From fb6713dd7d928f1e6e331dc1ce3f9e768364294b Mon Sep 17 00:00:00 2001 From: ModelHub XC Date: Thu, 18 Jun 2026 08:09:14 +0800 Subject: [PATCH] =?UTF-8?q?=E5=88=9D=E5=A7=8B=E5=8C=96=E9=A1=B9=E7=9B=AE?= =?UTF-8?q?=EF=BC=8C=E7=94=B1ModelHub=20XC=E7=A4=BE=E5=8C=BA=E6=8F=90?= =?UTF-8?q?=E4=BE=9B=E6=A8=A1=E5=9E=8B?= MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Model: second-state/llm-compiler-7b-ftd-GGUF Source: Original Platform --- .gitattributes | 48 ++++++++++++++++++++ README.md | 78 +++++++++++++++++++++++++++++++++ config.json | 27 ++++++++++++ configuration.json | 1 + llm-compiler-7b-ftd-Q2_K.gguf | 3 ++ llm-compiler-7b-ftd-Q3_K_L.gguf | 3 ++ llm-compiler-7b-ftd-Q3_K_M.gguf | 3 ++ llm-compiler-7b-ftd-Q3_K_S.gguf | 3 ++ llm-compiler-7b-ftd-Q4_0.gguf | 3 ++ llm-compiler-7b-ftd-Q4_K_M.gguf | 3 ++ llm-compiler-7b-ftd-Q4_K_S.gguf | 3 ++ llm-compiler-7b-ftd-Q5_0.gguf | 3 ++ llm-compiler-7b-ftd-Q5_K_M.gguf | 3 ++ llm-compiler-7b-ftd-Q5_K_S.gguf | 3 ++ llm-compiler-7b-ftd-Q6_K.gguf | 3 ++ llm-compiler-7b-ftd-Q8_0.gguf | 3 ++ llm-compiler-7b-ftd-f16.gguf | 3 ++ 17 files changed, 193 insertions(+) create mode 100644 .gitattributes create mode 100644 README.md create mode 100644 config.json create mode 100644 configuration.json create mode 100644 llm-compiler-7b-ftd-Q2_K.gguf create mode 100644 llm-compiler-7b-ftd-Q3_K_L.gguf create mode 100644 llm-compiler-7b-ftd-Q3_K_M.gguf create mode 100644 llm-compiler-7b-ftd-Q3_K_S.gguf create mode 100644 llm-compiler-7b-ftd-Q4_0.gguf create mode 100644 llm-compiler-7b-ftd-Q4_K_M.gguf create mode 100644 llm-compiler-7b-ftd-Q4_K_S.gguf create mode 100644 llm-compiler-7b-ftd-Q5_0.gguf create mode 100644 llm-compiler-7b-ftd-Q5_K_M.gguf create mode 100644 llm-compiler-7b-ftd-Q5_K_S.gguf create mode 100644 llm-compiler-7b-ftd-Q6_K.gguf create mode 100644 llm-compiler-7b-ftd-Q8_0.gguf create mode 100644 llm-compiler-7b-ftd-f16.gguf diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d126118 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,48 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt 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 +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz 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 +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl 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 +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* 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 +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +llm-compiler-7b-ftd-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +llm-compiler-7b-ftd-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +llm-compiler-7b-ftd-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llm-compiler-7b-ftd-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llm-compiler-7b-ftd-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +llm-compiler-7b-ftd-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llm-compiler-7b-ftd-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llm-compiler-7b-ftd-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +llm-compiler-7b-ftd-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +llm-compiler-7b-ftd-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +llm-compiler-7b-ftd-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +llm-compiler-7b-ftd-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llm-compiler-7b-ftd-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..e0ffe27 --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +language: +- code +license: other +model_name: llm-compiler-7b +base_model: facebook/llm-compiler-7b-ftd +inference: false +model_creator: facebook +quantized_by: Second State Inc. +--- + + + +
