commit a5ce826f7eafa6ad1e69a054604f77c82ac67800 Author: ModelHub XC Date: Thu May 28 12:46:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/OpenChat-3.5-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/README.md b/README.md new file mode 100644 index 0000000..33bdb62 --- /dev/null +++ b/README.md @@ -0,0 +1,73 @@ +--- +base_model: openchat/openchat_3.5 +inference: false +license: apache-2.0 +model_creator: OpenChat +model_name: OpenChat 3.5 7B +model_type: mistral +pipeline_tag: text-generation +quantized_by: Second State Inc. +tags: +- openchat +--- + + + +
+ +
+
+ + +# OpenChat-3.5-GGUF + +## Original Model + +[openchat/openchat_3.5](https://huggingface.co/openchat/openchat_3.5) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.2.8](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.8) and above + +- Prompt template + + - Prompt type: `openchat` + + - Prompt string + + ```text + GPT4 User: {prompt}<|end_of_turn|>GPT4 Assistant: + ``` + + - Reverse prompt: `<|end_of_turn|>` + +- Context size: `4096` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:openchat-3.5-0106-Q5_K_M.gguf llama-api-server.wasm -p openchat -r '<|end_of_turn|>' + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:openchat_3.5.Q5_K_M.gguf llama-chat.wasm -p openchat -r '<|end_of_turn|>' + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [openchat_3.5-Q2_K.gguf](https://huggingface.co/second-state/OpenChat-3.5-GGUF/blob/main/openchat_3.5-Q2_K.gguf) | Q2_K | 2 | 2.72 GB| smallest, significant quality loss - not recommended for most purposes | +| [openchat_3.5-Q3_K_L.gguf](https://huggingface.co/second-state/OpenChat-3.5-GGUF/blob/main/openchat_3.5-Q3_K_L.gguf) | Q3_K_L | 3 | 3.82 GB| small, substantial quality loss | +| [openchat_3.5-Q3_K_M.gguf](https://huggingface.co/second-state/OpenChat-3.5-GGUF/blob/main/openchat_3.5-Q3_K_M.gguf) | Q3_K_M | 3 | 3.52 GB| very small, high quality loss | +| [openchat_3.5-Q3_K_S.gguf](https://huggingface.co/second-state/OpenChat-3.5-GGUF/blob/main/openchat_3.5-Q3_K_S.gguf) | Q3_K_S | 3 | 3.16 GB| very small, high quality loss | +| [openchat_3.5-Q4_0.gguf](https://huggingface.co/second-state/OpenChat-3.5-GGUF/blob/main/openchat_3.5-Q4_0.gguf) | Q4_0 | 4 | 4.11 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [openchat_3.5-Q4_K_M.gguf](https://huggingface.co/second-state/OpenChat-3.5-GGUF/blob/main/openchat_3.5-Q4_K_M.gguf) | Q4_K_M | 4 | 4.37 GB| medium, balanced quality - recommended | +| [openchat_3.5-Q4_K_S.gguf](https://huggingface.co/second-state/OpenChat-3.5-GGUF/blob/main/openchat_3.5-Q4_K_S.gguf) | Q4_K_S | 4 | 4.14 GB| small, greater quality loss | +| [openchat_3.5-Q5_0.gguf](https://huggingface.co/second-state/OpenChat-3.5-GGUF/blob/main/openchat_3.5-Q5_0.gguf) | Q5_0 | 5 | 5.00 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [openchat_3.5-Q5_K_M.gguf](https://huggingface.co/second-state/OpenChat-3.5-GGUF/blob/main/openchat_3.5-Q5_K_M.gguf) | Q5_K_M | 5 | 5.13 GB| large, very low quality loss - recommended | +| [openchat_3.5-Q5_K_S.gguf](https://huggingface.co/second-state/OpenChat-3.5-GGUF/blob/main/openchat_3.5-Q5_K_S.gguf) | Q5_K_S | 5 | 5.00 GB| large, low quality loss - recommended | +| [openchat_3.5-Q6_K.gguf](https://huggingface.co/second-state/OpenChat-3.5-GGUF/blob/main/openchat_3.5-Q6_K.gguf) | Q6_K | 6 | 5.94 GB| very large, extremely low quality loss | +| [openchat_3.5-Q8_0.gguf](https://huggingface.co/second-state/OpenChat-3.5-GGUF/blob/main/openchat_3.5-Q8_0.gguf) | Q8_0 | 8 | 7.70 GB| very large, extremely low quality loss - not recommended | diff --git a/config.json b/config.json new file mode 100644 index 0000000..42fc7bf --- /dev/null +++ b/config.json @@ -0,0 +1,25 @@ +{ + "_name_or_path": "imone/Mistral_7B_with_EOT_token", + "architectures": [ + "MistralForCausalLM" + ], + "bos_token_id": 1, + "eos_token_id": 32000, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 