3_K_S.gguf new file mode 100644 index 0000000..219f05c --- /dev/null +++ b/Hermes-3-Llama-3.2-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c37dfe5067928c9390e604a4e390aae514cc9853a7052c3f99ddcde2ec860219 +size 1542844448 diff --git a/Hermes-3-Llama-3.2-3B.Q4_K_M.gguf b/Hermes-3-Llama-3.2-3B.Q4_K_M.gguf new file mode 100644 index 0000000..406e0cc --- /dev/null +++ b/Hermes-3-Llama-3.2-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb4a430fe9fba24016e595445a43d45d22ca7abb84dc8d3c01b8b3983fa96c98 +size 2019373088 diff --git a/Hermes-3-Llama-3.2-3B.Q4_K_S.gguf b/Hermes-3-Llama-3.2-3B.Q4_K_S.gguf new file mode 100644 index 0000000..41730ac --- /dev/null +++ b/Hermes-3-Llama-3.2-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b1f961cd8a3ab454fe9807b557a224792be78967ad3933923de4b3201fa1b6c +size 1928196128 diff --git a/Hermes-3-Llama-3.2-3B.Q5_K_M.gguf b/Hermes-3-Llama-3.2-3B.Q5_K_M.gguf new file mode 100644 index 0000000..9544f31 --- /dev/null +++ b/Hermes-3-Llama-3.2-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7233a19b28bc5401c0a1f072ab368fbd5ef3856f7ef91964f2a7e7dc8c7109c1 +size 2322149408 diff --git a/Hermes-3-Llama-3.2-3B.Q5_K_S.gguf b/Hermes-3-Llama-3.2-3B.Q5_K_S.gguf new file mode 100644 index 0000000..1fbeb1a --- /dev/null +++ b/Hermes-3-Llama-3.2-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8eff5e88ccc1a0d9a7cffa4c939cdffe63dd068df0c32632084dbdac5c4865f9 +size 2269507616 diff --git a/Hermes-3-Llama-3.2-3B.Q6_K.gguf b/Hermes-3-Llama-3.2-3B.Q6_K.gguf new file mode 100644 index 0000000..650648a --- /dev/null +++ b/Hermes-3-Llama-3.2-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:045539d959d7b0536b66f1b147d49a6af6ecf91ab9e260ec9cb8f78905b4f2a0 +size 2643849248 diff --git a/Hermes-3-Llama-3.2-3B.Q8_0.gguf b/Hermes-3-Llama-3.2-3B.Q8_0.gguf new file mode 100644 index 0000000..6dc128e --- /dev/null +++ b/Hermes-3-Llama-3.2-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b78df996b02de04054e30e0482edb23ad06675cb293c19c67c36cb3405d6612 +size 3421894688 diff --git a/README.md b/README.md new file mode 100644 index 0000000..b96cf6f --- /dev/null +++ b/README.md @@ -0,0 +1,45 @@ +--- +license: apache-2.0 +base_model: +- NousResearch/Hermes-3-Llama-3.2-3B +language: +- en +pipeline_tag: text-generation +library_name: transformers +tags: +- text-generation-inference +- SOTA +--- + +# **Hermes-3-Llama-3.2-3B-f32-GGUF** + +> Hermes 3 - Llama-3.2 3B by Nous Research is a compact yet powerful generalist language model fine-tuned from the Llama-3.2 3B foundation, designed to deliver advanced agentic capabilities, improved roleplaying, complex reasoning, and coherent multi-turn conversations with long context understanding. It offers powerful user steering and control, supports structured prompting with ChatML format, and enables function calling and JSON output for dynamic interaction and automation. + +> Trained on high-performance GPU infrastructure, Hermes 3 excels in problem-solving, dialogue, and code generation tasks, demonstrating competitive benchmark scores across GPT4All, AGIEval, and BigBench. This model is optimized for efficiency, supports 4-bit quantization for deployment, and is ideal for building sophisticated AI assistants with controllable and natural user interactions. + +## Model Files + +| Model File name | Size | QuantType | +|---|---|---| +| Hermes-3-Llama-3.2-3B.BF16.gguf | 6.43 GB | BF16 | +| Hermes-3-Llama-3.2-3B.F16.gguf | 6.43 GB | F16 | +| Hermes-3-Llama-3.2-3B.F32.gguf | 12.9 GB | F32 | +| Hermes-3-Llama-3.2-3B.Q2_K.gguf | 1.36 GB | Q2_K | +| Hermes-3-Llama-3.2-3B.Q3_K_L.gguf | 1.82 GB | Q3_K_L | +| Hermes-3-Llama-3.2-3B.Q3_K_M.gguf | 1.69 GB | Q3_K_M | +| Hermes-3-Llama-3.2-3B.Q3_K_S.gguf | 1.54 GB | Q3_K_S | +| Hermes-3-Llama-3.2-3B.Q4_K_M.gguf | 2.02 GB | Q4_K_M | +| Hermes-3-Llama-3.2-3B.Q4_K_S.gguf | 1.93 GB | Q4_K_S | +| Hermes-3-Llama-3.2-3B.Q5_K_M.gguf | 2.32 GB | Q5_K_M | +| Hermes-3-Llama-3.2-3B.Q5_K_S.gguf | 2.27 GB | Q5_K_S | +| Hermes-3-Llama-3.2-3B.Q6_K.gguf | 2.64 GB | Q6_K | +| Hermes-3-Llama-3.2-3B.Q8_0.gguf | 3.42 GB | Q8_0 | + +## Quants Usage + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +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) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a4ba21b --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "llama" +} \ 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