Upload model via Google Colab

.gitattributes

@@ -33,3 +33,13 @@ saved_model/**/* 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
+deepseek-r1-redistill-qwen-7b-v1.1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-redistill-qwen-7b-v1.1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-redistill-qwen-7b-v1.1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-redistill-qwen-7b-v1.1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-redistill-qwen-7b-v1.1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-redistill-qwen-7b-v1.1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-redistill-qwen-7b-v1.1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-redistill-qwen-7b-v1.1-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text
+deepseek-r1-redistill-qwen-7b-v1.1-fp16.gguf filter=lfs diff=lfs merge=lfs -text
+imatrix.dat filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,129 @@
+---
+license: mit
+train: false
+inference: true
+pipeline_tag: text-generation
+base_model:
+- deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
+---
+This is a version of the <a href="https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B">DeepSeek-R1-Distill-Qwen-7B</a> model re-distilled for better performance.
+
+## Performance
+
+| Models            | <a href="https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B">DeepSeek-R1-Distill-Qwen-7B</a> | <a href="https://huggingface.co/mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1">DeepSeek-R1-ReDistill-Qwen-7B-v1.1</a> | 
+|:-------------------:|:--------:|:----------------:|
+| ARC (25-shot)      | <b>55.03</b> | 52.3 | 
+| HellaSwag (10-shot)| 61.9  | <b>62.36</b> |
+| MMLU (5-shot)      | 56.75 | <b>59.53</b> | 
+| TruthfulQA-MC2     | 45.76 | <b>47.7</b> | 
+| Winogrande (5-shot)| 60.38 | <b>61.8</b> | 
+| GSM8K (5-shot)     | 78.85 | <b>83.4</b> | 
+| Average            | 59.78 | <b>61.18</b> | 
+
+| Models            | <a href="https://huggingface.co/deepseek-ai/DeepSeek-R1-Distill-Qwen-7B">DeepSeek-R1-Distill-Qwen-7B</a> | <a href="https://huggingface.co/mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1">DeepSeek-R1-ReDistill-Qwen-7B-v1.1</a>  | 
+|:-------------------:|:--------:|:----------------:|
+| GPQA (0-shot)     | 30.9  | <b>34.99</b> | 
+| MMLU PRO (5-shot) | 28.83 | <b>31.02</b> | 
+| MUSR (0-shot)     | 38.85 | <b>44.42</b> | 
+| BBH (3-shot)      | 43.54 | <b>51.53</b> | 
+| IfEval (0-shot) - strict  | <b>42.33</b> | 35.49 | 
+| IfEval (0-shot) - loose   | 30.31 | <b>38.49</b> | 
+
+## Usage
+```Python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+compute_dtype = torch.bfloat16
+device   = 'cuda'
+model_id = "mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1"
+
+model     = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=compute_dtype, attn_implementation="sdpa", device_map=device)
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+
+prompt  = "What is 1.5+102.2?"
+chat    = tokenizer.apply_chat_template([{"role":"user", "content":prompt}], tokenize=True, add_generation_prompt=True, return_tensors="pt")
+outputs = model.generate(chat.to(device), max_new_tokens=1024, do_sample=True) 
+print(tokenizer.decode(outputs[0]))
+```
+
+Output:
+```
+<｜begin▁of▁sentence｜><｜User｜>What is 1.5+102.2?<｜Assistant｜><think>
+First, I need to add the whole number parts of the two numbers. The whole numbers are 1 and 102, which add up to 103.
+
+Next, I add the decimal parts of the two numbers. The decimal parts are 0.5 and 0.2, which add up to 0.7.
+
+Finally, I combine the whole number and decimal parts to get the total sum. Adding 103 and 0.7 gives me 103.7.
+</think>
+
+To add the numbers \(1.5\) and \(102.2\), follow these steps:
+
+1. **Add the whole number parts:**
+   \[
+   1 + 102 = 103
+   \]
+
+2. **Add the decimal parts:**
+   \[
+   0.5 + 0.2 = 0.7
+   \]
+
+3. **Combine the results:**
+   \[
+   103 + 0.7 = 103.7
+   \]
+
+**Final Answer:**
+\[
+\boxed{103.7}
+\]<｜end▁of▁sentence｜>
+```
+
+## HQQ
+Run ~3.5x faster with <a href="https://github.com/mobiusml/hqq/">HQQ</a>. First, install the dependencies:
+```
+pip install hqq
+```
+
+```Python
+import torch
+from transformers import AutoModelForCausalLM, AutoTokenizer
+from hqq.models.hf.base import AutoHQQHFModel
+from hqq.core.quantize import *
+
+#Params
+device        = 'cuda:0'
+backend       = "torchao_int4" 
+compute_dtype = torch.bfloat16 if backend=="torchao_int4" else torch.float16
+model_id      = "mobiuslabsgmbh/DeepSeek-R1-ReDistill-Qwen-7B-v1.1"
+
+#Load
+tokenizer = AutoTokenizer.from_pretrained(model_id)
+model     = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=compute_dtype, attn_implementation="sdpa")
+
+#Quantize
+quant_config = BaseQuantizeConfig(nbits=4, group_size=64, axis=1)
+AutoHQQHFModel.quantize_model(model, quant_config=quant_config, compute_dtype=compute_dtype, device=device)
+
+#Optimize
+from hqq.utils.patching import prepare_for_inference
+prepare_for_inference(model, backend=backend, verbose=False)
+
+############################################################
+#Generate (streaming)
+from hqq.utils.generation_hf import HFGenerator
+gen = HFGenerator(model, tokenizer, max_new_tokens=4096, do_sample=True, compile='partial').warmup()
+
+prompt = "If A equals B, and C equals B - A, what would be the value of C?" 
+out    = gen.generate(prompt, print_tokens=True)
+
+############################################################
+# #Generate (simple)
+# from hqq.utils.generation_hf import patch_model_for_compiled_runtime
+# patch_model_for_compiled_runtime(model, tokenizer, warmup=True)
+
+# prompt = "If A equals B, and C equals B - A, what would be the value of C?" 
+# chat    = tokenizer.apply_chat_template([{"role":"user", "content":prompt}], tokenize=True, add_generation_prompt=True, return_tensors="pt")
+# outputs = model.generate(chat.to(device), max_new_tokens=8192, do_sample=True) 
+# print(tokenizer.decode(outputs[0]))
+```

deepseek-r1-redistill-qwen-7b-v1.1-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c4bff73ab778938195e7c856f4751da2e207bb453092388f28b947b696297f3
+size 3015940544

deepseek-r1-redistill-qwen-7b-v1.1-Q2_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e9d6aee55a86974069d8ea03ddfab2be1c5440e2ce3d728a7ea30c73dc01616
+size 2834074048

deepseek-r1-redistill-qwen-7b-v1.1-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d40c99217ceb34d1a7f7d87472252a77ddb625a04f74d8a2bd7e85716338d08f
+size 3808391616

deepseek-r1-redistill-qwen-7b-v1.1-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff8ff30ee356532be20a246e7d928adff4aaec89873f298b2751964bc319862
+size 4444121536

deepseek-r1-redistill-qwen-7b-v1.1-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:477c6051b5bb4cbce544b6f0d402d6b120c6920befacc6e62a581e955cece9ad
+size 4683073984

deepseek-r1-redistill-qwen-7b-v1.1-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d2f5a22470c6b85fcdb43791a2136b6e5e5673305b72e5df22759860bc3ccde
+size 5444831680

deepseek-r1-redistill-qwen-7b-v1.1-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:282f8b5bb29b17f98bc5b7ac3f9f4e2876542c7064f49edb919aa4017cf3fd2e
+size 6254199232

deepseek-r1-redistill-qwen-7b-v1.1-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:674565aa9434bc220327614a690ac4b3f7c006c1039653a3a58c935d5de74c0f
+size 8098525632

deepseek-r1-redistill-qwen-7b-v1.1-fp16.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e01b6c3a067974bdf6fbb5668d3ba69a0cf8f27bfd4a414a8f6e73000a206c3
+size 15237853344

imatrix.dat

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c618fc38a4065f2ad30214f63fad6f63546158a0a01af6f7d3c4f495a85a9fb6
+size 4536697