+ +
+
+ + + +# llm-compiler-7b-ftd-GGUF + +## Original Model + +[facebook/llm-compiler-7b-ftd](https://huggingface.co/facebook/llm-compiler-7b-ftd) + +**License** A custom commercial license is available at: [https://ai.meta.com/resources/models-and-libraries/llama-downloads/](https://ai.meta.com/resources/models-and-libraries/llama-downloads/) + +## Run with LlamaEdge + + + +- LlamaEdge version: coming soon + + + + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [llm-compiler-7b-ftd-Q2_K.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q2_K.gguf) | Q2_K | 2 | 2.53 GB| smallest, significant quality loss - not recommended for most purposes | +| [llm-compiler-7b-ftd-Q3_K_L.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q3_K_L.gguf) | Q3_K_L | 3 | 3.6 GB| small, substantial quality loss | +| [llm-compiler-7b-ftd-Q3_K_M.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q3_K_M.gguf) | Q3_K_M | 3 | 3.3 GB| very small, high quality loss | +| [llm-compiler-7b-ftd-Q3_K_S.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q3_K_S.gguf) | Q3_K_S | 3 | 2.95 GB| very small, high quality loss | +| [llm-compiler-7b-ftd-Q4_0.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q4_0.gguf) | Q4_0 | 4 | 3.83 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [llm-compiler-7b-ftd-Q4_K_M.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q4_K_M.gguf) | Q4_K_M | 4 | 4.08 GB| medium, balanced quality - recommended | +| [llm-compiler-7b-ftd-Q4_K_S.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q4_K_S.gguf) | Q4_K_S | 4 | 3.86 GB| small, greater quality loss | +| [llm-compiler-7b-ftd-Q5_0.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q5_0.gguf) | Q5_0 | 5 | 4.65 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [llm-compiler-7b-ftd-Q5_K_M.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q5_K_M.gguf) | Q5_K_M | 5 | 4.78 GB| large, very low quality loss - recommended | +| [llm-compiler-7b-ftd-Q5_K_S.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q5_K_S.gguf) | Q5_K_S | 5 | 4.65 GB| large, low quality loss - recommended | +| [llm-compiler-7b-ftd-Q6_K.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q6_K.gguf) | Q6_K | 6 | 5.53 GB| very large, extremely low quality loss | +| [llm-compiler-7b-ftd-Q8_0.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-Q8_0.gguf) | Q8_0 | 8 | 7.16 GB| very large, extremely low quality loss - not recommended | +| [llm-compiler-7b-ftd-f16.gguf](https://huggingface.co/second-state/llm-compiler-7b-ftd-GGUF/blob/main/llm-compiler-7b-ftd-f16.gguf) | f16 | f16 | 13.5 GB| | + +*Quantized with llama.cpp b3259* diff --git a/config.json b/config.json new file mode 100644 index 0000000..e07f7f1 --- /dev/null +++ b/config.json @@ -0,0 +1,27 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 16384, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 32, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.37.2", + "use_cache": true, + "vocab_size": 32000 +} 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/llm-compiler-7b-ftd-Q2_K.gguf b/llm-compiler-7b-ftd-Q2_K.gguf new file mode 100644 index 0000000..9a822df --- /dev/null +++ b/llm-compiler-7b-ftd-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7196a23999c22eb54e6b96612f314bd0e0cd4e4945483a732710949f63661cb6 +size 2532863872 diff --git a/llm-compiler-7b-ftd-Q3_K_L.gguf b/llm-compiler-7b-ftd-Q3_K_L.gguf new file mode 100644 index 0000000..28b71b0 --- /dev/null +++ b/llm-compiler-7b-ftd-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c691f5119cf467b363928f8d88d9418df2f075a7a891a2a53f0f173fd017866 +size 3597111168 diff --git a/llm-compiler-7b-ftd-Q3_K_M.gguf b/llm-compiler-7b-ftd-Q3_K_M.gguf new file mode 100644 index 0000000..597fa84 --- /dev/null +++ b/llm-compiler-7b-ftd-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db8ae0056c0b18ab6374930f2aefdd3e6c4eaabe85e2a2cf6a94f3afca1495ed +size 3298004864 diff --git a/llm-compiler-7b-ftd-Q3_K_S.gguf b/llm-compiler-7b-ftd-Q3_K_S.gguf new file mode 100644 index 0000000..39ab321 --- /dev/null +++ b/llm-compiler-7b-ftd-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b872e7611a3beb4a183b936a1d4d8dc44329fb42ea94ffbd8cb6fead7fa54c04 +size 2948304768 diff --git a/llm-compiler-7b-ftd-Q4_0.gguf b/llm-compiler-7b-ftd-Q4_0.gguf new file mode 100644 index 0000000..e5fc1c4 --- /dev/null +++ b/llm-compiler-7b-ftd-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e268640e541dcb658131be78c7635c74a3aba53a9f6187f42749f1774a9adfc +size 3825807232 diff --git a/llm-compiler-7b-ftd-Q4_K_M.gguf b/llm-compiler-7b-ftd-Q4_K_M.gguf new file mode 100644 index 0000000..5401afc --- /dev/null +++ b/llm-compiler-7b-ftd-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba608b8f0d5c5d779d20973d90fc479337f88f823a0f191d1972b6ef90c4be33 +size 4081004416 diff --git a/llm-compiler-7b-ftd-Q4_K_S.gguf b/llm-compiler-7b-ftd-Q4_K_S.gguf new file mode 100644 index 0000000..1b6c238 --- /dev/null +++ b/llm-compiler-7b-ftd-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5df5e5acaf163b47fd529739644aaa47fb510a05d2c17d08ecdb8feb7aebd58 +size 3856740224 diff --git a/llm-compiler-7b-ftd-Q5_0.gguf b/llm-compiler-7b-ftd-Q5_0.gguf new file mode 100644 index 0000000..1f96a56 --- /dev/null +++ b/llm-compiler-7b-ftd-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4668f30560094ec76548f1e040ee6439dd7c913214aeb57e23599eb473dc41d3 +size 4651691904 diff --git a/llm-compiler-7b-ftd-Q5_K_M.gguf b/llm-compiler-7b-ftd-Q5_K_M.gguf new file mode 100644 index 0000000..7fd12a1 --- /dev/null +++ b/llm-compiler-7b-ftd-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:95003f19e378c854ae1d6b3714bc30e4787f9e6c5673f92c006e49b2499599a4 +size 4783157120 diff --git a/llm-compiler-7b-ftd-Q5_K_S.gguf b/llm-compiler-7b-ftd-Q5_K_S.gguf new file mode 100644 index 0000000..94460cc --- /dev/null +++ b/llm-compiler-7b-ftd-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78e50e6e825427d613d4f27c83fb79fff50a13f901794163d683bcb35b0a1b2a +size 4651691904 diff --git a/llm-compiler-7b-ftd-Q6_K.gguf b/llm-compiler-7b-ftd-Q6_K.gguf new file mode 100644 index 0000000..19e5482 --- /dev/null +++ b/llm-compiler-7b-ftd-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7173b0b8bc292788673c1687d09d861643a7702f3fdd569f697c34c9c8b55967 +size 5529194368 diff --git a/llm-compiler-7b-ftd-Q8_0.gguf b/llm-compiler-7b-ftd-Q8_0.gguf new file mode 100644 index 0000000..47a708a --- /dev/null +++ b/llm-compiler-7b-ftd-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be40a09ea18ffc6ed60e480b836f2f3ca4d8a916970c209fe6ebf178f4156164 +size 7161089920 diff --git a/llm-compiler-7b-ftd-f16.gguf b/llm-compiler-7b-ftd-f16.gguf new file mode 100644 index 0000000..84a26ca --- /dev/null +++ b/llm-compiler-7b-ftd-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1f75d4f55656dbc7b2052f06d1eb1eaf99ed5d7aaf306f520e72136bd98f829 +size 13478104960