14336, + "max_position_embeddings": 8192, + "model_type": "mistral", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 8, + "rms_norm_eps": 1e-05, + "rope_theta": 10000.0, + "sliding_window": 4096, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.34.1", + "use_cache": true, + "vocab_size": 32002 +} 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/openchat_3.5-Q2_K.gguf b/openchat_3.5-Q2_K.gguf new file mode 100644 index 0000000..c1c627f --- /dev/null +++ b/openchat_3.5-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2176c14ff38a2c8161acec418ca8ffdbf7e973cf985ed3bc8b403b92919373d4 +size 2719251648 diff --git a/openchat_3.5-Q3_K_L.gguf b/openchat_3.5-Q3_K_L.gguf new file mode 100644 index 0000000..61b039f --- /dev/null +++ b/openchat_3.5-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1dd4eb92693e0af42a0c7afdef7f19591cf3270ae395a2681eb028e7ce2509a8 +size 3822034944 diff --git a/openchat_3.5-Q3_K_M.gguf b/openchat_3.5-Q3_K_M.gguf new file mode 100644 index 0000000..3ef5fc2 --- /dev/null +++ b/openchat_3.5-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bbe83e03ae403920405d448007d754a37893e4ce595a056fe80515576e084dd +size 3518996480 diff --git a/openchat_3.5-Q3_K_S.gguf b/openchat_3.5-Q3_K_S.gguf new file mode 100644 index 0000000..d674b69 --- /dev/null +++ b/openchat_3.5-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31494676038d8caeefa92cf4b76a44af702f156a74efc5261548e1f8448cf937 +size 3164577792 diff --git a/openchat_3.5-Q4_0.gguf b/openchat_3.5-Q4_0.gguf new file mode 100644 index 0000000..47660f3 --- /dev/null +++ b/openchat_3.5-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12c68c3c6293e5bcdab2025153a1439d7391c832bc789af4aa00478e1cf6428f +size 4108928064 diff --git a/openchat_3.5-Q4_K_M.gguf b/openchat_3.5-Q4_K_M.gguf new file mode 100644 index 0000000..f0bf6e0 --- /dev/null +++ b/openchat_3.5-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d57d81a2eed62f34408cb0db03818a51e7ca49cab2ea63d68f0bb1ee0d25bf15 +size 4368450624 diff --git a/openchat_3.5-Q4_K_S.gguf b/openchat_3.5-Q4_K_S.gguf new file mode 100644 index 0000000..1032a5d --- /dev/null +++ b/openchat_3.5-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70de5c4800c172f4bdfa3158243dda533de0c0f314c688d4c38e10180953aad8 +size 4140385344 diff --git a/openchat_3.5-Q5_0.gguf b/openchat_3.5-Q5_0.gguf new file mode 100644 index 0000000..4b99a63 --- /dev/null +++ b/openchat_3.5-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ef65c6363d7aa99db0156db7e5f8cdc4bc2f424be9d551ecc260c9d5d77c898 +size 4997728320 diff --git a/openchat_3.5-Q5_K_M.gguf b/openchat_3.5-Q5_K_M.gguf new file mode 100644 index 0000000..f0c0d01 --- /dev/null +++ b/openchat_3.5-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cea9e09a3e1d0fa779224710a543a07d92af46a64090af7a32001b94faf66a92 +size 5131421760 diff --git a/openchat_3.5-Q5_K_S.gguf b/openchat_3.5-Q5_K_S.gguf new file mode 100644 index 0000000..542ac95 --- /dev/null +++ b/openchat_3.5-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a72a7a30612df0378f4bfb30dc30f58922cb85b04c1aa2a21f5c3d01b3494819 +size 4997728320 diff --git a/openchat_3.5-Q6_K.gguf b/openchat_3.5-Q6_K.gguf new file mode 100644 index 0000000..d6bc364 --- /dev/null +++ b/openchat_3.5-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:905d216a9f9d1b653668ae4fae0222a48d1a576d4043228cdf0ae2e24785d610 +size 5942078592 diff --git a/openchat_3.5-Q8_0.gguf b/openchat_3.5-Q8_0.gguf new file mode 100644 index 0000000..7c6163e --- /dev/null +++ b/openchat_3.5-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:787cc439ae6c90ffe3fcb977c3b0f84c5978f3cbb8e55f67973d349839c218b9 +size 7695875072 diff --git a/openchat_3.5.Q5_K_M.gguf b/openchat_3.5.Q5_K_M.gguf new file mode 100644 index 0000000..6b89c0f --- /dev/null +++ b/openchat_3.5.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3abf26b0f2ff11394351a23f8d538a1404a2afb69465a6bbaba8836fef51899d +size 5131421440