Llamacpp quants

.gitattributes

@@ -33,3 +33,19 @@ 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
+NeuralSirKrishna-7b-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-Q5_0.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text
+NeuralSirKrishna-7b-Q8_0.gguf filter=lfs diff=lfs merge=lfs -text

NeuralSirKrishna-7b-IQ3_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46e9e0c90c776acf092064479fcd43b956eac74f4454e5bfc83cb69d7fd26690
+size 3284891360

NeuralSirKrishna-7b-IQ3_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:02ce5f66d03f48b61a627b28326f57a70535d60b49bd46100573825b703328e4
+size 3182393056

NeuralSirKrishna-7b-IQ4_NL.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1aff009a765015a543d361263c62d279391dbbf6b11547c46f7565477027cd7
+size 4155053792

NeuralSirKrishna-7b-IQ4_XS.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d6c0cbe3ee14529cdf601e4b2a04d788cbaeb1edf92910783be0b651f2623197
+size 3944388320

NeuralSirKrishna-7b-Q2_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ca1ff63e9e8a8ba7be6db0c9f90f3cefe361995b2b60c0bbede8c8d02d81880
+size 2719241952

NeuralSirKrishna-7b-Q3_K_L.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:82f07177a80f4a454d706419005f0478ddfa271fbdbe2fc229c99eb876c72019
+size 3822024416

NeuralSirKrishna-7b-Q3_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94061274a63f2885197d539a028296e76920f9c68da933f206f03395052285f0
+size 3518985952

NeuralSirKrishna-7b-Q3_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5034fcb64e91f7a12518d8a018cb544ca1b6de53f3424c4bb7f650c882c88ad9
+size 3164567264

NeuralSirKrishna-7b-Q4_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ce976fb22c62f589a0e528db6e6773b31b55eef81645bd01f0cc8f0e2954e26
+size 4108916448

NeuralSirKrishna-7b-Q4_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae6a36c5d72a150bdc7057bf12f66ebc037814927a3874554b6aca50357d8bd3
+size 4368439008

NeuralSirKrishna-7b-Q4_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4fc02b2c9434eab49a4eb7e99151129d42669d04270148f2aa7dac197cf63059
+size 4140373728

NeuralSirKrishna-7b-Q5_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a79f0913fd92b52e155b5151d153d0a6e37318cc60c1e9f789ea55e425925b35
+size 4997715680

NeuralSirKrishna-7b-Q5_K_M.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e164ce4f6b9f3aee0825ea592ea0a029dd8fb68957bd5f908b1456d69fa5bb29
+size 5131409120

NeuralSirKrishna-7b-Q5_K_S.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e7fea383b3ec2e3d0f219b1916b86b3664056d21b0804efb8c5c59d1518db935
+size 4997715680

NeuralSirKrishna-7b-Q6_K.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f375afb88d7d72150065caa1cb70c9f409d249b0c475a5d7070eeb3bfa66b74b
+size 5942064864

NeuralSirKrishna-7b-Q8_0.gguf

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3ef7bf7c6908ceeed55e102fba71aa68e032f079b99c9dddc8e160a92731c3f
+size 7695857376

