From dc9c84a817287e260a2e30fa7dcb7b17e99e93e7 Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:12:46 +0700 Subject: [PATCH 01/16] fix(yarn-mistral): broken gguf model --- models/yarn-mistral-7b/model.json | 31 ------------------------------- 1 file changed, 31 deletions(-) delete mode 100644 models/yarn-mistral-7b/model.json diff --git a/models/yarn-mistral-7b/model.json b/models/yarn-mistral-7b/model.json deleted file mode 100644 index ee6de1319..000000000 --- a/models/yarn-mistral-7b/model.json +++ /dev/null @@ -1,31 +0,0 @@ -{ - "sources": [ - { - "url": "https://huggingface.co/TheBloke/Yarn-Mistral-7B-128k-GGUF/resolve/main/yarn-mistral-7b-128k.Q4_K_M.gguf" - } - ], - "id": "yarn-mistral-7b", - "object": "model", - "name": "Yarn Mistral 7B Q4", - "version": "1.0", - "description": "Yarn Mistral 7B is a language model for long context and supports a 128k token context window.", - "format": "gguf", - "settings": { - "ctx_len": 4096, - "prompt_template": "{prompt}" - }, - "parameters": { - "temperature": 0.7, - "top_p": 0.95, - "stream": true, - "max_tokens": 4096, - "frequency_penalty": 0, - "presence_penalty": 0 - }, - "metadata": { - "author": "NousResearch, The Bloke", - "tags": ["7B", "Finetuned"], - "size": 4370000000 - }, - "engine": "nitro" -} From 73171c8fd3be748cb2df98762706ebd25aaf7e98 Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:31:05 +0700 Subject: [PATCH 02/16] add(dolphin phi2): add new best 3b model --- models/dolphin-phi-2/model.json | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 models/dolphin-phi-2/model.json diff --git a/models/dolphin-phi-2/model.json b/models/dolphin-phi-2/model.json new file mode 100644 index 000000000..3842e0a56 --- /dev/null +++ b/models/dolphin-phi-2/model.json @@ -0,0 +1,32 @@ +{ + "source": [ + { + "url": "https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF/resolve/main/dolphin-2_6-phi-2.Q4_K_M.gguf", + "filename": "dolphin-2_6-phi-2.Q4_K_M.gguf" + } + ], + "id": "dolphin-phi-2", + "object": "model", + "name": "Dolphin Phi-2 2.7B Q4", + "version": "1.0", + "description": "Dolphin Phi-2 is a 2.7B model, fine-tuned for chat, excelling in common sense and logical reasoning benchmarks.", + "format": "gguf", + "settings": { + "ctx_len": 4096, + "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n", + "llama_model_path": "dolphin-2_6-phi-2.Q4_K_M.gguf" + }, + "parameters": { + "max_tokens": 4096, + "stop": ["<|im_end|>"] + }, + "metadata": { + "author": "Cognitive Computations, Microsoft", + "tags": [ + "3B", + "Chat Model" + ], + "size": 1790000000 + }, + "engine": "nitro" + } \ No newline at end of file From 693c4e890a9f2aa5e360daac3d9fa488c874c79f Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:33:23 +0700 Subject: [PATCH 03/16] add(stablezephyr): add new stable 3b model --- models/dolphin-phi-2/model.json | 12 +++++------ models/stable-zephyr-3b/model.json | 34 ++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+), 6 deletions(-) create mode 100644 models/stable-zephyr-3b/model.json diff --git a/models/dolphin-phi-2/model.json b/models/dolphin-phi-2/model.json index 3842e0a56..c7348c359 100644 --- a/models/dolphin-phi-2/model.json +++ b/models/dolphin-phi-2/model.json @@ -1,20 +1,20 @@ { "source": [ { - "url": "https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF/resolve/main/dolphin-2_6-phi-2.Q4_K_M.gguf", - "filename": "dolphin-2_6-phi-2.Q4_K_M.gguf" + "url": "https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF/resolve/main/dolphin-2_6-phi-2.Q8_0.gguf", + "filename": "dolphin-2_6-phi-2.Q8_0.gguf" } ], "id": "dolphin-phi-2", "object": "model", - "name": "Dolphin Phi-2 2.7B Q4", + "name": "Dolphin Phi-2 2.7B Q8", "version": "1.0", "description": "Dolphin Phi-2 is a 2.7B model, fine-tuned for chat, excelling in common sense and logical reasoning benchmarks.", "format": "gguf", "settings": { "ctx_len": 4096, "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n", - "llama_model_path": "dolphin-2_6-phi-2.Q4_K_M.gguf" + "llama_model_path": "dolphin-2_6-phi-2.Q8_0.gguf" }, "parameters": { "max_tokens": 4096, @@ -24,9 +24,9 @@ "author": "Cognitive Computations, Microsoft", "tags": [ "3B", - "Chat Model" + "Finetuned" ], - "size": 1790000000 + "size": 2960000000 }, "engine": "nitro" } \ No newline at end of file diff --git a/models/stable-zephyr-3b/model.json b/models/stable-zephyr-3b/model.json new file mode 100644 index 000000000..f5df3dd76 --- /dev/null +++ b/models/stable-zephyr-3b/model.json @@ -0,0 +1,34 @@ +{ + "source": [ + { + "url": "https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF/resolve/main/stablelm-zephyr-3b.Q8_0.gguf", + "filename": "stablelm-zephyr-3b.Q8_0.gguf" + } + ], + "id": "stable-zephyr-3b", + "object": "model", + "name": "Stable Zephyr 3B Q8", + "version": "1.0", + "description": "StableLM Zephyr 3B is trained on a mix of publicly and synthetic datasets. It's focus on safety and reliability.", + "format": "gguf", + "settings": { + "ctx_len": 4096, + "prompt_template": "<|user|>\n{prompt}<|endoftext|>\n<|assistant|>", + "llama_model_path": "stablelm-zephyr-3b.Q8_0.gguf" + }, + "parameters": { + "temperature": 0.7, + "top_p": 0.95, + "stream": true, + "max_tokens": 4096, + "stop": ["<|endoftext|>"], + "frequency_penalty": 0, + "presence_penalty": 0 + }, + "metadata": { + "author": "StabilityAI", + "tags": ["3B", "Finetuned"], + "size": 2970000000 + }, + "engine": "nitro" + } \ No newline at end of file From 6c27bb8200366c2e1c74c90279b4e0bc114e704d Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:36:33 +0700 Subject: [PATCH 04/16] add(llamacorn): add new stable 1b model --- models/llamacorn-1.1b/model.json | 38 ++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 models/llamacorn-1.1b/model.json diff --git a/models/llamacorn-1.1b/model.json b/models/llamacorn-1.1b/model.json new file mode 100644 index 000000000..a66119648 --- /dev/null +++ b/models/llamacorn-1.1b/model.json @@ -0,0 +1,38 @@ +{ + "source": [ + { + "url":"https://huggingface.co/janhq/llamacorn-1.1b-chat-GGUF/resolve/main/llamacorn-1.1b-chat.Q8_0.gguf", + "filename": "llamacorn-1.1b-chat.Q8_0.gguf" + } + ], + "id": "llamacorn-1.1b", + "object": "model", + "name": "LlamaCorn 1.1B Q8", + "version": "1.0", + "description": "LlamaCorn is designed to improve chat functionality from TinyLlama.", + "format": "gguf", + "settings": { + "ctx_len": 2048, + "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant", + "llama_model_path": "llamacorn-1.1b-chat.Q8_0.gguf" + }, + "parameters": { + "temperature": 0.7, + "top_p": 0.95, + "stream": true, + "max_tokens": 2048, + "stop": [], + "frequency_penalty": 0, + "presence_penalty": 0 + }, + "metadata": { + "author": "Jan", + "tags": [ + "7B", + "Finetuned", + "Featured" + ], + "size": 1170000000 + }, + "engine": "nitro" + } \ No newline at end of file From 8cda7685ec3bfc11e7e2febf5b48d02da08b067b Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:37:06 +0700 Subject: [PATCH 05/16] add(llamacorn): correct tags --- models/llamacorn-1.1b/model.json | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/models/llamacorn-1.1b/model.json b/models/llamacorn-1.1b/model.json index a66119648..7e5ff0cea 100644 --- a/models/llamacorn-1.1b/model.json +++ b/models/llamacorn-1.1b/model.json @@ -28,9 +28,8 @@ "metadata": { "author": "Jan", "tags": [ - "7B", - "Finetuned", - "Featured" + "Tiny", + "Finetuned" ], "size": 1170000000 }, From 259ae3c24b6ca77211a89442923c0b1c864a9371 Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:38:57 +0700 Subject: [PATCH 06/16] fix(stable zephyr): update description --- models/stable-zephyr-3b/model.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/models/stable-zephyr-3b/model.json b/models/stable-zephyr-3b/model.json index f5df3dd76..ab18d690b 100644 --- a/models/stable-zephyr-3b/model.json +++ b/models/stable-zephyr-3b/model.json @@ -9,7 +9,7 @@ "object": "model", "name": "Stable Zephyr 3B Q8", "version": "1.0", - "description": "StableLM Zephyr 3B is trained on a mix of publicly and synthetic datasets. It's focus on safety and reliability.", + "description": "StableLM Zephyr 3B is trained for safe and reliable chatting.", "format": "gguf", "settings": { "ctx_len": 4096, From fc04c1664edd70caf0c11cccb75d045d3af9e9ee Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:42:16 +0700 Subject: [PATCH 07/16] fix(model extension): pump to 1.0.24 --- extensions/model-extension/package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/extensions/model-extension/package.json b/extensions/model-extension/package.json index 86f177d14..f5609e1d5 100644 --- a/extensions/model-extension/package.json +++ b/extensions/model-extension/package.json @@ -1,6 +1,6 @@ { "name": "@janhq/model-extension", - "version": "1.0.23", + "version": "1.0.24", "description": "Model Management Extension provides model exploration and seamless downloads", "main": "dist/index.js", "module": "dist/module.js", From a1ac7f9eb35947ad6a2c49cd33a956721a4c422f Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:12:46 +0700 Subject: [PATCH 08/16] fix(yarn-mistral): broken gguf model --- models/yarn-mistral-7b/model.json | 31 ------------------------------- 1 file changed, 31 deletions(-) delete mode 100644 models/yarn-mistral-7b/model.json diff --git a/models/yarn-mistral-7b/model.json b/models/yarn-mistral-7b/model.json deleted file mode 100644 index ee6de1319..000000000 --- a/models/yarn-mistral-7b/model.json +++ /dev/null @@ -1,31 +0,0 @@ -{ - "sources": [ - { - "url": "https://huggingface.co/TheBloke/Yarn-Mistral-7B-128k-GGUF/resolve/main/yarn-mistral-7b-128k.Q4_K_M.gguf" - } - ], - "id": "yarn-mistral-7b", - "object": "model", - "name": "Yarn Mistral 7B Q4", - "version": "1.0", - "description": "Yarn Mistral 7B is a language model for long context and supports a 128k token context window.", - "format": "gguf", - "settings": { - "ctx_len": 4096, - "prompt_template": "{prompt}" - }, - "parameters": { - "temperature": 0.7, - "top_p": 0.95, - "stream": true, - "max_tokens": 