commit 5544edeef46d76d5571513ae125a47f55fc66247 Author: ModelHub XC Date: Sun Aug 30 04:40:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/Chinda-Qwen3-4B-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/Chinda-Qwen3-4B-F32.BF16.gguf b/Chinda-Qwen3-4B-F32.BF16.gguf new file mode 100644 index 0000000..1346c94 --- /dev/null +++ b/Chinda-Qwen3-4B-F32.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb4ad7431497c724a34bd6a2cbe4d3f7f1ff2ab41ce7c9c00ca684616366a4ba +size 8051284640 diff --git a/Chinda-Qwen3-4B-F32.F16.gguf b/Chinda-Qwen3-4B-F32.F16.gguf new file mode 100644 index 0000000..35cc8bf --- /dev/null +++ b/Chinda-Qwen3-4B-F32.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:220d97ceade81293f6ef3a1f8549729aca44139c2b2c79eae05eefd21991ffb2 +size 8051284640 diff --git a/Chinda-Qwen3-4B-F32.F32.gguf b/Chinda-Qwen3-4B-F32.F32.gguf new file mode 100644 index 0000000..7616baa --- /dev/null +++ b/Chinda-Qwen3-4B-F32.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0759aa335d68c1f39aea9ccbfbab019bbc4585cf7f098be4c31002e155c9c1e5 +size 16095828640 diff --git a/Chinda-Qwen3-4B-F32.Q2_K.gguf b/Chinda-Qwen3-4B-F32.Q2_K.gguf new file mode 100644 index 0000000..2dde8cd --- /dev/null +++ b/Chinda-Qwen3-4B-F32.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e79c3faa39673f23ca7411b32c6ab19ae81e20896cea4c615604e726ddc659a4 +size 1669499040 diff --git a/Chinda-Qwen3-4B-F32.Q3_K_L.gguf b/Chinda-Qwen3-4B-F32.Q3_K_L.gguf new file mode 100644 index 0000000..42cb2c0 --- /dev/null +++ b/Chinda-Qwen3-4B-F32.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c29a36175842823a2f1cab6a30fb387003145562c8673e2bf05731007e904652 +size 2239785120 diff --git a/Chinda-Qwen3-4B-F32.Q3_K_M.gguf b/Chinda-Qwen3-4B-F32.Q3_K_M.gguf new file mode 100644 index 0000000..eec9bf2 --- /dev/null +++ b/Chinda-Qwen3-4B-F32.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce2102dd09877d251600bd4be1d1e6654f4c930dc0cfd110de25bec28c770f21 +size 2075617440 diff --git a/Chinda-Qwen3-4B-F32.Q3_K_S.gguf b/Chinda-Qwen3-4B-F32.Q3_K_S.gguf new file mode 100644 index 0000000..8b2b312 --- /dev/null +++ b/Chinda-Qwen3-4B-F32.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbd1486f22fb8bac3c273a8a4d6bf9bcd6f3e2f9f42744dd79fc02bf0f41ef36 +size 1886996640 diff --git a/Chinda-Qwen3-4B-F32.Q4_K_M.gguf b/Chinda-Qwen3-4B-F32.Q4_K_M.gguf new file mode 100644 index 0000000..a339362 --- /dev/null +++ b/Chinda-Qwen3-4B-F32.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e0769ea0aaab3fd648fce7eee3abcbb6301560bcbb934c116399b35dba99030 +size 2497280160 diff --git a/Chinda-Qwen3-4B-F32.Q4_K_S.gguf b/Chinda-Qwen3-4B-F32.Q4_K_S.gguf new file mode 100644 index 0000000..0343101 --- /dev/null +++ b/Chinda-Qwen3-4B-F32.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40416f9c686e46f0e47a0f730c2db197009cb1cb17557c59cbf0d667a5a1edb6 +size 2383308960 diff --git a/Chinda-Qwen3-4B-F32.Q5_K_M.gguf b/Chinda-Qwen3-4B-F32.Q5_K_M.gguf new file mode 100644 index 0000000..589be38 --- /dev/null +++ b/Chinda-Qwen3-4B-F32.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbd6c8a2555b7ae8c666b2b061c730ce4c4bdc4de77bbed727e7a1577a5089de +size 2889513120 diff --git a/Chinda-Qwen3-4B-F32.Q5_K_S.gguf b/Chinda-Qwen3-4B-F32.Q5_K_S.gguf new file mode 100644 index 0000000..aec82cb --- /dev/null +++ b/Chinda-Qwen3-4B-F32.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67eed718471cf96801aa53b775e8b568da2e10adfc9961da23f8cd0a56d09c75 +size 2823710880 diff --git a/Chinda-Qwen3-4B-F32.Q6_K.gguf b/Chinda-Qwen3-4B-F32.Q6_K.gguf new file mode 100644 index 0000000..8c87abc --- /dev/null +++ b/Chinda-Qwen3-4B-F32.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45366337700b719089782a02f8744b0bdcca49dfd2efbecc062b94385d591a18 +size 3306260640 diff --git a/Chinda-Qwen3-4B-F32.Q8_0.gguf b/Chinda-Qwen3-4B-F32.Q8_0.gguf new file mode 100644 index 0000000..ef85cc7 --- /dev/null +++ b/Chinda-Qwen3-4B-F32.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:563e30da1c070d51def50f2d358284c898580b3dcf00dc5362012a1fe2d1a69c +size 4280404640 diff --git a/README.md b/README.md new file mode 100644 index 0000000..47dfd5f --- /dev/null +++ b/README.md @@ -0,0 +1,43 @@ +--- +license: apache-2.0 +language: +- en +- th +base_model: +- iapp/chinda-qwen3-4b +pipeline_tag: text-generation +library_name: transformers +tags: +- text-generation-inference +--- + +# **Chinda-Qwen3-4B-F32-GGUF** + +> Chinda Opensource Thai LLM 4B is iApp Technology's cutting-edge Thai language model that brings advanced thinking capabilities to the Thai AI ecosystem. Built on the latest Qwen3-4B architecture, Chinda represents our commitment to developing sovereign AI solutions for Thailand. + +## Model Files + +| File | Size | Format | +|------|------|--------| +| Chinda-Qwen3-4B-F32.F32.gguf | 16.1 GB | 32-bit float | +| Chinda-Qwen3-4B-F32.BF16.gguf | 8.05 GB | BFloat16 | +| Chinda-Qwen3-4B-F32.F16.gguf | 8.05 GB | 16-bit float | +| Chinda-Qwen3-4B-F32.Q8_0.gguf | 4.28 GB | 8-bit quantized | +| Chinda-Qwen3-4B-F32.Q6_K.gguf | 3.31 GB | 6-bit quantized | +| Chinda-Qwen3-4B-F32.Q5_K_M.gguf | 2.89 GB | 5-bit quantized (medium) | +| Chinda-Qwen3-4B-F32.Q5_K_S.gguf | 2.82 GB | 5-bit quantized (small) | +| Chinda-Qwen3-4B-F32.Q4_K_M.gguf | 2.5 GB | 4-bit quantized (medium) | +| Chinda-Qwen3-4B-F32.Q4_K_S.gguf | 2.38 GB | 4-bit quantized (small) | +| Chinda-Qwen3-4B-F32.Q3_K_L.gguf | 2.24 GB | 3-bit quantized (large) | +| Chinda-Qwen3-4B-F32.Q3_K_M.gguf | 2.08 GB | 3-bit quantized (medium) | +| Chinda-Qwen3-4B-F32.Q3_K_S.gguf | 1.89 GB | 3-bit quantized (small) | +| Chinda-Qwen3-4B-F32.Q2_K.gguf | 1.67 GB | 2-bit quantized | + +## 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..5d0c447 --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "qwen3" +} \ 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