commit f6a540f05bdd9ee298e36709a0cf645a337432d0 Author: ModelHub XC Date: Fri May 29 13:23:13 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..f15b49c --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.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 +*.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/ELYZA-japanese-Llama-2-13b-fast-instruct-Q2_K.gguf b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q2_K.gguf new file mode 100644 index 0000000..51dc2d1 --- /dev/null +++ b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1af295fe3ebba88b45e0c95ca2afdf34d97bd2a166ed9c6e7c3aa5c495709461 +size 5503618208 diff --git a/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_L.gguf b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_L.gguf new file mode 100644 index 0000000..677a868 --- /dev/null +++ b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb51af018f0bf8cbd966ad28154ea492c7a0edd3c5677ebee679f89c861e7a8f +size 7010371520 diff --git a/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_M.gguf b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_M.gguf new file mode 100644 index 0000000..c640d73 --- /dev/null +++ b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46ab63904bd49a8978a3c6c9b09efc8191caa3f791ea1e75ff4196e0adbf1a94 +size 6418581440 diff --git a/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_S.gguf b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_S.gguf new file mode 100644 index 0000000..65eb9d8 --- /dev/null +++ b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:175c130066aafccf1879121f0ccba237d5f9006494dcfbdf029083b0e189f9d8 +size 5739792320 diff --git a/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_0.gguf b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_0.gguf new file mode 100644 index 0000000..37139aa --- /dev/null +++ b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74292e65a7fe8817dec57046de79b4b4439f745d480512aca64c0f23e1896b96 +size 7455201792 diff --git a/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_M.gguf b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_M.gguf new file mode 100644 index 0000000..4ab29db --- /dev/null +++ b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19045bb5daa4b8d36b6b34a8861a78f65f326e567ab5761d706aea7a5374dc64 +size 7955323392 diff --git a/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_S.gguf b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_S.gguf new file mode 100644 index 0000000..48a3e42 --- /dev/null +++ b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:345dbbbb30f5e4c108951046b63098c7fa015bf2c06bd7f807cdb9a818e25e26 +size 7503698432 diff --git a/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_0.gguf b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_0.gguf new file mode 100644 index 0000000..48fe611 --- /dev/null +++ b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64e13f475c0628fbb19ea90b5d083f18fb863e928aa187e4763f3b7861130859 +size 9069704832 diff --git a/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_M.gguf b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_M.gguf new file mode 100644 index 0000000..385b4fe --- /dev/null +++ b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5afdb0941cb08cdaa248a890b17256ea4776b2db4e9fed4982073e9ffbd7cff6 +size 9327343232 diff --git a/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_S.gguf b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_S.gguf new file mode 100644 index 0000000..3c5576a --- /dev/null +++ b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b4d90586e8b85e55a20f2cb07cdab30d7c1f183b2b353d2a033f476387b153b +size 9069704832 diff --git a/ELYZA-japanese-Llama-2-13b-fast-instruct-Q6_K.gguf b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q6_K.gguf new file mode 100644 index 0000000..ba575a4 --- /dev/null +++ b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d55221da27a493d1bc10d6d30445d0480029f8af5bd41ec1fa2e1da704440ff8 +size 10785114336 diff --git a/ELYZA-japanese-Llama-2-13b-fast-instruct-Q8_0.gguf b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q8_0.gguf new file mode 100644 index 0000000..e65edba --- /dev/null +++ b/ELYZA-japanese-Llama-2-13b-fast-instruct-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31f9bd3248e2717b5a5496ba41b340d6feb18dac793871fb389f33e1265ba56a +size 13968494368 diff --git a/README.md b/README.md new file mode 100644 index 0000000..78a6cee --- /dev/null +++ b/README.md @@ -0,0 +1,76 @@ +--- +base_model: elyza/ELYZA-japanese-Llama-2-13b-fast-instruct +inference: false +library_name: transformers +license: llama2 +model_creator: elyza +model_name: ELYZA-japanese-Llama-2-13b-fast-instruct +pipeline_tag: text-generation +quantized_by: Second State Inc. +language: +- ja +- en +--- + + + +
+ +
+
+ + +# ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF + +## Original Model + +[elyza/ELYZA-japanese-Llama-2-13b-fast-instruct](https://huggingface.co/elyza/ELYZA-japanese-Llama-2-13b-fast-instruct) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.2.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.8) and above + +- Prompt template + + - Prompt type: `llama-2-chat` + + - Prompt string + + ```text + [INST] <> + {{ system_prompt }} + <> + + {{ user_msg_1 }} [/INST] {{ model_answer_1 }} [INST] {{ user_msg_2 }} + ``` + +- Context size: `5120` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_M.gguf llama-api-server.wasm -p llama-2-chat + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_M.gguf llama-chat.wasm -p llama-2-chat + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q2_K.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q2_K.gguf) | Q2_K | 2 | 5.5 GB| smallest, significant quality loss - not recommended for most purposes | +| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_L.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_L.gguf) | Q3_K_L | 3 | 7.01 GB| small, substantial quality loss | +| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_M.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_M.gguf) | Q3_K_M | 3 | 6.42 GB| very small, high quality loss | +| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_S.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q3_K_S.gguf) | Q3_K_S | 3 | 5.74 GB| very small, high quality loss | +| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_0.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_0.gguf) | Q4_0 | 4 | 7.46 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_M.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_M.gguf) | Q4_K_M | 4 | 7.96 GB| medium, balanced quality - recommended | +| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_S.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q4_K_S.gguf) | Q4_K_S | 4 | 7.5 GB| small, greater quality loss | +| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_0.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_0.gguf) | Q5_0 | 5 | 9.07 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_M.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_M.gguf) | Q5_K_M | 5 | 9.33 GB| large, very low quality loss - recommended | +| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_S.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q5_K_S.gguf) | Q5_K_S | 5 | 9.07 GB| large, low quality loss - recommended | +| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q6_K.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q6_K.gguf) | Q6_K | 6 | 10.8 GB| very large, extremely low quality loss | +| [ELYZA-japanese-Llama-2-13b-fast-instruct-Q8_0.gguf](https://huggingface.co/second-state/ELYZA-japanese-Llama-2-13b-fast-instruct-GGUF/blob/main/ELYZA-japanese-Llama-2-13b-fast-instruct-Q8_0.gguf) | Q8_0 | 8 | 14 GB| very large, extremely low quality loss - not recommended | diff --git a/config.json b/config.json new file mode 100644 index 0000000..dc7677a --- /dev/null +++ b/config.json @@ -0,0 +1,28 @@ +{ + "_name_or_path": "elyza/ELYZA-japanese-Llama-2-13b-fast-instruct", + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 5120, + "initializer_range": 0.02, + "intermediate_size": 13824, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 40, + "num_hidden_layers": 40, + "num_key_value_heads": 40, + "pad_token_id": 2, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 10000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.34.1", + "use_cache": true, + "vocab_size": 44581 +} 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