commit 915ee397abea00dae36d621d364117d835a20f6a Author: ModelHub XC Date: Fri Jun 19 13:58:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/Omega-Qwen2.5-Coder-3B-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/Omega-Qwen2.5-Coder-3B.BF16.gguf b/Omega-Qwen2.5-Coder-3B.BF16.gguf new file mode 100644 index 0000000..5abe4da --- /dev/null +++ b/Omega-Qwen2.5-Coder-3B.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01bc008e1dc356e58e5579efc4201a64f9402319d3ec71577d3ac2bea056f0df +size 6178316544 diff --git a/Omega-Qwen2.5-Coder-3B.F16.gguf b/Omega-Qwen2.5-Coder-3B.F16.gguf new file mode 100644 index 0000000..858eb09 --- /dev/null +++ b/Omega-Qwen2.5-Coder-3B.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4138be6f012cf17f43e864c9e1ac1dcace83269d2cd0e58bb6e59f560f93f62 +size 6178316544 diff --git a/Omega-Qwen2.5-Coder-3B.F32.gguf b/Omega-Qwen2.5-Coder-3B.F32.gguf new file mode 100644 index 0000000..5e92229 --- /dev/null +++ b/Omega-Qwen2.5-Coder-3B.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c3d04c8ef639599c5816f552a42830de73c1741f7f91ca9e60bef64e334feda +size 12349710592 diff --git a/Omega-Qwen2.5-Coder-3B.Q2_K.gguf b/Omega-Qwen2.5-Coder-3B.Q2_K.gguf new file mode 100644 index 0000000..fc2381f --- /dev/null +++ b/Omega-Qwen2.5-Coder-3B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83685ea3087b51d740381d9365993e0537c5515d943270875d9102780b68de76 +size 1274755328 diff --git a/Omega-Qwen2.5-Coder-3B.Q3_K_L.gguf b/Omega-Qwen2.5-Coder-3B.Q3_K_L.gguf new file mode 100644 index 0000000..382fcd0 --- /dev/null +++ b/Omega-Qwen2.5-Coder-3B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ca4edb366cc8e5eca601dcfb322c14aebbe13f584d04b0eede358407fc45af5 +size 1707391232 diff --git a/Omega-Qwen2.5-Coder-3B.Q3_K_M.gguf b/Omega-Qwen2.5-Coder-3B.Q3_K_M.gguf new file mode 100644 index 0000000..04388ee --- /dev/null +++ b/Omega-Qwen2.5-Coder-3B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b55cee1451ec76cc0f149480b15f90cef30f851da7eeab19a0db4a1d81efa7 +size 1590475008 diff --git a/Omega-Qwen2.5-Coder-3B.Q3_K_S.gguf b/Omega-Qwen2.5-Coder-3B.Q3_K_S.gguf new file mode 100644 index 0000000..0b8380c --- /dev/null +++ b/Omega-Qwen2.5-Coder-3B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74ce55c8d02dcbc090f340dfb68432e0ccf9df9330f33af527e7b82163e031ea +size 1454356736 diff --git a/Omega-Qwen2.5-Coder-3B.Q4_K_M.gguf b/Omega-Qwen2.5-Coder-3B.Q4_K_M.gguf new file mode 100644 index 0000000..000f7b7 --- /dev/null +++ b/Omega-Qwen2.5-Coder-3B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5134379ae8d081a7c2b21b2ca59d8cb4c01f3c3f0330b2f171a323fad8c33640 +size 1929902336 diff --git a/Omega-Qwen2.5-Coder-3B.Q4_K_S.gguf b/Omega-Qwen2.5-Coder-3B.Q4_K_S.gguf new file mode 100644 index 0000000..8f3b5ef --- /dev/null +++ b/Omega-Qwen2.5-Coder-3B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:022e900780d34a6d2c308fd1a087e90b6b91c59a76268e9b81606fb65e828488 +size 1834383616 diff --git a/Omega-Qwen2.5-Coder-3B.Q5_K_M.gguf b/Omega-Qwen2.5-Coder-3B.Q5_K_M.gguf new file mode 100644 