commit 6bfd3b4908624d0f5d5ad554870b259347bc6a10 Author: ModelHub XC Date: Sat Jul 18 22:01:05 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: SupraLabs/Supra-1.5-50M-instruct-exp-gguf Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..a5cd370 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,83 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bin.* filter=lfs diff=lfs merge=lfs -text +*.bz2 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 +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack 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 +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +saved_model/**/* 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 +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zstandard filter=lfs diff=lfs merge=lfs -text +*.tfevents* filter=lfs diff=lfs merge=lfs -text +*.db* filter=lfs diff=lfs merge=lfs -text +*.ark* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text +**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text + +*.ggml filter=lfs diff=lfs merge=lfs -text +*.llamafile* filter=lfs diff=lfs merge=lfs -text +*.pt2 filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text + +Supra-1.5-50M-Instruct-exp.F16.gguf filter=lfs diff=lfs merge=lfs -text +Supra-1.5-50M-Instruct-exp.BF16.gguf filter=lfs diff=lfs merge=lfs -text + +Supra-1.5-50M-Instruct-exp.F32.gguf filter=lfs diff=lfs merge=lfs -text +Supra-1.5-50M-Instruct-exp.IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text + +Supra-1.5-50M-Instruct-exp.IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text +Supra-1.5-50M-Instruct-exp.IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text + +Supra-1.5-50M-Instruct-exp.IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Supra-1.5-50M-Instruct-exp.Q1_0.gguf filter=lfs diff=lfs merge=lfs -text + +Supra-1.5-50M-Instruct-exp.Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Supra-1.5-50M-Instruct-exp.Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text + +Supra-1.5-50M-Instruct-exp.Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Supra-1.5-50M-Instruct-exp.Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text + +Supra-1.5-50M-Instruct-exp.Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Supra-1.5-50M-Instruct-exp.Q4_0.gguf filter=lfs diff=lfs merge=lfs -text + +Supra-1.5-50M-Instruct-exp.Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Supra-1.5-50M-Instruct-exp.Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text + +Supra-1.5-50M-Instruct-exp.Q5_1.gguf filter=lfs diff=lfs merge=lfs -text +Supra-1.5-50M-Instruct-exp.Q5_0.gguf filter=lfs diff=lfs merge=lfs -text + +Supra-1.5-50M-Instruct-exp.Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Supra-1.5-50M-Instruct-exp.Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text + +Supra-1.5-50M-Instruct-exp.Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +Supra-1.5-50M-Instruct-exp.Q6_K.gguf filter=lfs diff=lfs merge=lfs -text + +Supra-1.5-50M-Instruct-exp.TQ2_0.gguf filter=lfs diff=lfs merge=lfs -text +Supra-1.5-50M-Instruct-exp.TQ1_0.gguf filter=lfs diff=lfs merge=lfs -text \ No newline at end of file diff --git a/README.md b/README.md new file mode 100644 index 0000000..9b19d42 --- /dev/null +++ b/README.md @@ -0,0 +1,212 @@ +--- +license: apache-2.0 +language: +- en +base_model: SupraLabs/Supra-1.5-50M-instruct-exp +pipeline_tag: text-generation +tags: +- supra +- chimera +- project-chimera +- gguf +- quantized +- instruct +- conversational +- QnA +- GPT +- CPU +- tiny +- SLM +- open +- open-source +- 50M +- llama +--- + +

Supra-1.5 Instruct • Experimental Chat Tune — GGUF

