commit a0f271fc8e88125f404ce309f066b2ec995a68d4 Author: ModelHub XC Date: Sun Nov 1 06:19:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/SmolLM2-1.7B-Instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..84b1c78 --- /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 +SmolLM2-1.7B-Instruct-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +SmolLM2-1.7B-Instruct-f16.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..48041d6 --- /dev/null +++ b/README.md @@ -0,0 +1,83 @@ +--- +base_model: HuggingFaceTB/SmolLM2-1.7B-Instruct +license: apache-2.0 +library_name: transformers +model_creator: HuggingFaceTB +model_name: SmolLM2-1.7B-Instruct +quantized_by: Second State Inc. +language: +- en +--- + + + +
+ +
+
+ + +# SmolLM2-1.7B-Instruct-GGUF + +## Original Model + +[HuggingFaceTB/SmolLM2-1.7B-Instruct](https://huggingface.co/HuggingFaceTB/SmolLM2-1.7B-Instruct) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.14.15](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.14.15) and above + +- Prompt template + + - Prompt type: `chatml` + + - Prompt string + + ```text + <|im_start|>system + {system_message}<|im_end|> + <|im_start|>user + {prompt}<|im_end|> + <|im_start|>assistant + ``` + +- Context size: `2048` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:SmolLM2-1.7B-Instruct-Q5_K_M.gguf \ + llama-api-server.wasm \ + --model-name SmolLM2-1.7B-Instruct \ + --prompt-template chatml \ + --ctx-size 2048 + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:SmolLM2-1.7B-Instruct-Q5_K_M.gguf \ + llama-chat.wasm \ + --prompt-template chatml \ + --ctx-size 2048 + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [SmolLM2-1.7B-Instruct-Q2_K.gguf](https://huggingface.co/second-state/SmolLM2-1.7B-Instruct-GGUF/blob/main/SmolLM2-1.7B-Instruct-Q2_K.gguf) | Q2_K | 2 | 675 MB| smallest, significant quality loss - not recommended for most purposes | +| [SmolLM2-1.7B-Instruct-Q3_K_L.gguf](https://huggingface.co/second-state/SmolLM2-1.7B-Instruct-GGUF/blob/main/SmolLM2-1.7B-Instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 933 MB| small, substantial quality loss | +| [SmolLM2-1.7B-Instruct-Q3_K_M.gguf](https://huggingface.co/second-state/SmolLM2-1.7B-Instruct-GGUF/blob/main/SmolLM2-1.7B-Instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 860 MB| very small, high quality loss | +| [SmolLM2-1.7B-Instruct-Q3_K_S.gguf](https://huggingface.co/second-state/SmolLM2-1.7B-Instruct-GGUF/blob/main/SmolLM2-1.7B-Instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 777 MB| very small, high quality loss | +| [SmolLM2-1.7B-Instruct-Q4_0.gguf](https://huggingface.co/second-state/SmolLM2-1.7B-Instruct-GGUF/blob/main/SmolLM2-1.7B-Instruct-Q4_0.gguf) | Q4_0 | 4 | 991 MB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [SmolLM2-1.7B-Instruct-Q4_K_M.gguf](https://huggingface.co/second-state/SmolLM2-1.7B-Instruct-GGUF/blob/main/SmolLM2-1.7B-Instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 1.06 GB| medium, balanced quality - recommended | +| [SmolLM2-1.7B-Instruct-Q4_K_S.gguf](https://huggingface.co/second-state/SmolLM2-1.7B-Instruct-GGUF/blob/main/SmolLM2-1.7B-Instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 999 MB| small, greater quality loss | +| [SmolLM2-1.7B-Instruct-Q5_0.gguf](https://huggingface.co/second-state/SmolLM2-1.7B-Instruct-GGUF/blob/main/SmolLM2-1.7B-Instruct-Q5_0.gguf) | Q5_0 | 5 | 1.19 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [SmolLM2-1.7B-Instruct-Q5_K_M.gguf](https://huggingface.co/second-state/SmolLM2-1.7B-Instruct-GGUF/blob/main/SmolLM2-1.7B-Instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 1.23 GB| large, very low quality loss - recommended | +| [SmolLM2-1.7B-Instruct-Q5_K_S.gguf](https://huggingface.co/second-state/SmolLM2-1.7B-Instruct-GGUF/blob/main/SmolLM2-1.7B-Instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 1.19 GB| large, low quality loss - recommended | +| [SmolLM2-1.7B-Instruct-Q6_K.gguf](https://huggingface.co/second-state/SmolLM2-1.7B-Instruct-GGUF/blob/main/SmolLM2-1.7B-Instruct-Q6_K.gguf) | Q6_K | 6 | 1.41 GB| very large, extremely low quality loss | +| [SmolLM2-1.7B-Instruct-Q8_0.gguf](https://huggingface.co/second-state/SmolLM2-1.7B-Instruct-GGUF/blob/main/SmolLM2-1.7B-Instruct-Q8_0.gguf) | Q8_0 | 8 | 1.82 GB| very large, extremely low quality loss - not recommended | +| [SmolLM2-1.7B-Instruct-f16.gguf](https://huggingface.co/second-state/SmolLM2-1.7B-Instruct-GGUF/blob/main/SmolLM2-1.7B-Instruct-f16.gguf) | f16 | 16 | 3.42 GB| | + +*Quantized with llama.cpp b4120* diff --git