index 0000000..dfd3ad8 --- /dev/null +++ b/Omega-Qwen2.5-Coder-3B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e11248caed0235184558532591c81bea65f856bf659d55ce4b04661e826b3dd6 +size 2224814336 diff --git a/Omega-Qwen2.5-Coder-3B.Q5_K_S.gguf b/Omega-Qwen2.5-Coder-3B.Q5_K_S.gguf new file mode 100644 index 0000000..31626ea --- /dev/null +++ b/Omega-Qwen2.5-Coder-3B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d3ce36150d45817daefc3a74cccde52d8a6ba789418f8eb8720fa541f698842 +size 2169665792 diff --git a/Omega-Qwen2.5-Coder-3B.Q6_K.gguf b/Omega-Qwen2.5-Coder-3B.Q6_K.gguf new file mode 100644 index 0000000..608b329 --- /dev/null +++ b/Omega-Qwen2.5-Coder-3B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8410c5604733facb72f652d4fc8cdbac4081dbe949cff9881706f2c8820cf61d +size 2538158336 diff --git a/Omega-Qwen2.5-Coder-3B.Q8_0.gguf b/Omega-Qwen2.5-Coder-3B.Q8_0.gguf new file mode 100644 index 0000000..5e39ac9 --- /dev/null +++ b/Omega-Qwen2.5-Coder-3B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a36d36919c8f8d7bf1fe2586239b0453c304f81745debdff0cc8b5ca6fbe0469 +size 3285475584 diff --git a/README.md b/README.md new file mode 100644 index 0000000..5ee6541 --- /dev/null +++ b/README.md @@ -0,0 +1,43 @@ +--- +license: apache-2.0 +tags: +- 'Thinking: Disabled' +- text-generation-inference +language: +- en +base_model: +- prithivMLmods/Omega-Qwen2.5-Coder-3B +pipeline_tag: text-generation +library_name: transformers +--- + +# **Omega-Qwen2.5-Coder-3B-GGUF** + +> Omega-Qwen2.5-Coder-3B is a compact and high-efficiency code-focused model fine-tuned on Qwen2.5-Coder-3B-Instruct, using the symbolic-rich Open-Omega-Forge-1M dataset. Designed specifically for hard-coded tasks and deterministic computation, this model runs in a "thinking-disabled" mode—delivering precise, structured outputs with minimal hallucination, making it ideal for rigorous coding workflows and embedded logic applications. + +## Model Files + +| File Name | Size | Precision | +|-----------|------|-----------| +| Omega-Qwen2.5-Coder-3B.BF16.gguf | 6.18 GB | BF16 | +| Omega-Qwen2.5-Coder-3B.F16.gguf | 6.18 GB | F16 | +| Omega-Qwen2.5-Coder-3B.F32.gguf | 12.3 GB | F32 | +| Omega-Qwen2.5-Coder-3B.Q2_K.gguf | 1.27 GB | Q2_K | +| Omega-Qwen2.5-Coder-3B.Q3_K_L.gguf | 1.71 GB | Q3_K_L | +| Omega-Qwen2.5-Coder-3B.Q3_K_M.gguf | 1.59 GB | Q3_K_M | +| Omega-Qwen2.5-Coder-3B.Q3_K_S.gguf | 1.45 GB | Q3_K_S | +| Omega-Qwen2.5-Coder-3B.Q4_K_M.gguf | 1.93 GB | Q4_K_M | +| Omega-Qwen2.5-Coder-3B.Q4_K_S.gguf | 1.83 GB | Q4_K_S | +| Omega-Qwen2.5-Coder-3B.Q5_K_M.gguf | 2.22 GB | Q5_K_M | +| Omega-Qwen2.5-Coder-3B.Q5_K_S.gguf | 2.17 GB | Q5_K_S | +| Omega-Qwen2.5-Coder-3B.Q6_K.gguf | 2.54 GB | Q6_K | +| Omega-Qwen2.5-Coder-3B.Q8_0.gguf | 3.29 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..5ca493c --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "qwen2" +} \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..159097f --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "others", "allow_remote": true} \ No newline at end of file