commit d04a3a1817a5284c18dabe769371fd3dfc6bd7b4 Author: ModelHub XC Date: Tue Jun 30 07:43:12 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: unsloth/granite-4.0-350m-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..fa1ce2b --- /dev/null +++ b/.gitattributes @@ -0,0 +1,67 @@ +*.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 + +granite-4.0-350m-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-BF16.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-UD-Q3_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-UD-Q4_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-UD-Q6_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-UD-Q5_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-UD-Q8_K_XL.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-UD-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +granite-4.0-350m-Q4_1.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..0e329bb --- /dev/null +++ b/README.md @@ -0,0 +1,618 @@ +--- +license: apache-2.0 +library_name: transformers +tags: +- language +- unsloth +- granite-4.0 +base_model: +- ibm-granite/granite-4.0-350m +--- +
+

+ Unsloth Dynamic 2.0 achieves superior accuracy & outperforms other leading quants. +

+
+ + + + + + + + + +
+
+ + +# Granite-4.0-350M + +**Model Summary:** +Granite-4.0-350M is a lightweight instruct model finetuned from *Granite-4.0-350M-Base* using a combination of open source instruction datasets with permissive license and internally collected synthetic datasets. This model is developed using a diverse set of techniques including supervised finetuning, reinforcement learning, and model merging. + +- **Developers:** Granite Team, IBM +- **HF Collection:** [Granite 4.0 Nano Language Models HF Collection](https://huggingface.co/collections/ibm-granite/granite-40-nano-language-models-68e5775c80b60e43b72cfa16) +- **GitHub Repository:** [ibm-granite/granite-4.0-nano-language-models](https://github.com/ibm-granite/granite-4.0-nano-language-models) +- **Website**: [Granite Docs](https://www.ibm.com/granite/docs/) +- **Release Date**: October 28, 2025 +- **License:** [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0) + +**Supported Languages:** +English, German, Spanish, French, Japanese, Portuguese, Arabic, Czech, Italian, Korean, Dutch, and Chinese. Users may fine-tune Granite 4.0 Nano models to support languages beyond those included in this list. + +**Intended use:** +Granite 4.0 Nano instruct models feature strong instruction following capabilities bringing advanced AI capabilities within reach for on-device deployments and research use cases. Additionally, their compact size makes them well-suited for fine-tuning on specialized domains without requiring massive compute resources. + +*Capabilities* +* Summarization +* Text classification +* Text extraction +* Question-answering +* Retrieval Augmented Generation (RAG) +* Code related tasks +* Function-calling tasks +* Multilingual dialog use cases +* Fill-In-the-Middle (FIM) code completions + + + +**Generation:** +This is a simple example of how to use Granite-4.0-350M model. + +Install the following libraries: + +```shell +pip install torch torchvision torchaudio +pip install accelerate +pip install transformers +``` +Then, copy the snippet from the section that is relevant for your use case. + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +device = "cuda" +model_path = "ibm-granite/granite-4.0-350M" +tokenizer = AutoTokenizer.from_pretrained(model_path) +# drop device_map if running on CPU +model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device) +model.eval() +# change input text as desired +chat = [ + { "role": "user", "content": "Please list one IBM Research laboratory located in the United States. You should only output its name and location." }, +] +chat = tokenizer.apply_chat_template(chat, tokenize=False, add_generation_prompt=True) +# tokenize the text +input_tokens = tokenizer(chat, return_tensors="pt").to(device) +# generate output tokens +output = model.generate(**input_tokens, + max_new_tokens=100) +# decode output tokens into text +output = tokenizer.batch_decode(output) +# print output +print(output[0]) +``` + +Expected output: +```shell +<|start_of_role|>user<|end_of_role|>Please list one IBM Research laboratory located in the United States. You should only output its name and location.