4096, - "frequency_penalty": 0, - "presence_penalty": 0 - }, - "metadata": { - "author": "NousResearch, The Bloke", - "tags": ["7B", "Finetuned"], - "size": 4370000000 - }, - "engine": "nitro" -} From 48a6be558dd546a47b85e7e0c249a8058b9bfd1a Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:31:05 +0700 Subject: [PATCH 09/16] add(dolphin phi2): add new best 3b model --- models/dolphin-phi-2/model.json | 32 ++++++++++++++++++++++++++++++++ 1 file changed, 32 insertions(+) create mode 100644 models/dolphin-phi-2/model.json diff --git a/models/dolphin-phi-2/model.json b/models/dolphin-phi-2/model.json new file mode 100644 index 000000000..3842e0a56 --- /dev/null +++ b/models/dolphin-phi-2/model.json @@ -0,0 +1,32 @@ +{ + "source": [ + { + "url": "https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF/resolve/main/dolphin-2_6-phi-2.Q4_K_M.gguf", + "filename": "dolphin-2_6-phi-2.Q4_K_M.gguf" + } + ], + "id": "dolphin-phi-2", + "object": "model", + "name": "Dolphin Phi-2 2.7B Q4", + "version": "1.0", + "description": "Dolphin Phi-2 is a 2.7B model, fine-tuned for chat, excelling in common sense and logical reasoning benchmarks.", + "format": "gguf", + "settings": { + "ctx_len": 4096, + "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n", + "llama_model_path": "dolphin-2_6-phi-2.Q4_K_M.gguf" + }, + "parameters": { + "max_tokens": 4096, + "stop": ["<|im_end|>"] + }, + "metadata": { + "author": "Cognitive Computations, Microsoft", + "tags": [ + "3B", + "Chat Model" + ], + "size": 1790000000 + }, + "engine": "nitro" + } \ No newline at end of file From 698f1f5bfdac0412116983c3d8927638b2ecec6d Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:33:23 +0700 Subject: [PATCH 10/16] add(stablezephyr): add new stable 3b model --- models/dolphin-phi-2/model.json | 12 +++++------ models/stable-zephyr-3b/model.json | 34 ++++++++++++++++++++++++++++++ 2 files changed, 40 insertions(+), 6 deletions(-) create mode 100644 models/stable-zephyr-3b/model.json diff --git a/models/dolphin-phi-2/model.json b/models/dolphin-phi-2/model.json index 3842e0a56..c7348c359 100644 --- a/models/dolphin-phi-2/model.json +++ b/models/dolphin-phi-2/model.json @@ -1,20 +1,20 @@ { "source": [ { - "url": "https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF/resolve/main/dolphin-2_6-phi-2.Q4_K_M.gguf", - "filename": "dolphin-2_6-phi-2.Q4_K_M.gguf" + "url": "https://huggingface.co/TheBloke/dolphin-2_6-phi-2-GGUF/resolve/main/dolphin-2_6-phi-2.Q8_0.gguf", + "filename": "dolphin-2_6-phi-2.Q8_0.gguf" } ], "id": "dolphin-phi-2", "object": "model", - "name": "Dolphin Phi-2 2.7B Q4", + "name": "Dolphin Phi-2 2.7B Q8", "version": "1.0", "description": "Dolphin Phi-2 is a 2.7B model, fine-tuned for chat, excelling in common sense and logical reasoning benchmarks.", "format": "gguf", "settings": { "ctx_len": 4096, "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n", - "llama_model_path": "dolphin-2_6-phi-2.Q4_K_M.gguf" + "llama_model_path": "dolphin-2_6-phi-2.Q8_0.gguf" }, "parameters": { "max_tokens": 4096, @@ -24,9 +24,9 @@ "author": "Cognitive Computations, Microsoft", "tags": [ "3B", - "Chat Model" + "Finetuned" ], - "size": 1790000000 + "size": 2960000000 }, "engine": "nitro" } \ No newline at end of file diff --git a/models/stable-zephyr-3b/model.json b/models/stable-zephyr-3b/model.json new file mode 100644 index 000000000..f5df3dd76 --- /dev/null +++ b/models/stable-zephyr-3b/model.json @@ -0,0 +1,34 @@ +{ + "source": [ + { + "url": "https://huggingface.co/TheBloke/stablelm-zephyr-3b-GGUF/resolve/main/stablelm-zephyr-3b.Q8_0.gguf", + "filename": "stablelm-zephyr-3b.Q8_0.gguf" + } + ], + "id": "stable-zephyr-3b", + "object": "model", + "name": "Stable Zephyr 3B Q8", + "version": "1.0", + "description": "StableLM Zephyr 3B is trained on a mix of publicly and synthetic datasets. It's focus on safety and reliability.", + "format": "gguf", + "settings": { + "ctx_len": 4096, + "prompt_template": "<|user|>\n{prompt}<|endoftext|>\n<|assistant|>", + "llama_model_path": "stablelm-zephyr-3b.Q8_0.gguf" + }, + "parameters": { + "temperature": 0.7, + "top_p": 0.95, + "stream": true, + "max_tokens": 4096, + "stop": ["<|endoftext|>"], + "frequency_penalty": 0, + "presence_penalty": 0 + }, + "metadata": { + "author": "StabilityAI", + "tags": ["3B", "Finetuned"], + "size": 2970000000 + }, + "engine": "nitro" + } \ No newline at end of file From f22ad8adb97032ff54b48181a4800d1682b602ff Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:36:33 +0700 Subject: [PATCH 11/16] add(llamacorn): add new stable 1b model --- models/llamacorn-1.1b/model.json | 38 ++++++++++++++++++++++++++++++++ 1 file changed, 38 insertions(+) create mode 100644 models/llamacorn-1.1b/model.json diff --git a/models/llamacorn-1.1b/model.json b/models/llamacorn-1.1b/model.json new file mode 100644 index 000000000..a66119648 --- /dev/null +++ b/models/llamacorn-1.1b/model.json @@ -0,0 +1,38 @@ +{ + "source": [ + { + "url":"https://huggingface.co/janhq/llamacorn-1.1b-chat-GGUF/resolve/main/llamacorn-1.1b-chat.Q8_0.gguf", + "filename": "llamacorn-1.1b-chat.Q8_0.gguf" + } + ], + "id": "llamacorn-1.1b", + "object": "model", + "name": "LlamaCorn 1.1B Q8", + "version": "1.0", + "description": "LlamaCorn is designed to improve chat functionality from TinyLlama.", + "format": "gguf", + "settings": { + "ctx_len": 2048, + "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant", + "llama_model_path": "llamacorn-1.1b-chat.Q8_0.gguf" + }, + "parameters": { + "temperature": 0.7, + "top_p": 0.95, + "stream": true, + "max_tokens": 2048, + "stop": [], + "frequency_penalty": 0, + "presence_penalty": 0 + }, + "metadata": { + "author": "Jan", + "tags": [ + "7B", + "Finetuned", + "Featured" + ], + "size": 1170000000 + }, + "engine": "nitro" + } \ No newline at end of file From 25d7c6a0b5acb4c8ebc223ae48fa601f9e022079 Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:37:06 +0700 Subject: [PATCH 12/16] add(llamacorn): correct tags --- models/llamacorn-1.1b/model.json | 5 ++--- 1 file changed, 2 insertions(+), 3 deletions(-) diff --git a/models/llamacorn-1.1b/model.json b/models/llamacorn-1.1b/model.json index a66119648..7e5ff0cea 100644 --- a/models/llamacorn-1.1b/model.json +++ b/models/llamacorn-1.1b/model.json @@ -28,9 +28,8 @@ "metadata": { "author": "Jan", "tags": [ - "7B", - "Finetuned", - "Featured" + "Tiny", + "Finetuned" ], "size": 1170000000 }, From 8d81c7eb418cbd66fd15f022f4a448ff056f118c Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:38:57 +0700 Subject: [PATCH 13/16] fix(stable zephyr): update description --- models/stable-zephyr-3b/model.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/models/stable-zephyr-3b/model.json b/models/stable-zephyr-3b/model.json index f5df3dd76..ab18d690b 100644 --- a/models/stable-zephyr-3b/model.json +++ b/models/stable-zephyr-3b/model.json @@ -9,7 +9,7 @@ "object": "model", "name": "Stable Zephyr 3B Q8", "version": "1.0", - "description": "StableLM Zephyr 3B is trained on a mix of publicly and synthetic datasets. It's focus on safety and reliability.", + "description": "StableLM Zephyr 3B is trained for safe and reliable chatting.", "format": "gguf", "settings": { "ctx_len": 4096, From 76bff3bede677437d90ee0ee5932f3441cfe485b Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 29 Jan 2024 10:42:16 +0700 Subject: [PATCH 14/16] fix(model extension): pump to 1.0.24 --- extensions/model-extension/package.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/extensions/model-extension/package.json b/extensions/model-extension/package.json index 86f177d14..f5609e1d5 100644 --- a/extensions/model-extension/package.json +++ b/extensions/model-extension/package.json @@ -1,6 +1,6 @@ { "name": "@janhq/model-extension", - "version": "1.0.23", + "version": "1.0.24", "description": "Model Management Extension provides model exploration and seamless downloads", "main": "dist/index.js", "module": "dist/module.js", From 24dd13a305dbb27dac14abaa0a709bde8aeb27bc Mon Sep 17 00:00:00 2001 From: Hoang Ha <64120343+hahuyhoang411@users.noreply.github.com> Date: Mon, 5 Feb 2024 11:20:49 +0700 Subject: [PATCH 15/16] fix(dolphin-phi): redundant of new lines character --- models/dolphin-phi-2/model.json | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/models/dolphin-phi-2/model.json b/models/dolphin-phi-2/model.json index c7348c359..ae82041fc 100644 --- a/models/dolphin-phi-2/model.json +++ b/models/dolphin-phi-2/model.json @@ -13,7 +13,7 @@ "format": "gguf", "settings": { "ctx_len": 4096, - "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant\n", + "prompt_template": "<|im_start|>system\n{system_message}<|im_end|>\n<|im_start|>user\n{prompt}<|im_end|>\n<|im_start|>assistant", "llama_model_path": "dolphin-2_6-phi-2.Q8_0.gguf" }, "parameters": { @@ -29,4 +29,4 @@ "size": 2960000000 }, "engine": "nitro" - } \ No newline at end of file + } From 2b0bc9f790a3493ccc5fd658bcceb11ce35a5013 Mon Sep 17 00:00:00 2001 From: hahuyhoang411 Date: Mon, 19 Feb 2024 09:54:41 +0700 Subject: [PATCH 16/16] update(openchat-3.5): pump to the latest version --- models/openchat-3.5-7b/model.json | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/models/openchat-3.5-7b/model.json b/models/openchat-3.5-7b/model.json index 294f7d269..18db33f8e 100644 --- a/models/openchat-3.5-7b/model.json +++ b/models/openchat-3.5-7b/model.json @@ -1,8 +1,8 @@ { "sources": [ { - "filename": "openchat-3.5-1210.Q4_K_M.gguf", - "url": "https://huggingface.co/TheBloke/openchat-3.5-1210-GGUF/resolve/main/openchat-3.5-1210.Q4_K_M.gguf" + "filename": "openchat-3.5-0106.Q4_K_M.gguf", + "url": "https://huggingface.co/TheBloke/openchat-3.5-0106-GGUF/resolve/main/openchat-3.5-0106.Q4_K_M.gguf" } ], "id": "openchat-3.5-7b", @@ -14,7 +14,7 @@ "settings": { "ctx_len": 4096, "prompt_template": "GPT4 Correct User: {prompt}<|end_of_turn|>GPT4 Correct Assistant:", - "llama_model_path": "openchat-3.5-1210.Q4_K_M.gguf" + "llama_model_path": "openchat-3.5-0106.Q4_K_M.gguf" }, "parameters": { "temperature": 0.7,