commit a45fe74a56465866487eb5f448b4c424e7a6a552 Author: ModelHub XC Date: Wed May 27 00:56:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: second-state/Yi-6B-Chat-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..dc51a57 --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +base_model: 01-ai/Yi-6B-Chat +inference: false +license: other +license_link: LICENSE +license_name: yi-license +model_creator: 01-ai +model_name: Yi 6B Chat +model_type: yi +pipeline_tag: text-generation +quantized_by: Second State Inc. +--- + + + +
+ +
+
+ + +# Yi-34B-Chat-GGUF + +## Original Model + +[01-ai/Yi-6B-Chat](https://huggingface.co/01-ai/Yi-6B-Chat) + +## Run with LlamaEdge + +- LlamaEdge version: [v0.2.15](https://github.com/LlamaEdge/LlamaEdge/releases/tag/0.2.15) 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 + ``` + + - Reverse prompt: `<|im_end|>` + +- Context size: `4096` + +- Run as LlamaEdge service + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-6B-Chat-Q5_K_M.gguf llama-api-server.wasm -p chatml -r '<|im_end|>' + ``` + +- Run as LlamaEdge command app + + ```bash + wasmedge --dir .:. --nn-preload default:GGML:AUTO:Yi-6B-Chat-Q5_K_M.gguf llama-chat.wasm -p chatml -r '<|im_end|>' + ``` + +## Quantized GGUF Models + +| Name | Quant method | Bits | Size | Use case | +| ---- | ---- | ---- | ---- | ----- | +| [Yi-6B-Chat-Q2_K.gguf](https://huggingface.co/second-state/Yi-6B-Chat-GGUF/blob/main/Yi-6B-Chat-Q2_K.gguf) | Q2_K | 2 |2.34 GB| smallest, significant quality loss - not recommended for most purposes | +| [Yi-6B-Chat-Q3_K_L.gguf](https://huggingface.co/second-state/Yi-6B-Chat-GGUF/blob/main/Yi-6B-Chat-Q3_K_L.gguf) | Q3_K_L | 3 | 3.24 GB| small, substantial quality loss | +| [Yi-6B-Chat-Q3_K_M.gguf](https://huggingface.co/second-state/Yi-6B-Chat-GGUF/blob/main/Yi-6B-Chat-Q3_K_M.gguf) | Q3_K_M | 3 | 2.99 GB| very small, high quality loss | +| [Yi-6B-Chat-Q3_K_S.gguf](https://huggingface.co/second-state/Yi-6B-Chat-GGUF/blob/main/Yi-6B-Chat-Q3_K_S.gguf) | Q3_K_S | 3 | 2.71 GB| very small, high quality loss | +| [Yi-6B-Chat-Q4_0.gguf](https://huggingface.co/second-state/Yi-6B-Chat-GGUF/blob/main/Yi-6B-Chat-Q4_0.gguf) | Q4_0 | 4 | 3.48 GB| legacy; small, very high quality loss - prefer using Q3_K_M | +| [Yi-6B-Chat-Q4_K_M.gguf](https://huggingface.co/second-state/Yi-6B-Chat-GGUF/blob/main/Yi-6B-Chat-Q4_K_M.gguf) | Q4_K_M | 4 | 3.67 GB| medium, balanced quality - recommended | +| [Yi-6B-Chat-Q4_K_S.gguf](https://huggingface.co/second-state/Yi-6B-Chat-GGUF/blob/main/Yi-6B-Chat-Q4_K_S.gguf) | Q4_K_S | 4 | 3.50 GB| small, greater quality loss | +| [Yi-6B-Chat-Q5_0.gguf](https://huggingface.co/second-state/Yi-6B-Chat-GGUF/blob/main/Yi-6B-Chat-Q5_0.gguf) | Q5_0 | 5 | 4.20 GB| legacy; medium, balanced quality - prefer using Q4_K_M | +| [Yi-6B-Chat-Q5_K_M.gguf](https://huggingface.co/second-state/Yi-6B-Chat-GGUF/blob/main/Yi-6B-Chat-Q5_K_M.gguf) | Q5_K_M | 5 | 4.30 GB| large, very low quality loss - recommended | +| [Yi-6B-Chat-Q5_K_S.gguf](https://huggingface.co/second-state/Yi-6B-Chat-GGUF/blob/main/Yi-6B-Chat-Q5_K_S.gguf) | Q5_K_S | 5 | 4.20 GB| large, low quality loss - recommended | +| [Yi-6B-Chat-Q6_K.gguf](https://huggingface.co/second-state/Yi-6B-Chat-GGUF/blob/main/Yi-6B-Chat-Q6_K.gguf) | Q6_K | 6 | 4.97 GB| very large, extremely low quality loss | +| [Yi-6B-Chat-Q8_0.gguf](https://huggingface.co/second-state/Yi-6B-Chat-GGUF/blob/main/Yi-6B-Chat-Q8_0.gguf) | Q8_0 | 8 | 6.44 GB| very large, extremely low quality loss - not recommended | diff --git a/Yi-6B-Chat-Q2_K.gguf b/Yi-6B-Chat-Q2_K.gguf new file mode 100644 index 0000000..1a88d0d --- /dev/null +++ b/Yi-6B-Chat-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc806602f79ed2aebe424008cbfc686e170eaf3b4737ac48e2112d0d2f753ec3 +size 2337066560 diff --git a/Yi-6B-Chat-Q3_K_L.gguf b/Yi-6B-Chat-Q3_K_L.gguf new file mode 100644 index 0000000..da77fa7 --- /dev/null +++ b/Yi-6B-Chat-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccdd89d615949ad4dbb91bfea8bcec78a10c9ac9b765079cae6e6b39f91eeff1 +size 3236892224 diff --git a/Yi-6B-Chat-Q3_K_M.gguf b/Yi-6B-Chat-Q3_K_M.gguf new file mode 100644 index 0000000..e852b16 --- /dev/null +++ b/Yi-6B-Chat-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75626fc7ea6c4e01a41170bbc43124a6bd2963b493a78b46b328d599f0529592 +size 2992836160 diff --git a/Yi-6B-Chat-Q3_K_S.gguf b/Yi-6B-Chat-Q3_K_S.gguf new file mode 100644 index 0000000..adfa3ec --- /dev/null +++ b/Yi-6B-Chat-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb3e35dd5b243380804f3d38308acc35cef7b75f8204ab8a9a276a8656cb819a +size 2709196352 diff --git a/Yi-6B-Chat-Q4_0.gguf b/Yi-6B-Chat-Q4_0.gguf new file mode 100644 index 0000000..05c66fc --- /dev/null +++ b/Yi-6B-Chat-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b952595b8f04e799c2d89d580f643a4b18a97af2496c89916def76fb8b2b5e8 +size 3479326272 diff --git a/Yi-6B-Chat-Q4_K_M.gguf b/Yi-6B-Chat-Q4_K_M.gguf new file mode 100644 index 0000000..9cfae42 --- /dev/null +++ b/Yi-6B-Chat-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d576bd9326c2c33e0fa1cb06126c9142b87124209471e50c84c6784061d89f21 +size 3673968192 diff --git a/Yi-6B-Chat-Q4_K_S.gguf b/Yi-6B-Chat-Q4_K_S.gguf new file mode 100644 index 0000000..9541bcb --- /dev/null +++ b/Yi-6B-Chat-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5050681a0f9f8aff8836cd8b873f01a99c36758214958952e8f68064dfb80cce +size 3502919232 diff --git a/Yi-6B-Chat-Q5_0.gguf b/Yi-6B-Chat-Q5_0.gguf new file mode 100644 index 0000000..7987512 --- /dev/null +++ b/Yi-6B-Chat-Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:638bb22db311dec304a100f08481b20d2c735bc1e16d3c38c6badd1a6d141a3a +size 4204154432 diff --git a/Yi-6B-Chat-Q5_K_M.gguf b/Yi-6B-Chat-Q5_K_M.gguf new file mode 100644 index 0000000..2922f8f --- /dev/null +++ b/Yi-6B-Chat-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b2388e48016f2730233286794a25ff4210a0cae0bf79199cf1f834a591b1527 +size 4304424512 diff --git a/Yi-6B-Chat-Q5_K_S.gguf b/Yi-6B-Chat-Q5_K_S.gguf new file mode 100644 index 0000000..a8c56ac --- /dev/null +++ b/Yi-6B-Chat-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bc210a78a21ac0a8e1780ee4b44372f2918ddfa6e63bf115d9a147dbe2ed6cb +size 4204154432 diff --git a/Yi-6B-Chat-Q6_K.gguf b/Yi-6B-Chat-Q6_K.gguf new file mode 100644 index 0000000..3ecebda --- /dev/null +++ b/Yi-6B-Chat-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e0052b8971dcbc21f73d12db00526f0325851b0b26c597fea868f5f5dd2276b +size 4974284352 diff --git a/Yi-6B-Chat-Q8_0.gguf b/Yi-6B-Chat-Q8_0.gguf new file mode 100644 index 0000000..8ea21b1 --- /dev/null +++ b/Yi-6B-Chat-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e98959bfa3bddc221eb45ba9d870174844e7de9e9b8f05e0b953e100e5ebe343 +size 6442126912 diff --git a/config.json b/config.json new file mode 100644 index 0000000..d00a870 --- /dev/null +++ b/config.json @@ -0,0 +1,26 @@ +{ + "architectures": [ + "LlamaForCausalLM" + ], + "attention_bias": false, + "bos_token_id": 1, + "eos_token_id": 2, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 11008, + "max_position_embeddings": 4096, + "model_type": "llama", + "num_attention_heads": 32, + "num_hidden_layers": 32, + "num_key_value_heads": 4, + "pretraining_tp": 1, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 5000000.0, + "tie_word_embeddings": false, + "torch_dtype": "bfloat16", + "transformers_version": "4.35.0", + "use_cache": true, + "vocab_size": 64000 +} 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