commit e2fd191d3356e10d1124744bab8d09f3c0a49649 Author: ModelHub XC Date: Tue Apr 21 23:39:28 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: afrideva/Llama-68M-Chat-v1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..d542f97 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,42 @@ +*.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 +llama-68m-chat-v1.fp16.gguf filter=lfs diff=lfs merge=lfs -text +llama-68m-chat-v1.q2_k.gguf filter=lfs diff=lfs merge=lfs -text +llama-68m-chat-v1.q3_k_m.gguf filter=lfs diff=lfs merge=lfs -text +llama-68m-chat-v1.q4_k_m.gguf filter=lfs diff=lfs merge=lfs -text +llama-68m-chat-v1.q5_k_m.gguf filter=lfs diff=lfs merge=lfs -text +llama-68m-chat-v1.q6_k.gguf filter=lfs diff=lfs merge=lfs -text +llama-68m-chat-v1.q8_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..8d53b55 --- /dev/null +++ b/README.md @@ -0,0 +1,143 @@ +--- +base_model: Felladrin/Llama-68M-Chat-v1 +datasets: +- THUDM/webglm-qa +- databricks/databricks-dolly-15k +- cognitivecomputations/wizard_vicuna_70k_unfiltered +- totally-not-an-llm/EverythingLM-data-V3 +- Amod/mental_health_counseling_conversations +- sablo/oasst2_curated +- starfishmedical/webGPT_x_dolly +- Open-Orca/OpenOrca +- mlabonne/chatml_dpo_pairs +inference: false +language: +- en +license: apache-2.0 +model_creator: Felladrin +model_name: Llama-68M-Chat-v1 +pipeline_tag: text-generation +quantized_by: afrideva +tags: +- text-generation +- gguf +- ggml +- quantized +- q2_k +- q3_k_m +- q4_k_m +- q5_k_m +- q6_k +- q8_0 +widget: +- text: '<|im_start|>system + + You are a knowledgeable assistant. Help the user as much as you can.<|im_end|> + + <|im_start|>user + + How to become healthier?<|im_end|> + + <|im_start|>assistant' +- text: '<|im_start|>system + + You are a career counselor. The user will provide you with an individual looking + for guidance in their professional life, and your task is to assist them in determining + what careers they are most suited for based on their skills, interests, and experience. + You should also conduct research into the various options available, explain the + job market trends in different industries, and advice on which qualifications + would be beneficial for pursuing particular fields.<|im_end|> + + <|im_start|>user + + Heya!<|im_end|> + + <|im_start|>assistant + + Hi! How may I help you?<|im_end|> + + <|im_start|>user + + I am interested in developing a career in software engineering. What would you + recommend me to do?<|im_end|> + + <|im_start|>assistant' +- text: '<|im_start|>system + + You are a helpful assistant who provides concise responses.<|im_end|> + + <|im_start|>user + + Hi!<|im_end|> + + <|im_start|>assistant + + Hello there! How may I help you?<|im_end|> + + <|im_start|>user + + I need to build a simple website. Where should I start learning about web development?<|im_end|> + + <|im_start|>assistant' +- text: '<|im_start|>system + + You are a very creative assistant. User will give you a task, which you should + complete with all your knowledge.<|im_end|> + + <|im_start|>user + + Write the background story of an RPG game about wizards and dragons in a sci-fi + world.<|im_end|> + + <|im_start|>assistant' +--- +# Felladrin/Llama-68M-Chat-v1-GGUF + +Quantized GGUF model files for [Llama-68M-Chat-v1](https://huggingface.co/Felladrin/Llama-68M-Chat-v1) from [Felladrin](https://huggingface.co/Felladrin) + + +| Name | Quant method | Size | +| ---- | ---- | ---- | +| [llama-68m-chat-v1.fp16.gguf](https://huggingface.co/afrideva/Llama-68M-Chat-v1-GGUF/resolve/main/llama-68m-chat-v1.fp16.gguf) | fp16 | 136.79 MB | +| [llama-68m-chat-v1.q2_k.gguf](https://huggingface.co/afrideva/Llama-68M-Chat-v1-GGUF/resolve/main/llama-68m-chat-v1.q2_k.gguf) | q2_k | 35.88 MB | +| [llama-68m-chat-v1.q3_k_m.gguf](https://huggingface.co/afrideva/Llama-68M-Chat-v1-GGUF/resolve/main/llama-68m-chat-v1.q3_k_m.gguf) | q3_k_m | 40.66 MB | +| [llama-68m-chat-v1.q4_k_m.gguf](https://huggingface.co/afrideva/Llama-68M-Chat-v1-GGUF/resolve/main/llama-68m-chat-v1.q4_k_m.gguf) | q4_k_m | 46.10 MB | +| [llama-68m-chat-v1.q5_k_m.gguf](https://huggingface.co/afrideva/Llama-68M-Chat-v1-GGUF/resolve/main/llama-68m-chat-v1.q5_k_m.gguf) | q5_k_m | 51.16 MB | +| [llama-68m-chat-v1.q6_k.gguf](https://huggingface.co/afrideva/Llama-68M-Chat-v1-GGUF/resolve/main/llama-68m-chat-v1.q6_k.gguf) | q6_k | 56.54 MB | +| [llama-68m-chat-v1.q8_0.gguf](https://huggingface.co/afrideva/Llama-68M-Chat-v1-GGUF/resolve/main/llama-68m-chat-v1.q8_0.gguf) | q8_0 | 73.02 MB | + + + +## Original Model Card: +# A Llama Chat Model of 68M Parameters + +- Base model: [JackFram/llama-68m](https://huggingface.co/JackFram/llama-68m) +- Datasets: + - [THUDM/webglm-qa](https://huggingface.co/datasets/THUDM/webglm-qa) + - [databricks/databricks-dolly-15k](https://huggingface.co/datasets/databricks/databricks-dolly-15k) + - [cognitivecomputations/wizard_vicuna_70k_unfiltered](https://huggingface.co/datasets/cognitivecomputations/wizard_vicuna_70k_unfiltered) + - [totally-not-an-llm/EverythingLM-data-V3](https://huggingface.co/datasets/totally-not-an-llm/EverythingLM-data-V3) + - [Amod/mental_health_counseling_conversations](https://huggingface.co/datasets/Amod/mental_health_counseling_conversations) + - [sablo/oasst2_curated](https://huggingface.co/datasets/sablo/oasst2_curated) + - [starfishmedical/webGPT_x_dolly](https://huggingface.co/datasets/starfishmedical/webGPT_x_dolly) + - [Open-Orca/OpenOrca](https://huggingface.co/datasets/Open-Orca/OpenOrca) + - [mlabonne/chatml_dpo_pairs](https://huggingface.co/datasets/mlabonne/chatml_dpo_pairs) +- Availability in other ML formats: + - ONNX: [Felladrin/onnx-Llama-68M-Chat-v1](https://huggingface.co/Felladrin/onnx-Llama-68M-Chat-v1) + +## Recommended Prompt Format + +``` +<|im_start|>system +{system_message}<|im_end|> +<|im_start|>user +{user_message}<|im_end|> +<|im_start|>assistant +``` + +## Recommended Inference Parameters + +```yml +penalty_alpha: 0.5 +top_k: 4 +``` \ No newline at end of file diff --git a/llama-68m-chat-v1.fp16.gguf b/llama-68m-chat-v1.fp16.gguf new file mode 100644 index 0000000..a6e5fb3 --- /dev/null +++ b/llama-68m-chat-v1.fp16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b163fcac5a6c40c23864fb2f05c6757b659b237c7680ca3857ee642d1e432052 +size 136793344 diff --git a/llama-68m-chat-v1.q2_k.gguf b/llama-68m-chat-v1.q2_k.gguf new file mode 100644 index 0000000..a75f4d5 --- /dev/null +++ b/llama-68m-chat-v1.q2_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fefe6262dbb32619817058e8149fd88121801104b61b04b45ffe08c19b933c6 +size 35876672 diff --git a/llama-68m-chat-v1.q3_k_m.gguf b/llama-68m-chat-v1.q3_k_m.gguf new file mode 100644 index 0000000..3fd01a0 --- /dev/null +++ b/llama-68m-chat-v1.q3_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47a59cb13e7c83a862c4d1ba43b413f2d6c83111aaa5b11c1f68c0621db690fd +size 40658240 diff --git a/llama-68m-chat-v1.q4_k_m.gguf b/llama-68m-chat-v1.q4_k_m.gguf new file mode 100644 index 0000000..ab31e33 --- /dev/null +++ b/llama-68m-chat-v1.q4_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c54993794e010aab3905be305719e9d8fe45b4e939e7a2a5d7aaf53310a64eb4 +size 46101824 diff --git a/llama-68m-chat-v1.q5_k_m.gguf b/llama-68m-chat-v1.q5_k_m.gguf new file mode 100644 index 0000000..8cf7cb2 --- /dev/null +++ b/llama-68m-chat-v1.q5_k_m.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:148a39089cbd5b4634e7d2680edfc43a6e310cf2bc7c7519f661b216c34cbed2 +size 51164480 diff --git a/llama-68m-chat-v1.q6_k.gguf b/llama-68m-chat-v1.q6_k.gguf new file mode 100644 index 0000000..d4be49e --- /dev/null +++ b/llama-68m-chat-v1.q6_k.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60e2650024424f3220b8588c6887cb912126bdabaeaafdfb19d6b14ae7c5e317 +size 56543552 diff --git a/llama-68m-chat-v1.q8_0.gguf b/llama-68m-chat-v1.q8_0.gguf new file mode 100644 index 0000000..b74b69e --- /dev/null +++ b/llama-68m-chat-v1.q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdd6bad08258f53c637c233309c3b41ccd91907359364aaa02e18df54c34b836 +size 73018688