README.md

@@ -0,0 +1,144 @@
+---
+license: apache-2.0
+tags:
+- merge
+- mergekit
+- lazymergekit
+- Kukedlc/NeuralKrishna-7B-v3
+- Kukedlc/NeuralMarioMonarch-7B-slerp
+- liminerity/M7-7b
+base_model:
+- Kukedlc/NeuralKrishna-7B-v3
+- Kukedlc/NeuralMarioMonarch-7B-slerp
+- liminerity/M7-7b
+model-index:
+- name: NeuralSirKrishna-7b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 73.72
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 89.05
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.63
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 75.6
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 85.32
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 71.27
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=Kukedlc/NeuralSirKrishna-7b
+      name: Open LLM Leaderboard
+quantized_by: bartowski
+pipeline_tag: text-generation
+---
+
+## Llamacpp Quantizations of NeuralSirKrishna-7b
+
+Using <a href="https://github.com/ggerganov/llama.cpp/">llama.cpp</a> release <a href="https://github.com/ggerganov/llama.cpp/releases/tag/b2440">b2440</a> for quantization.
+
+Original model: https://huggingface.co/Kukedlc/NeuralSirKrishna-7b/
+
+Download a file (not the whole branch) from below:
+
+| Filename | Quant type | File Size | Description |
+| -------- | ---------- | --------- | ----------- |
+| [NeuralSirKrishna-7b-Q8_0.gguf](https://huggingface.co/bartowski/NeuralSirKrishna-7b-GGUF/blob/main/NeuralSirKrishna-7b-Q8_0.gguf) | Q8_0 | 7.69GB | Extremely high quality, generally unneeded but max available quant. |
+| [NeuralSirKrishna-7b-Q6_K.gguf](https://huggingface.co/bartowski/NeuralSirKrishna-7b-GGUF/blob/main/NeuralSirKrishna-7b-Q6_K.gguf) | Q6_K | 5.94GB | Very high quality, near perfect, *recommended*. |
+| [NeuralSirKrishna-7b-Q5_K_M.gguf](https://huggingface.co/bartowski/NeuralSirKrishna-7b-GGUF/blob/main/NeuralSirKrishna-7b-Q5_K_M.gguf) | Q5_K_M | 5.13GB | High quality, very usable. |
+| [NeuralSirKrishna-7b-Q5_K_S.gguf](https://huggingface.co/bartowski/NeuralSirKrishna-7b-GGUF/blob/main/NeuralSirKrishna-7b-Q5_K_S.gguf) | Q5_K_S | 4.99GB | High quality, very usable. |
+| [NeuralSirKrishna-7b-Q5_0.gguf](https://huggingface.co/bartowski/NeuralSirKrishna-7b-GGUF/blob/main/NeuralSirKrishna-7b-Q5_0.gguf) | Q5_0 | 4.99GB | High quality, older format, generally not recommended. |
+| [NeuralSirKrishna-7b-Q4_K_M.gguf](https://huggingface.co/bartowski/NeuralSirKrishna-7b-GGUF/blob/main/NeuralSirKrishna-7b-Q4_K_M.gguf) | Q4_K_M | 4.36GB | Good quality, similar to 4.25 bpw. |
+| [NeuralSirKrishna-7b-Q4_K_S.gguf](https://huggingface.co/bartowski/NeuralSirKrishna-7b-GGUF/blob/main/NeuralSirKrishna-7b-Q4_K_S.gguf) | Q4_K_S | 4.14GB | Slightly lower quality with small space savings. |
+| [NeuralSirKrishna-7b-Q4_0.gguf](https://huggingface.co/bartowski/NeuralSirKrishna-7b-GGUF/blob/main/NeuralSirKrishna-7b-Q4_0.gguf) | Q4_0 | 4.10GB | Decent quality, older format, generally not recommended. |
+| [NeuralSirKrishna-7b-Q3_K_L.gguf](https://huggingface.co/bartowski/NeuralSirKrishna-7b-GGUF/blob/main/NeuralSirKrishna-7b-Q3_K_L.gguf) | Q3_K_L | 3.82GB | Lower quality but usable, good for low RAM availability. |
+| [NeuralSirKrishna-7b-Q3_K_M.gguf](https://huggingface.co/bartowski/NeuralSirKrishna-7b-GGUF/blob/main/NeuralSirKrishna-7b-Q3_K_M.gguf) | Q3_K_M | 3.51GB | Even lower quality. |
+| [NeuralSirKrishna-7b-Q3_K_S.gguf](https://huggingface.co/bartowski/NeuralSirKrishna-7b-GGUF/blob/main/NeuralSirKrishna-7b-Q3_K_S.gguf) | Q3_K_S | 3.16GB | Low quality, not recommended. |
+| [NeuralSirKrishna-7b-Q2_K.gguf](https://huggingface.co/bartowski/NeuralSirKrishna-7b-GGUF/blob/main/NeuralSirKrishna-7b-Q2_K.gguf) | Q2_K | 2.71GB | Extremely low quality, *not* recommended.
+
+Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski