commit 4021165798cd8e1d4b3f64257f698c191b212c64 Author: ModelHub XC Date: Tue Sep 22 23:54:20 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: merterbak/Llama-3.2-3B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..90b9e96 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,2 @@ +*.gguf filter=xet diff=xet merge=xet +Llama-3.2-3B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Llama-3.2-3B-Instruct-Q2_K.gguf b/Llama-3.2-3B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..38a2a70 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acaa33323c8f33b566d01085b2e9a4b460f00d8a4c10525670beedbaf65c8959 +size 1363935392 diff --git a/Llama-3.2-3B-Instruct-Q3_K_L.gguf b/Llama-3.2-3B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..3cacdf1 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46daec9fd6d2e03e355f352e4568e4bb8a35e88167ccae6bbf9872ef7bc2624a +size 1815347360 diff --git a/Llama-3.2-3B-Instruct-Q3_K_M.gguf b/Llama-3.2-3B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..9bb9150 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3509557e0320b28ca85678e07041a8e6523fbac232485e85d375ea1c2b924047 +size 1687158944 diff --git a/Llama-3.2-3B-Instruct-Q3_K_S.gguf b/Llama-3.2-3B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..7d7d3ed --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37eed2b99c7bb7f935bd07bdb935ea80273d511bd15b2442bccb851e19eec4f8 +size 1542848672 diff --git a/Llama-3.2-3B-Instruct-Q4_0.gguf b/Llama-3.2-3B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..335d67a --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe31f0a6465b7adbeb5e429fa1276e2f97c97783f234b5904b64f036e1acf1d3 +size 1917190304 diff --git a/Llama-3.2-3B-Instruct-Q4_1.gguf b/Llama-3.2-3B-Instruct-Q4_1.gguf new file mode 100644 index 0000000..ff164a0 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6b45136ffd89c8394bcad44674ab132b25938eaf23f3afb566b7ec72b02afb7 +size 2093351072 diff --git a/Llama-3.2-3B-Instruct-Q4_K_M.gguf b/Llama-3.2-3B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..f011826 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfb199b76738aa565e9ebfd043480852394b53af9ab489d83a2aed00567da0a3 +size 2019377312 diff --git a/Llama-3.2-3B-Instruct-Q4_K_S.gguf b/Llama-3.2-3B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..32fa663 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b35eeb432f993edf287f5062cd809cdd874ae123570ccd164c2609073602447 +size 1928200352 diff --git a/Llama-3.2-3B-Instruct-Q5_0.gguf b/Llama-3.2-3B-Instruct-Q5_0.gguf new file mode 100644 index 0000000..3254752 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc1d9b597f4b4429f6dd53bf97346933ac821f7836ce6adc361a9d791266012f +size 2269511840 diff --git a/Llama-3.2-3B-Instruct-Q5_1.gguf b/Llama-3.2-3B-Instruct-Q5_1.gguf new file mode 100644 index 0000000..240d506 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e18866b631833766531ac249739fd693f01bc5033ac3eb352c17439c6e0e89c +size 2445672608 diff --git a/Llama-3.2-3B-Instruct-Q5_K_M.gguf b/Llama-3.2-3B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..72a861e --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a2c65e14a4a02d1832906eff3aa8ed3a49f4d7943d8b805150ead93758545a7 +size 2322153632 diff --git a/Llama-3.2-3B-Instruct-Q5_K_S.gguf b/Llama-3.2-3B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..bc2330f --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77322cc32aaf1743e550cc7cc9eeb87d938a6b8d64a40efdf2e14efcd82a5a7 +size 2269511840 diff --git a/Llama-3.2-3B-Instruct-Q6_K.gguf b/Llama-3.2-3B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..3022a32 --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00f1dae7e08cc2c886a3f8c056819479305f62ec3fa656249b102f1c9428d206 +size 2643853472 diff --git a/Llama-3.2-3B-Instruct-Q8_0.gguf b/Llama-3.2-3B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..1d0d7cf --- /dev/null +++ b/Llama-3.2-3B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d29614a02eb5b7158eb5ae43a42bebcca45e861f233de9225bc5f5b0434bb242 +size 3421898912 diff --git a/Llama-3.2-3B-Instruct-f16.gguf b/Llama-3.2-3B-Instruct-f16.gguf new file mode 100644 index 0000000..82ee622 --- /dev/null +++ b/Llama-3.2-3B-Instruct-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f712db13de0498e5ab0705d0c0d835eba53b1ea01611f67734e964db21493b4 +size 6433687712 diff --git a/README.md b/README.md new file mode 100644 index 0000000..a3f2a38 --- /dev/null +++ b/README.md @@ -0,0 +1,29 @@ +--- +license: llama3.2 +language: + - en + - de + - fr + - it + - pt + - hi + - es + - th +base_model: +- meta-llama/Llama-3.2-3B-Instruct +pipeline_tag: text-generation +tags: +- llama +- llama3 +- meta +--- + +Llama 3.2 3B Instruct model available in multiple GGUF quantization formats, also stored on Xet for fast and efficient access. + +Original model: https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct + +## Model Information + +The Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out). The Llama 3.2 instruction-tuned text only models are optimized for multilingual dialogue use cases, including agentic retrieval and summarization tasks. They outperform many of the available open source and closed chat models on common industry benchmarks. + +**Model Architecture:** Llama 3.2 is an auto-regressive language model that uses an optimized transformer architecture. The tuned versions use supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety.