commit 2ca7688cc8eb9f5cfa606e03cd8fb9c2f9cccde4 Author: ModelHub XC Date: Tue Sep 22 06:11:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/Spiral-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/README.md b/README.md new file mode 100644 index 0000000..e55f9f0 --- /dev/null +++ b/README.md @@ -0,0 +1,44 @@ +--- +license: apache-2.0 +base_model: +- spiral-rl/Spiral-Qwen3-4B +library_name: transformers +language: +- en +pipeline_tag: text-generation +tags: +- text-generation-inference +- spiral +- rl +--- + +# **Spiral-Qwen3-4B-F32-GGUF** + +> SPIRAL employs an actor-learner architecture for scalable self-play training. Parallel actors sample trajectories from a diverse set of games using vectorized environments. A single policy $\pi_t$ plays both roles, generating zero-sum, sparse reward game trajectories. The centralized learner processes these trajectories using Role-conditioned Advantage Estimation (RAE) to compute separate advantages, $A_0(s,a)$ and $A_1(s,a)$, for each role. These are then used for on-policy reinforcement learning updates. + +# Model Files + +| File | Size | Format | +|------|------|--------| +| Spiral-Qwen3-4B.F32.gguf | 16.1 GB | 32-bit float | +| Spiral-Qwen3-4B.BF16.gguf | 8.05 GB | BFloat16 | +| Spiral-Qwen3-4B.F16.gguf | 8.05 GB | 16-bit float | +| Spiral-Qwen3-4B.Q8_0.gguf | 4.28 GB | 8-bit quantized | +| Spiral-Qwen3-4B.Q6_K.gguf | 3.31 GB | 6-bit quantized | +| Spiral-Qwen3-4B.Q5_K_M.gguf | 2.89 GB | 5-bit quantized (medium) | +| Spiral-Qwen3-4B.Q5_K_S.gguf | 2.82 GB | 5-bit quantized (small) | +| Spiral-Qwen3-4B.Q4_K_M.gguf | 2.5 GB | 4-bit quantized (medium) | +| Spiral-Qwen3-4B.Q4_K_S.gguf | 2.38 GB | 4-bit quantized (small) | +| Spiral-Qwen3-4B.Q3_K_L.gguf | 2.24 GB | 3-bit quantized (large) | +| Spiral-Qwen3-4B.Q3_K_M.gguf | 2.08 GB | 3-bit quantized (medium) | +| Spiral-Qwen3-4B.Q3_K_S.gguf | 1.89 GB | 3-bit quantized (small) | +| Spiral-Qwen3-4B.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/Spiral-Qwen3-4B.BF16.gguf b/Spiral-Qwen3-4B.BF16.gguf new file mode 100644 index 0000000..7b24966 --- /dev/null +++ b/Spiral-Qwen3-4B.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:557a5bc21886e9a6453f9739e67699078dc9c91dbfa7a5a2399308eda6d190cb +size 8051284640 diff --git a/Spiral-Qwen3-4B.F16.gguf b/Spiral-Qwen3-4B.F16.gguf new file mode 100644 index 0000000..371957a --- /dev/null +++ b/Spiral-Qwen3-4B.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04fb8cd2e9ae148498b23d95c63b90418d42a5f0e3fd154c8d4507d72ec226bf +size 8051284640 diff --git a/Spiral-Qwen3-4B.F32.gguf b/Spiral-Qwen3-4B.F32.gguf new file mode 100644 index 0000000..da34532 --- /dev/null +++ b/Spiral-Qwen3-4B.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d470eba0e7cab1e17103e5de1464efb6e469d9599d39eeb1f10e4174d8515078 +size 16095828640 diff --git a/Spiral-Qwen3-4B.Q2_K.gguf b/Spiral-Qwen3-4B.Q2_K.gguf new file mode 100644 index 0000000..dc5ae4c --- /dev/null +++ b/Spiral-Qwen3-4B.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b7c43cc9f36e4d3e401f5dc1cc98333ce0c668ee6a6db12897617fbf4395a09 +size 1669499040 diff --git a/Spiral-Qwen3-4B.Q3_K_L.gguf b/Spiral-Qwen3-4B.Q3_K_L.gguf new file mode 100644 index 0000000..8b4c6d9 --- /dev/null +++ b/Spiral-Qwen3-4B.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a4b3e254f256e3511bb8d175ea947eb03f44af7e033500b698238794bc2f908 +size 2239785120 diff --git a/Spiral-Qwen3-4B.Q3_K_M.gguf b/Spiral-Qwen3-4B.Q3_K_M.gguf new file mode 100644 index 0000000..a8c2e0d --- /dev/null +++ b/Spiral-Qwen3-4B.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b42ad4941b8d210865c7f35d1270809cea165dd4b6c4d89a83004174f8f5e1e +size 2075617440 diff --git a/Spiral-Qwen3-4B.Q3_K_S.gguf b/Spiral-Qwen3-4B.Q3_K_S.gguf new file mode 100644 index 0000000..5c9718f --- /dev/null +++ b/Spiral-Qwen3-4B.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7641ec45f753ec363e0370cf84e998494e0f0c49a26fdd98102bf40617f02ca6 +size 1886996640 diff --git a/Spiral-Qwen3-4B.Q4_K_M.gguf b/Spiral-Qwen3-4B.Q4_K_M.gguf new file mode 100644 index 0000000..442b318 --- /dev/null +++ b/Spiral-Qwen3-4B.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:848e82890dd3f92003c0fc2103284371b4aaff0b7882d412d3ee62fbc990cf0c +size 2497280160 diff --git a/Spiral-Qwen3-4B.Q4_K_S.gguf b/Spiral-Qwen3-4B.Q4_K_S.gguf new file mode 100644 index 0000000..beae33b --- /dev/null +++ b/Spiral-Qwen3-4B.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1f8a2760f20e5b178d8ac1924fe70ca8b8c781a769708b55f6152d2d37ffb9e +size 2383308960 diff --git a/Spiral-Qwen3-4B.Q5_K_M.gguf b/Spiral-Qwen3-4B.Q5_K_M.gguf new file mode 100644 index 0000000..e031002 --- /dev/null +++ b/Spiral-Qwen3-4B.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b34b89764fe5d9c191d24992616250c455adb720ea79d44b74efd5d44777ffb +size 2889513120 diff --git a/Spiral-Qwen3-4B.Q5_K_S.gguf b/Spiral-Qwen3-4B.Q5_K_S.gguf new file mode 100644 index 0000000..4b03423 --- /dev/null +++ b/Spiral-Qwen3-4B.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02fbf9fafe609026fded6c9b083659ab8f8f6d12e2d90debedca2a46534bbc56 +size 2823710880 diff --git a/Spiral-Qwen3-4B.Q6_K.gguf b/Spiral-Qwen3-4B.Q6_K.gguf new file mode 100644 index 0000000..27bb3b3 --- /dev/null +++ b/Spiral-Qwen3-4B.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8853a8d790ad31583fb26107d0ecb355288927ae4b802d00f0bc8dec6dee34b +size 3306260640 diff --git a/Spiral-Qwen3-4B.Q8_0.gguf b/Spiral-Qwen3-4B.Q8_0.gguf new file mode 100644 index 0000000..082961c --- /dev/null +++ b/Spiral-Qwen3-4B.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ce06ddd8cafd62510926ca41df106434dad79db66127480f379bdc981c95f5 +size 4280404640 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