+ +![Supra-1.5 Instruct](https://cdn-uploads.huggingface.co/production/uploads/68a5d0966d33a07f8aad2e51/GUYqhtlWoCAUnRLR1zEOX.png) + +GGUF quantizations of [SupraLabs/Supra-1.5-50M-instruct-exp](https://huggingface.co/SupraLabs/Supra-1.5-50M-instruct-exp), an experimental 50M-parameter instruction-tuned model by [SupraLabs](https://huggingface.co/SupraLabs), part of **Project Chimera**. + +Run it entirely on CPU, low-VRAM GPUs, or embedded hardware. No cloud required. + +> **Note:** This is an experimental model. Do not use in production. + +--- + +## 📦 Available Quantizations + +| Bits | Quantization | Size | +|:--|:--|:--| +| 1-bit | `Q1_0` | 19.6 MB | +| 1-bit | `TQ1_0` | 25.1 MB | +| 2-bit | `Q2_K` | 28.8 MB | +| 2-bit | `TQ2_0` | 26.4 MB | +| 3-bit | `IQ3_S` | 31 MB | +| 3-bit | `Q3_K_S` | 31 MB | +| 3-bit | `IQ3_M` | 31.7 MB | +| 3-bit | `Q3_K_M` | 32.7 MB | +| 3-bit | `Q3_K_L` | 33.8 MB | +| 4-bit | `IQ4_XS` | 33.8 MB | +| 4-bit | `Q4_K_S` | 35.7 MB | +| 4-bit | `IQ4_NL` | 34.7 MB | +| 4-bit | `Q4_0` | 34.5 MB | +| 4-bit | `Q4_1` | 36.8 MB | +| 4-bit | `Q4_K_M` | 37.4 MB | +| 5-bit | `Q5_K_S` | 39.5 MB | +| 5-bit | `Q5_0` | 39 MB | +| 5-bit | `Q5_1` | 41.2 MB | +| 5-bit | `Q5_K_M` | 41 MB | +| 6-bit | `Q6_K` | 45.8 MB | +| 8-bit | `Q8_0` | 56.2 MB | +| 16-bit | `BF16` | 105 MB | +| 16-bit | `F16` | 105 MB | +| 32-bit | `F32` | 208 MB | + +> **`Q4_K_M`** — Usable, not recommended unless device is compute-constrained. +> **`Q8_0`** — Perfect size/performance!. +> **`Q2_K`** — ultra-constrained devices (not reccomended!). + +--- + +## 🚀 Quick Start + +### llama.cpp + +```bash +# Download +huggingface-cli download SupraLabs/Supra-1.5-50M-instruct-exp-gguf \ + --include "*.Q4_K_M.gguf" \ + --local-dir ./ + +# Run +./llama-cli \ + -m supra-1.5-50m-instruct-exp-Q4_K_M.gguf \ + -p "### Instruction:\nWhat is machine learning?\n\n### Response:\n" \ + -n 256 \ + --temp 0.7 \ + --repeat-penalty 1.15 +``` + +### Ollama + +```bash +ollama run hf.co/SupraLabs/Supra-1.5-50M-instruct-exp-gguf:Q4_K_M +``` + +### Python (llama-cpp-python) + +```python +from llama_cpp import Llama + +llm = Llama.from_pretrained( + repo_id="SupraLabs/Supra-1.5-50M-instruct-exp-gguf", + filename="*Q4_K_M.gguf", + n_ctx=1024, + verbose=False, +) + +def chat(instruction: str, input_text: str = "") -> str: + if input_text.strip(): + prompt = ( + "Below is an instruction that describes a task, paired with an input " + "that provides further context. Write a response that appropriately " + "completes the request.\n\n" + f"### Instruction:\n{instruction}\n\n" + f"### Input:\n{input_text}\n\n" + "### Response:\n" + ) + else: + prompt = ( + "Below is an instruction that describes a task. Write a response that " + "appropriately completes the request.\n\n" + f"### Instruction:\n{instruction}\n\n" + "### Response:\n" + ) + output = llm(prompt, max_tokens=256, temperature=0.7, top_k=50, top_p=0.9, repeat_penalty=1.15) + return output["choices"][0]["text"].strip() + +print(chat("Explain what artificial intelligence is.")) +``` + +--- + +## 💬 Prompt Format + +This model uses the **Alpaca Chat Format**: + +``` +Below is an instruction that describes a task. Write a response that appropriately completes the request. + +### Instruction: +{instruction} + +### Response: +``` + +With optional input: + +``` +Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request. + +### Instruction: +{instruction} + +### Input: +{input} + +### Response: +``` + +--- + +## 🏆 Benchmarks + +Supra-1.5-50M-instruct-exp achieves superior performance within the 50M-parameter class, with a consistent **BLiMP score of 67.4**. + +Key findings from evaluation: +- **Scientific/factual tasks** perform best under raw inference (no normalization) +- **Math and logical reasoning** benefit from normalized inference +- **Top syntactic categories**: structural dependency tracking, complex clausal configurations, and subtle syntactic error detection — performing at near-flawless precision +- **Hardest categories**: advanced binding phenomena and morphological agreement edge cases, reflecting known limits of 50M-class architectures + +> For full benchmark charts and BLiMP probe analysis, see the [base model card](https://huggingface.co/SupraLabs/Supra-1.5-50M-instruct-exp). + +--- + +## 🧠 Model Architecture + +| Property | Value | +|:--|:--| +| Architecture | Llama (decoder-only) | +| Parameters | ~50M | +| Vocabulary | 32,000 (custom BPE) | +| Context length | 5,120 tokens | +| Hidden size | 512 | +| Layers | 12 | +| Attention heads | 8 (GQA: 4 KV heads) | +| Base model | SupraLabs/Supra-1.5-50M-Base-exp | +| License | Apache 2.0 | + +--- + +## 🔗 Related Models + +| Model | Description | +|:--|:--| +| [Supra-1.5-50M-Base-exp](https://huggingface.co/SupraLabs/Supra-1.5-50M-Base-exp) | Pretrained base (v1.5) | +| [Supra-1.5-50M-instruct-exp](https://huggingface.co/SupraLabs/Supra-1.5-50M-instruct-exp) | fp weights | +| [Supra-50M-Base](https://huggingface.co/SupraLabs/Supra-50M-Base) | v1.0 pretrained base | +| [Supra-50M-Instruct](https://huggingface.co/SupraLabs/Supra-50M-Instruct) | v1.0 instruct model | +| [Supra-50M-Reasoning](https://huggingface.co/SupraLabs/Supra-50M-Reasoning) | Chain-of-thought reasoning variant | + +--- + +## 📄 License + +Released under the [Apache 2.0 License](https://www.apache.org/licenses/LICENSE-2.0). + +--- + +*© SupraLabs 2026 — Project Chimera* \ No newline at end of file diff --git a/Supra-1.5-50M-Instruct-exp.BF16.gguf b/Supra-1.5-50M-Instruct-exp.BF16.gguf new file mode 100644 index 0000000..e9548e1 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bb981ec71b8c356d9f2388380501218388124d6558aa3869549c6593768fdb8 +size 104740320 diff --git a/Supra-1.5-50M-Instruct-exp.F16.gguf b/Supra-1.5-50M-Instruct-exp.F16.gguf new file mode 100644 index 0000000..f299121 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.F16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c676d3e4591bf08dcfc5876daee87488808e6b6339d5e74a495b6a5eac75dd7f +size 104740320 diff --git a/Supra-1.5-50M-Instruct-exp.F32.gguf b/Supra-1.5-50M-Instruct-exp.F32.gguf new file mode 100644 index 0000000..ea70ef5 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.F32.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c2031d239bc018115e365ce92b9d8546ce946cc6e8b11bf1433954f4566877a +size 208287200 diff --git a/Supra-1.5-50M-Instruct-exp.IQ3_M.gguf b/Supra-1.5-50M-Instruct-exp.IQ3_M.gguf new file mode 100644 index 0000000..bb3b473 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7244eaa3889a51c7ec51ca793bb7e36b24a64cc5da674ea99d7235c056845ae +size 31705568 diff --git a/Supra-1.5-50M-Instruct-exp.IQ3_S.gguf b/Supra-1.5-50M-Instruct-exp.IQ3_S.gguf new file mode 100644 index 0000000..80a05e8 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19d1da3464c5f7cd01b57ddcfb41946dc45f268c02cda8fbe919918438eecb5 +size 30988768 diff --git a/Supra-1.5-50M-Instruct-exp.IQ4_NL.gguf b/Supra-1.5-50M-Instruct-exp.IQ4_NL.gguf new file mode 100644 index 0000000..a5c0ed6 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02f3b5d6f423b1e7e8891ec3bf6288d74d31c587cb0dc979ddf4d9a6d0e35bf7 +size 34675168 diff --git a/Supra-1.5-50M-Instruct-exp.IQ4_XS.gguf b/Supra-1.5-50M-Instruct-exp.IQ4_XS.gguf new file mode 100644 index 0000000..5406c0f --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee350e7fa1949be217d5fffc7aa3cb148079f97d01263a40acfbd0ca0fb17335 +size 33839584 diff --git a/Supra-1.5-50M-Instruct-exp.Q1_0.gguf b/Supra-1.5-50M-Instruct-exp.Q1_0.gguf new file mode 100644 index 0000000..7fab703 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q1_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad63e1d1404b8ce85c443cb0935ae55ac46902a21e610bcdcca946a5f769f63c +size 19610080 diff --git a/Supra-1.5-50M-Instruct-exp.Q2_K.gguf b/Supra-1.5-50M-Instruct-exp.Q2_K.gguf new file mode 100644 index 0000000..c1f48ae --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25670601e6c28ee307448e6de1cfb3bda7e9760bb21df8a4aca395ad023a08d7 +size 28752352 diff --git a/Supra-1.5-50M-Instruct-exp.Q3_K_L.gguf b/Supra-1.5-50M-Instruct-exp.Q3_K_L.gguf new file mode 100644 index 0000000..310ecea --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a43ba5ea76cb8b82ddff15de419a8c744572b43322dc3ea4c7305332e16d32ef +size 33827296 diff --git a/Supra-1.5-50M-Instruct-exp.Q3_K_M.gguf b/Supra-1.5-50M-Instruct-exp.Q3_K_M.gguf new file mode 100644 index 0000000..dfabf23 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eed188d2bacb45ec44f3cc5365d83b522ed234786b8f2584c2e54f02104222d2 +size 32729568 diff --git a/Supra-1.5-50M-Instruct-exp.Q3_K_S.gguf b/Supra-1.5-50M-Instruct-exp.Q3_K_S.gguf new file mode 100644 index 0000000..2cdf599 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ca4b7ddb4fc943d321bb5f3bff439b97c21ea14344d4ae736d2300d0077afd3 +size 30988768 diff --git a/Supra-1.5-50M-Instruct-exp.Q4_0.gguf b/Supra-1.5-50M-Instruct-exp.Q4_0.gguf new file mode 100644 index 0000000..88c4695 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d81dc1cd6f6f3f1680451d055f9fd758b18da922b69d6111205e43a23ceb0729 +size 34540000 diff --git a/Supra-1.5-50M-Instruct-exp.Q4_1.gguf b/Supra-1.5-50M-Instruct-exp.Q4_1.gguf new file mode 100644 index 0000000..f98c0ef --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be920d0b74686aa16ee6bef8982afa68b9f4168d60ccca585244864e924a098b +size 36751840 diff --git a/Supra-1.5-50M-Instruct-exp.Q4_K_M.gguf b/Supra-1.5-50M-Instruct-exp.Q4_K_M.gguf new file mode 100644 index 0000000..b3dccc5 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e839cb0e618a52acd5d3adec95f4a6de893b3ab00893826f55cf54c6bd6250f5 +size 37446112 diff --git a/Supra-1.5-50M-Instruct-exp.Q4_K_S.gguf b/Supra-1.5-50M-Instruct-exp.Q4_K_S.gguf new file mode 100644 index 0000000..4c669ca --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d581095acdaf14168dde1d4bb9308d239389343f06d8aa095cdf1381a27c6724 +size 35731936 diff --git a/Supra-1.5-50M-Instruct-exp.Q5_0.gguf b/Supra-1.5-50M-Instruct-exp.Q5_0.gguf new file mode 100644 index 0000000..1e0c4fe --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q5_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8cecd81b1dd43b991bbf1c71881c85aed1dc6faa25423e94cf06fbc9266bfd5b +size 38963680 diff --git a/Supra-1.5-50M-Instruct-exp.Q5_1.gguf b/Supra-1.5-50M-Instruct-exp.Q5_1.gguf new file mode 100644 index 0000000..29ed839 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q5_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61a79ca5932a7e7a0dea279d4f4ecd5a2ef77b05c5158c3a4398e468888381f6 +size 41175520 diff --git a/Supra-1.5-50M-Instruct-exp.Q5_K_M.gguf b/Supra-1.5-50M-Instruct-exp.Q5_K_M.gguf new file mode 100644 index 0000000..67f3132 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:05c51010bc5f0955c7c9a9206684e563be1b9ceab3b282ed9698fd85f77a6c23 +size 40960480 diff --git a/Supra-1.5-50M-Instruct-exp.Q5_K_S.gguf b/Supra-1.5-50M-Instruct-exp.Q5_K_S.gguf new file mode 100644 index 0000000..735884b --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:987d8ef97eba532624324d34aca8d9849b3c6bf758ed8eeee3f529f408d62a81 +size 39504352 diff --git a/Supra-1.5-50M-Instruct-exp.Q6_K.gguf b/Supra-1.5-50M-Instruct-exp.Q6_K.gguf new file mode 100644 index 0000000..0ba49fc --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:897306f0539dd5a0aea53682a92280c47a5ac155a3cae3c5014b25eef7bad082 +size 45758944 diff --git a/Supra-1.5-50M-Instruct-exp.Q8_0.gguf b/Supra-1.5-50M-Instruct-exp.Q8_0.gguf new file mode 100644 index 0000000..6e69fb3 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c943cd868d4ae3e44731ca03661f381816a2f9d39586b73ab21a2d1f2f61b96 +size 56202720 diff --git a/Supra-1.5-50M-Instruct-exp.TQ1_0.gguf b/Supra-1.5-50M-Instruct-exp.TQ1_0.gguf new file mode 100644 index 0000000..63aa4d9 --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.TQ1_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50035f3178ec36efdf21a1b8e72857f07ef7dc7d30d4f78e2f5196b9dd0e412d +size 25139680 diff --git a/Supra-1.5-50M-Instruct-exp.TQ2_0.gguf b/Supra-1.5-50M-Instruct-exp.TQ2_0.gguf new file mode 100644 index 0000000..31dceca --- /dev/null +++ b/Supra-1.5-50M-Instruct-exp.TQ2_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ad0eb6108e21a7507be7921c12d68afac0cdbc0008eb08570b77e76d68a84f3 +size 26393056 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