commit e01593435a87d453c264a5f763a17d1296d4651d Author: ModelHub XC Date: Thu Oct 8 13:19:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: prithivMLmods/trlm-135m-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..1c0b2a5 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,67 @@ +*.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 + +*.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 + +trlm-135m.F16.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.BF16.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.F32.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q5_K.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q4_K.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +trlm-135m.Q5_K_M.gguf 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..3dfaa0e --- /dev/null +++ b/README.md @@ -0,0 +1,58 @@ +--- +license: apache-2.0 +language: +- en +base_model: +- Shekswess/trlm-135m +pipeline_tag: text-generation +library_name: transformers +tags: +- text-generation-inference +--- + +# **trlm-135m-GGUF** + +> The Tiny Reasoning Language Model ([trlm-135m](https://huggingface.co/Shekswess/trlm-135m)) is a 135 million parameter research prototype aimed at exploring how smaller language models can acquire step-by-step reasoning abilities. Built on the SmolLM2-135M-Instruct model (a Llama 3 based decoder-only transformer), it undergoes a three-stage fine-tuning pipeline: Stage 1 for general instruction tuning without reasoning, Stage 2 for incorporating reasoning traces marked by tags, and Stage 3 for preference alignment to refine reasoning style using Direct Preference Optimization (DPO). + +If you are running in **LM Studio**, start with a context length of 1024 and adjust it based on the responses. It’s recommended to use high-precision quants for better performance. + +## Execute using Ollama + +run -> + +```py +ollama run hf.co/prithivMLmods/trlm-135m-GGUF:BF16 +``` + +## Model Files + +| File Name | Quant Type | File Size | +| - | - | - | +| trlm-135m.BF16.gguf | BF16 | 271 MB | +| trlm-135m.F16.gguf | F16 | 271 MB | +| trlm-135m.F32.gguf | F32 | 540 MB | +| trlm-135m.Q2_K.gguf | Q2_K | 88.2 MB | +| trlm-135m.Q3_K_L.gguf | Q3_K_L | 97.5 MB | +| trlm-135m.Q3_K_M.gguf | Q3_K_M | 93.5 MB | +| trlm-135m.Q3_K_S.gguf | Q3_K_S | 88.2 MB | +| trlm-135m.Q4_0.gguf | Q4_0 | 91.7 MB | +| trlm-135m.Q4_1.gguf | Q4_1 | 98.4 MB | +| trlm-135m.Q4_K.gguf | Q4_K | 105 MB | +| trlm-135m.Q4_K_M.gguf | Q4_K_M | 105 MB | +| trlm-135m.Q4_K_S.gguf | Q4_K_S | 102 MB | +| trlm-135m.Q5_0.gguf | Q5_0 | 105 MB | +| trlm-135m.Q5_1.gguf | Q5_1 | 112 MB | +| trlm-135m.Q5_K.gguf | Q5_K | 112 MB | +| trlm-135m.Q5_K_M.gguf | Q5_K_M | 112 MB | +| trlm-135m.Q5_K_S.gguf | Q5_K_S | 110 MB | +| trlm-135m.Q6_K.gguf | Q6_K | 138 MB | +| trlm-135m.Q8_0.gguf | Q8_0 | 145 MB | + +## 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 diff --git a/trlm-135m.BF16.gguf b/trlm-135m.BF16.gguf new file mode 100644 index 0000000..8337ff9 --- /dev/null +++ b/trlm-135m.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d284c078a23fd5645e75e35643b2bf407550e18b44faa9067885806d82d37965 +size 270888544 diff --git a/trlm-135m.F16.gguf b/trlm-135m.F16.gguf new file mode 100644 index 0000000..f88ea90 --- /dev/null +++ b/trlm-135m.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e825ffa6427edd6080540ae651e41a5be48490b8703a4956523577f2393a6d3 +size 270888544 diff --git a/trlm-135m.F32.gguf b/trlm-135m.F32.gguf new file mode 100644 index 0000000..02c7f18 --- /dev/null +++ b/trlm-135m.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09ed9250a7b068ed824e32c0b3d11a9dbcfd2364a18c50df891a7a9b96b20e7b +size 539850592 diff --git a/trlm-135m.Q2_K.gguf b/trlm-135m.Q2_K.gguf new file mode 100644 index 0000000..155bc37 --- /dev/null +++ b/trlm-135m.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b729c7304e525668fb61aa083ceb92ad91d587606e13469604b6c137e3e39207 +size 88203328 diff --git a/trlm-135m.Q3_K_L.gguf b/trlm-135m.Q3_K_L.gguf new file mode 100644 index 0000000..8002ca8 --- /dev/null +++ b/trlm-135m.