commit 7b3029e7fa467c106fe2ebd37a4cb37c9b9cdf30 Author: ModelHub XC Date: Fri Aug 14 17:15:16 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: reedmayhew/Llama-3.2-1B-claude-3.7-sonnet-reasoning-distilled Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..265f2ff --- /dev/null +++ b/.gitattributes @@ -0,0 +1,39 @@ +*.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 +unsloth.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +unsloth.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-claude-3.7-sonnet-reasoning-distilled.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +llama-3.2-1b-claude-3.7-sonnet-reasoning-distilled.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Modelfile b/Modelfile new file mode 100644 index 0000000..407bf02 --- /dev/null +++ b/Modelfile @@ -0,0 +1,57 @@ + +FROM /content/reedmayhew/Llama-3.2-1B-claude-3.7-sonnet-reasoning-distilled/unsloth.BF16.gguf +TEMPLATE """{{ if .Messages }} +{{- if or .System .Tools }}<|start_header_id|>system<|end_header_id|> +{{- if .System }} + +{{ .System }} +{{- end }} +{{- if .Tools }} + +You are a helpful assistant with tool calling capabilities. When you receive a tool call response, use the output to format an answer to the original use question. +{{- end }} +{{- end }}<|eot_id|> +{{- range $i, $_ := .Messages }} +{{- $last := eq (len (slice $.Messages $i)) 1 }} +{{- if eq .Role "user" }}<|start_header_id|>user<|end_header_id|> +{{- if and $.Tools $last }} + +Given the following functions, please respond with a JSON for a function call with its proper arguments that best answers the given prompt. + +Respond in the format {"name": function name, "parameters": dictionary of argument name and its value}. Do not use variables. + +{{ $.Tools }} +{{- end }} + +{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|> + +{{ end }} +{{- else if eq .Role "assistant" }}<|start_header_id|>assistant<|end_header_id|> +{{- if .ToolCalls }} + +{{- range .ToolCalls }}{"name": "{{ .Function.Name }}", "parameters": {{ .Function.Arguments }}}{{ end }} +{{- else }} + +{{ .Content }}{{ if not $last }}<|eot_id|>{{ end }} +{{- end }} +{{- else if eq .Role "tool" }}<|start_header_id|>ipython<|end_header_id|> + +{{ .Content }}<|eot_id|>{{ if $last }}<|start_header_id|>assistant<|end_header_id|> + +{{ end }} +{{- end }} +{{- end }} +{{- else }} +{{- if .System }}<|start_header_id|>system<|end_header_id|> + +{{ .System }}<|eot_id|>{{ end }}{{ if .Prompt }}<|start_header_id|>user<|end_header_id|> + +{{ .Prompt }}<|eot_id|>{{ end }}<|start_header_id|>assistant<|end_header_id|> + +{{ end }}{{ .Response }}{{ if .Response }}<|eot_id|>{{ end }}""" +PARAMETER stop "<|start_header_id|>" +PARAMETER stop "<|end_header_id|>" +PARAMETER stop "<|eot_id|>" +PARAMETER stop "<|eom_id|>" +PARAMETER temperature 1.5 +PARAMETER min_p 0.1 \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..39fa2d0 --- /dev/null +++ b/README.md @@ -0,0 +1,37 @@ +--- +base_model: unsloth/llama-3.2-1b-instruct +tags: +- text-generation-inference +- transformers +- unsloth +- llama +- gguf +license: apache-2.0 +language: +- en +datasets: +- mfielding92/claude-3.7-sonnet-reasoning +--- + +# Uploaded Model + +## Overview +This model is a Llama 3.2 1B Instruct variant that has been specifically fine-tuned using reasoning data from Claude 3.7 Sonnet. The goal was to leverage Claude's renowned reasoning capabilities within a more accessible, open-source architecture like Llama. + +## Technical Details +- **Developed by:** mfielding92 +- **Base Model:** unsloth/llama-3.2-1b-instruct +- **Finetuning Method:** Supervised Fine-Tuning (SFT) using LoRA +- **Training Speed Enhancement:** Trained 2x faster with Unsloth and Huggingface's TRL library + +## Training Data +The model was fine-tuned on a dataset derived from: +- mfielding92/claude-3.7-sonnet-reasoning + +This allows the model to potentially exhibit improved logical thinking, problem-solving abilities, and complex reasoning compared to the base Llama 3.2 model while remaining open-source. + +## Usage Notes +While this model inherits some of Claude's strenghs in reasoning, it is still a derivative work built on Llama architecture. Users should evaluate its performance carefully for their specific use cases. + +This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library. +[](https://github.com/unslothai/unsloth) \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..a4ba21b --- /dev/null +++ b/config.json @@ -0,0 +1,3 @@ +{ + "model_type": "llama" +} \ No newline at end of file diff --git a/llama-3.2-1b-claude-3.7-sonnet-reasoning-distilled.Q4_0.gguf b/llama-3.2-1b-claude-3.7-sonnet-reasoning-distilled.Q4_0.gguf new file mode 100644 index 0000000..600adb3 --- /dev/null +++ b/llama-3.2-1b-claude-3.7-sonnet-reasoning-distilled.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c13d4a10a5e05377f9ab514932dede1a65708f6fed1320e72b983dde2330600b +size 770929120 diff --git a/llama-3.2-1b-claude-3.7-sonnet-reasoning-distilled.Q8_0.gguf b/llama-3.2-1b-claude-3.7-sonnet-reasoning-distilled.Q8_0.gguf new file mode 100644 index 0000000..3f1a1af --- /dev/null +++ b/llama-3.2-1b-claude-3.7-sonnet-reasoning-distilled.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a67788d7e8e984b09870591e26a9a3932425264a57d203f5d7cd3bb9e8094dc +size 1321083360