<|end_of_text|> +<|start_of_role|>assistant<|end_of_role|>Almaden Research Center, San Jose, California<|end_of_text|> +``` + +**Tool-calling:** +Granite-4.0-350M comes with enhanced tool calling capabilities, enabling seamless integration with external functions and APIs. To define a list of tools please follow OpenAI's function [definition schema](https://platform.openai.com/docs/guides/function-calling?api-mode=responses#defining-functions). + +This is an example of how to use Granite-4.0-350M model tool-calling ability: + +```python +import torch +from transformers import AutoModelForCausalLM, AutoTokenizer + +device = "cuda" +model_path = "ibm-granite/granite-4.0-350M" +tokenizer = AutoTokenizer.from_pretrained(model_path) +# drop device_map if running on CPU +model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device) +model.eval() + +tools = [ + { + "type": "function", + "function": { + "name": "get_current_weather", + "description": "Get the current weather for a specified city.", + "parameters": { + "type": "object", + "properties": { + "city": { + "type": "string", + "description": "Name of the city" + } + }, + "required": ["city"] + } + } + } +] + +# change input text as desired +chat = [ + { "role": "user", "content": "What's the weather like in Boston right now?" }, +] +chat = tokenizer.apply_chat_template(chat, \ + tokenize=False, \ + tools=tools, \ + add_generation_prompt=True) +# tokenize the text +input_tokens = tokenizer(chat, return_tensors="pt").to(device) +# generate output tokens +output = model.generate(**input_tokens, + max_new_tokens=100) +# decode output tokens into text +output = tokenizer.batch_decode(output) +# print output +print(output[0]) +``` + +Expected output: +```shell +<|start_of_role|>system<|end_of_role|>You are a helpful assistant with access to the following tools. You may call one or more tools to assist with the user query. + +You are provided with function signatures within XML tags: +- +- unsloth +{"type": "function", "function": {"name": "get_current_weather", "description": "Get the current weather for a specified city.", "parameters": {"type": "object", "properties": {"city": {"type": "string", "description": "Name of the city"}}, "required": ["city"]}}} + + +For each tool call, return a json object with function name and arguments within XML tags: +- +- unsloth +{"name": , "arguments": } +. If a tool does not exist in the provided list of tools, notify the user that you do not have the ability to fulfill the request.<|end_of_text|> +<|start_of_role|>user<|end_of_role|>What's the weather like in Boston right now?<|end_of_text|> +<|start_of_role|>assistant<|end_of_role|> +{"name": "get_current_weather", "arguments": {"city": "Boston"}} +<|end_of_text|> +``` + + + +**Evaluation Results:** + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
BenchmarksMetric350M DenseH 350M Dense1B DenseH 1B Dense
+ General Tasks +
MMLU5-shot35.0136.2159.3959.74
MMLU-Pro5-shot, CoT12.1314.3834.0232.86
BBH3-shot, CoT33.0733.2860.3759.68
AGI EVAL0-shot, CoT26.2229.6149.2252.44
GPQA0-shot, CoT24.1126.1229.9129.69
+ Alignment Tasks +
IFEvalInstruct, Strict61.6367.6380.8282.37
IFEvalPrompt, Strict49.1755.6473.9474.68
IFEvalAverage55.461.6377.3878.53
+ Math Tasks +
GSM8K8-shot30.7139.2776.3569.83
GSM Symbolic8-shot26.7633.772.365.72
Minerva Math0-shot, CoT13.045.7645.2849.4
DeepMind Math0-shot, CoT8.456.23434.98
+ Code Tasks +
HumanEvalpass@139387473
HumanEval+pass@137356968
MBPPpass@148496569
MBPP+pass@138445760
CRUXEval-Opass@123.7525.533.1336
BigCodeBenchpass@111.1411.2330.1829.12
+ Tool Calling Tasks +
BFCL v339.3243.3254.8250.21
+ Multilingual Tasks +
MULTIPLEpass@115.9914.3132.2436.11
MMMLU5-shot28.2327.954549.43
INCLUDE5-shot27.7427.0942.1243.35
MGSM8-shot14.7216.1637.8427.52
+ Safety +
SALAD-Bench97.1296.5593.4496.4
AttaQ82.5381.7685.2682.85
+ + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Multilingual Benchmarks and thr included languages:
Benchmarks# LangsLanguages
MMMLU11ar, de, en, es, fr, ja, ko, pt, zh, bn, hi
INCLUDE14hi, bn, ta, te, ar, de, es, fr, it, ja, ko, nl, pt, zh
MGSM5en, es, fr, ja, zh
+ +**Model Architecture:** + +Granite-4.0-350M baseline is based on a decoder-only dense transformer architecture. Core components of this architecture are: GQA, MLP with SwiGLU, RMSNorm, and shared input/output embeddings. + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + + +
Model350M DenseH 350M Dense1B DenseH 1B Dense
Embedding size102476820481536
Number of layers28 attention4 attention / 28 Mamba240 attention4 attention / 36 Mamba2
Attention head size6464128128
Number of attention heads16121612
Number of KV heads4444
Mamba2 state size-128-128
Number of Mamba2 heads-48-48
MLP / Shared expert hidden size2048204840964096
Num. Experts----
Num. active Experts----
Expert hidden size----
MLP activationSwiGLUSwiGLUSwiGLUSwiGLU
Sequence length32K32K128K128K
Position embeddingRoPENoPERoPENoPE
# Parameters350M340M1.6B1.5B
# Active parameters350M340M1.6B1.5B
+ +**Training Data:** +Overall, our SFT data is largely comprised of three key sources: (1) publicly available datasets with permissive license, (2) internal synthetic data targeting specific capabilities, and (3) a select set of human-curated data. + +**Infrastructure:** +We trained the Granite 4.0 Nano Language Models utilizing an NVIDIA GB200 NVL72 cluster hosted in CoreWeave. Intra-rack communication occurs via the 72-GPU NVLink domain, and a non-blocking, full Fat-Tree NDR 400 Gb/s InfiniBand network provides inter-rack communication. This cluster provides a scalable and efficient infrastructure for training our models over thousands of GPUs. + +**Ethical Considerations and Limitations:** +Granite 4.0 Nano Instruct Models are primarily finetuned using instruction-response pairs mostly in English, but also multilingual data covering multiple languages. Although this model can handle multilingual dialog use cases, its performance might not be similar to English tasks. In such case, introducing a small number of examples (few-shot) can help the model in generating more accurate outputs. While this model has been aligned by keeping safety in consideration, the model may in some cases produce inaccurate, biased, or unsafe responses to user prompts. So we urge the community to use this model with proper safety testing and tuning tailored for their specific tasks. + +**Resources** +- ⭐️ Learn about the latest updates with Granite: https://www.ibm.com/granite +- 📄 Get started with tutorials, best practices, and prompt engineering advice: https://www.ibm.com/granite/docs/ +- 💡 Learn about the latest Granite learning resources: https://ibm.biz/granite-learning-resources + + \ No newline at end of file diff --git a/configuration.json b/configuration.json new file mode 100644 index 0000000..159097f --- /dev/null +++ b/configuration.json @@ -0,0 +1 @@ +{"framework": "pytorch", "task": "others", "allow_remote": true} \ No newline at end of file diff --git a/granite-4.0-350m-BF16.gguf b/granite-4.0-350m-BF16.gguf new file mode 100644 index 0000000..759ccae --- /dev/null +++ b/granite-4.0-350m-BF16.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fabc4c52987044b385af182f99549bc861139e2e5da56dbfd8174f08ae52999 +size 708439552 diff --git a/granite-4.0-350m-IQ4_NL.gguf b/granite-4.0-350m-IQ4_NL.gguf new file mode 100644 index 0000000..b77a4dc --- /dev/null +++ b/granite-4.0-350m-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:964c6fc2e0c73d6ec5ec9fb85d94145adfb924284f865a97f30218acef189299 +size 229388064 diff --git a/granite-4.0-350m-IQ4_XS.gguf b/granite-4.0-350m-IQ4_XS.gguf new file mode 100644 index 0000000..26292ea --- /dev/null +++ b/granite-4.0-350m-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae79acd677add0b5acb0d8b250902e72bd9dc329eb21ff1182b9510bdb96825a +size 221818656 diff --git a/granite-4.0-350m-Q3_K_M.gguf b/granite-4.0-350m-Q3_K_M.gguf new file mode 100644 index 0000000..c747765 --- /dev/null +++ b/granite-4.0-350m-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0221ced8cc6282b1b9fb0b31770fca10a5f06fe10bd2086e8e48e2b798e6264 +size 208326432 diff --git a/granite-4.0-350m-Q3_K_S.gguf b/granite-4.0-350m-Q3_K_S.gguf new file mode 100644 index 0000000..0cace62 --- /dev/null +++ b/granite-4.0-350m-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:19f6eba2bc4559cc5ad4ab539a781cec3d089aabfbd73dd79be761717fa2b8bd +size 195325728 diff --git