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6afcf519ead4b2a21e939b27339f19c652ddaf4f6dc59b75ce699ed2526b88f4 +size 97534528 diff --git a/trlm-135m.Q3_K_M.gguf b/trlm-135m.Q3_K_M.gguf new file mode 100644 index 0000000..0edb06e --- /dev/null +++ b/trlm-135m.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45fe37419e943289eb425d71c838d2eeb866dde8ea6654db293ce0546818ebf3 +size 93511744 diff --git a/trlm-135m.Q3_K_S.gguf b/trlm-135m.Q3_K_S.gguf new file mode 100644 index 0000000..063ce8a --- /dev/null +++ b/trlm-135m.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5185538f5c480d4234a1c9075c9d262d9cf25611a764ca2543075566107005dc +size 88203328 diff --git a/trlm-135m.Q4_0.gguf b/trlm-135m.Q4_0.gguf new file mode 100644 index 0000000..0d1da5e --- /dev/null +++ b/trlm-135m.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba7e99a6012c2d7426134eb4f548b2b481537f04089280ecd83a96544718fc64 +size 91728448 diff --git a/trlm-135m.Q4_1.gguf b/trlm-135m.Q4_1.gguf new file mode 100644 index 0000000..ad1b322 --- /dev/null +++ b/trlm-135m.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca1f11fb7f8403733e1b75cf527d95a0edbf1eb4e27e6b5106db005b0e3be668 +size 98363968 diff --git a/trlm-135m.Q4_K.gguf b/trlm-135m.Q4_K.gguf new file mode 100644 index 0000000..3391da1 --- /dev/null +++ b/trlm-135m.Q4_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b61771e4cea5c27b80a28fedc06a3aad4dc2acc6cca2eb487bf91237db16a6b9 +size 105455680 diff --git a/trlm-135m.Q4_K_M.gguf b/trlm-135m.Q4_K_M.gguf new file mode 100644 index 0000000..3391da1 --- /dev/null +++ b/trlm-135m.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b61771e4cea5c27b80a28fedc06a3aad4dc2acc6cca2eb487bf91237db16a6b9 +size 105455680 diff --git a/trlm-135m.Q4_K_S.gguf b/trlm-135m.Q4_K_S.gguf new file mode 100644 index 0000000..a9c12f4 --- /dev/null +++ b/trlm-135m.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e64d5dd95b77b648c312ca02dbb7483e458cbe6d464921012dde3c6660203aa8 +size 102041152 diff --git a/trlm-135m.Q5_0.gguf b/trlm-135m.Q5_0.gguf new file mode 100644 index 0000000..f695920 --- /dev/null +++ b/trlm-135m.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe7c05380bfec264904b4490a76180ea079308967a2b4fba6e538048a6b34a73 +size 104999488 diff --git a/trlm-135m.Q5_1.gguf b/trlm-135m.Q5_1.gguf new file mode 100644 index 0000000..eea7e5d --- /dev/null +++ b/trlm-135m.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db52fe2cb62ba75cc19c88d505300fe6ba793475cd22865ccf2e3753bc4daa23 +size 111635008 diff --git a/trlm-135m.Q5_K.gguf b/trlm-135m.Q5_K.gguf new file mode 100644 index 0000000..bd89a42 --- /dev/null +++ b/trlm-135m.Q5_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:123f7fbb819e55a9b018d7f2557b90c15edacaa64c418f402485a053f8ce6e0d +size 112105024 diff --git a/trlm-135m.Q5_K_M.gguf b/trlm-135m.Q5_K_M.gguf new file mode 100644 index 0000000..bd89a42 --- /dev/null +++ b/trlm-135m.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:123f7fbb819e55a9b018d7f2557b90c15edacaa64c418f402485a053f8ce6e0d +size 112105024 diff --git a/trlm-135m.Q5_K_S.gguf b/trlm-135m.Q5_K_S.gguf new file mode 100644 index 0000000..7964f17 --- /dev/null +++ b/trlm-135m.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01bd362bae23c92a808663f42e45e73e3d1d9e47838b4b7f62a2bdc785e75a5e +size 109976128 diff --git a/trlm-135m.Q6_K.gguf b/trlm-135m.Q6_K.gguf new file mode 100644 index 0000000..1b68806 --- /dev/null +++ b/trlm-135m.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29163060d765d05f1c1d30d68a561b247274e16ce04872502e5e26bd81cbd89c +size 138384448 diff --git a/trlm-135m.Q8_0.gguf b/trlm-135m.Q8_0.gguf new file mode 100644 index 0000000..68a0c5c --- /dev/null +++ b/trlm-135m.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aaa931d7036fb9ec0dc97cb0fb9107763635a5fc9497bf7782e4f6658fc379f0 +size 144812608