a/SmolLM2-1.7B-Instruct-Q2_K.gguf b/SmolLM2-1.7B-Instruct-Q2_K.gguf new file mode 100644 index 0000000..1e02564 --- /dev/null +++ b/SmolLM2-1.7B-Instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a81276a962be228e83df40e1be833b5735a902974e635d4931d6bc5d76053e0 +size 674583392 diff --git a/SmolLM2-1.7B-Instruct-Q3_K_L.gguf b/SmolLM2-1.7B-Instruct-Q3_K_L.gguf new file mode 100644 index 0000000..1b8a405 --- /dev/null +++ b/SmolLM2-1.7B-Instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:722e0f3846c0cd6613fc93580da4c1165de956d3626c55aed0b230a50194987f +size 932533088 diff --git a/SmolLM2-1.7B-Instruct-Q3_K_M.gguf b/SmolLM2-1.7B-Instruct-Q3_K_M.gguf new file mode 100644 index 0000000..1d2f49c --- /dev/null +++ b/SmolLM2-1.7B-Instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2ce91737dfa2127c4fce6604b29218567f6343b16c560aab93efa025f958ecb +size 860181344 diff --git a/SmolLM2-1.7B-Instruct-Q3_K_S.gguf b/SmolLM2-1.7B-Instruct-Q3_K_S.gguf new file mode 100644 index 0000000..37d9388 --- /dev/null +++ b/SmolLM2-1.7B-Instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c34cbe3aeca752c09b39089a1c4fb521d7cb4699cc080cc6de9b03980c5b42d +size 776819552 diff --git a/SmolLM2-1.7B-Instruct-Q4_0.gguf b/SmolLM2-1.7B-Instruct-Q4_0.gguf new file mode 100644 index 0000000..4e90c38 --- /dev/null +++ b/SmolLM2-1.7B-Instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d202c4c42d0bd299551cc099ac4fb2c12228b03f3bfa0d06cb00ab7f011d577 +size 990729056 diff --git a/SmolLM2-1.7B-Instruct-Q4_K_M.gguf b/SmolLM2-1.7B-Instruct-Q4_K_M.gguf new file mode 100644 index 0000000..a832f4e --- /dev/null +++ b/SmolLM2-1.7B-Instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fab954d296aa25885960ed771a005343c220ac93ef78a53454e667e334935fe9 +size 1055609696 diff --git a/SmolLM2-1.7B-Instruct-Q4_K_S.gguf b/SmolLM2-1.7B-Instruct-Q4_K_S.gguf new file mode 100644 index 0000000..48f5476 --- /dev/null +++ b/SmolLM2-1.7B-Instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b73b7bdaf7106c7a21da146b8ac4fd732afecffe591fb06f43313cdd57a4259 +size 999117664 diff --git a/SmolLM2-1.7B-Instruct-Q5_0.gguf b/SmolLM2-1.7B-Instruct-Q5_0.gguf new file mode 100644 index 0000000..88a6c7f --- /dev/null +++ b/SmolLM2-1.7B-Instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23ecf83012ddcbb17c8b9227b2cf7f6a4abff4b1ebfe2fec5caf9d7318243551 +size 1192055648 diff --git a/SmolLM2-1.7B-Instruct-Q5_K_M.gguf b/SmolLM2-1.7B-Instruct-Q5_K_M.gguf new file mode 100644 index 0000000..339eb1e --- /dev/null +++ b/SmolLM2-1.7B-Instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57b99e35d3538d90385687402ab5cbaba76ba52618071f72fc467689b1ddaffa +size 1225479008 diff --git a/SmolLM2-1.7B-Instruct-Q5_K_S.gguf b/SmolLM2-1.7B-Instruct-Q5_K_S.gguf new file mode 100644 index 0000000..c11b683 --- /dev/null +++ b/SmolLM2-1.7B-Instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfe968c323792f71eff38719450aee55263bf7964bb9fddf61e33e9f2e540147 +size 1192055648 diff --git a/SmolLM2-1.7B-Instruct-Q6_K.gguf b/SmolLM2-1.7B-Instruct-Q6_K.gguf new file mode 100644 index 0000000..ed8722f --- /dev/null +++ b/SmolLM2-1.7B-Instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a5e500d36887cb68be1b24ab7adefb07ea77b7d2e0d1000095025b5f7bc8a6f +size 1405965152 diff --git a/SmolLM2-1.7B-Instruct-Q8_0.gguf b/SmolLM2-1.7B-Instruct-Q8_0.gguf new file mode 100644 index 0000000..5dbbf83 --- /dev/null +++ b/SmolLM2-1.7B-Instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1812c04a6a47bf08da5d352d89978712db8225cb17d571c3c12805dd33411e6b +size 1820414816 diff --git a/SmolLM2-1.7B-Instruct-f16.gguf b/SmolLM2-1.7B-Instruct-f16.gguf new file mode 100644 index 0000000..5468147 --- /dev/null +++ b/SmolLM2-1.7B-Instruct-f16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84f3bea5ec6149793d9087205c433f11ac0de5602b942b59d5399773786a0b83 +size 3424736096 diff --git a/config.json b/config.json new file mode 100644 index 0000000..d25647d --- /dev/null +++ b/config.json @@ -0,0 +1,35 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 2048, + "initializer_range": 0.02, + "intermediate_size": 8192, + "max_position_embeddings": 8192, + "mlp_bias": false, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 24, + "num_key_value_heads": 32, + "pad_token_id": 2, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 130000, + "tie_word_embeddings": true, + "torch_dtype": "bfloat16", + "transformers_version": "4.42.3", + "transformers.js_config": { + "kv_cache_dtype": { + "q4f16": "float16", + "fp16": "float16" + } + }, + "use_cache": true, + "vocab_size": 49152 +}