a/granite-4.0-350m-Q4_0.gguf b/granite-4.0-350m-Q4_0.gguf new file mode 100644 index 0000000..b68e1e4 --- /dev/null +++ b/granite-4.0-350m-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d079f6c8a9b425e6c7aca25afbd34d72091984246bf6409b800a8f81c257ea1f +size 228863776 diff --git a/granite-4.0-350m-Q4_1.gguf b/granite-4.0-350m-Q4_1.gguf new file mode 100644 index 0000000..983e816 --- /dev/null +++ b/granite-4.0-350m-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d990657eba5d75a61714bac0f7f67cac2fc796279fd28de75a013614eb964559 +size 244068128 diff --git a/granite-4.0-350m-Q4_K_M.gguf b/granite-4.0-350m-Q4_K_M.gguf new file mode 100644 index 0000000..6768a8e --- /dev/null +++ b/granite-4.0-350m-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:84f8ee2d191f49a26dee7928039ecbca7079403ccd6817652bd5e834ca40b6d5 +size 236986144 diff --git a/granite-4.0-350m-Q4_K_S.gguf b/granite-4.0-350m-Q4_K_S.gguf new file mode 100644 index 0000000..dde54b4 --- /dev/null +++ b/granite-4.0-350m-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32a3dd7db1fc35e4e325fceb95ac1e0036ec1e8d5c10cae3c337501f07a8aaa9 +size 229388064 diff --git a/granite-4.0-350m-Q5_K_M.gguf b/granite-4.0-350m-Q5_K_M.gguf new file mode 100644 index 0000000..14b4667 --- /dev/null +++ b/granite-4.0-350m-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:463151ec5563a0f7e6a11bab02dc813dcdc1e46236ffdfa736c862c0bf0fd13b +size 264052512 diff --git a/granite-4.0-350m-Q5_K_S.gguf b/granite-4.0-350m-Q5_K_S.gguf new file mode 100644 index 0000000..56b8238 --- /dev/null +++ b/granite-4.0-350m-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93fc0e43891fb3d9cfd62fbf5d539b432c6f35c7e66e425426ef0a77370cc2db +size 259665696 diff --git a/granite-4.0-350m-Q6_K.gguf b/granite-4.0-350m-Q6_K.gguf new file mode 100644 index 0000000..f42642d --- /dev/null +++ b/granite-4.0-350m-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0e25ea454fa42a722303fdca026f20e77fa31e3db51f1b08c25991e443dbd14 +size 292810528 diff --git a/granite-4.0-350m-Q8_0.gguf b/granite-4.0-350m-Q8_0.gguf new file mode 100644 index 0000000..959e04f --- /dev/null +++ b/granite-4.0-350m-Q8_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ec711b8b5e71f98b88132c658d02d7bfa47f3a8525f5b51e130c0c1e99556e9 +size 378138400 diff --git a/granite-4.0-350m-UD-IQ3_XXS.gguf b/granite-4.0-350m-UD-IQ3_XXS.gguf new file mode 100644 index 0000000..006043c --- /dev/null +++ b/granite-4.0-350m-UD-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b56d32edb03a350985818c20d11faa008afb7ce0ae4f40bdbd0deb8e65075ce3 +size 172142368 diff --git a/granite-4.0-350m-UD-Q3_K_XL.gguf b/granite-4.0-350m-UD-Q3_K_XL.gguf new file mode 100644 index 0000000..dd6a8fa --- /dev/null +++ b/granite-4.0-350m-UD-Q3_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:934cf1ec03423d1935ac0a8883e4fb1796d26365ebe577e51f809f232a847c18 +size 213272352 diff --git a/granite-4.0-350m-UD-Q4_K_XL.gguf b/granite-4.0-350m-UD-Q4_K_XL.gguf new file mode 100644 index 0000000..0beb8fd --- /dev/null +++ b/granite-4.0-350m-UD-Q4_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fd597eb32557fabb17695eaeb4f367f286dc67d464b0f97c904d70373d067d3 +size 240742176 diff --git a/granite-4.0-350m-UD-Q5_K_XL.gguf b/granite-4.0-350m-UD-Q5_K_XL.gguf new file mode 100644 index 0000000..103c914 --- /dev/null +++ b/granite-4.0-350m-UD-Q5_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b78e32b40b3b4b241e31a7167595b538162ca0cb964a1a492d245a8f4944eaca +size 265213728 diff --git a/granite-4.0-350m-UD-Q6_K_XL.gguf b/granite-4.0-350m-UD-Q6_K_XL.gguf new file mode 100644 index 0000000..90bed7b --- /dev/null +++ b/granite-4.0-350m-UD-Q6_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2498de1f74f53bb1e0dff9e691f8e9d34638045870bb56b7c580e22c414f84d5 +size 338521888 diff --git a/granite-4.0-350m-UD-Q8_K_XL.gguf b/granite-4.0-350m-UD-Q8_K_XL.gguf new file mode 100644 index 0000000..c2222ae --- /dev/null +++ b/granite-4.0-350m-UD-Q8_K_XL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bcf826bb96a7f28181d84b3d1ab98d3716995531603892f3af5de5f2606f66a +size 516992800 diff --git a/imatrix_unsloth.gguf_file b/imatrix_unsloth.gguf_file new file mode 100644 index 0000000..e1b524b Binary files /dev/null and b/imatrix_unsloth.gguf_file differ