Upload folder using huggingface_hub

README.md

@@ -0,0 +1,20 @@
+---
+base_model: inflatebot/MN-12B-Mag-Mell-R1
+---
+
+[EXL3](https://github.com/turboderp-org/exllamav3) quantization of [MN-12B-Mag-Mell-R1](https://huggingface.co/inflatebot/MN-12B-Mag-Mell-R1), 4 bits per weight.
+
+### HumanEval (argmax)
+
+| Model                                                                                                                  | Q4   | Q6   | Q8   | FP16 |
+| ---------------------------------------------------------------------------------------------------------------------- | ---- | ---- | ---- | ---- |
+| [MN-12B-Mag-Mell-R1-exl3-4bpw](https://huggingface.co/isogen/MN-12B-Mag-Mell-R1-exl3-4bpw) (`mistral`)                 | 72.6 | 71.3 | 73.2 | 72.0 |
+| [MN-12B-Mag-Mell-R1-exl3-4bpw](https://huggingface.co/isogen/MN-12B-Mag-Mell-R1-exl3-4bpw) (`chatml`)                  | 71.3 | 73.2 | 73.2 | 73.8 |
+| [MN-12B-Mag-Mell-R1-exl3-6bpw](https://huggingface.co/isogen/MN-12B-Mag-Mell-R1-exl3-6bpw) (`mistral`)                 | 74.4 | 74.4 | 74.4 | 73.8 |
+| [MN-12B-Mag-Mell-R1-exl3-6bpw](https://huggingface.co/isogen/MN-12B-Mag-Mell-R1-exl3-6bpw) (`chatml`)                  | 76.8 | 72.0 | 72.0 | 71.3 |
+| [Mistral-Nemo-Instruct-2407-exl3-4bpw](https://huggingface.co/isogen/Mistral-Nemo-Instruct-2407-exl3-4bpw) (`mistral`) | 74.4 | 72.6 | 73.2 | 72.0 |
+| [Mistral-Nemo-Instruct-2407-exl3-4bpw](https://huggingface.co/isogen/Mistral-Nemo-Instruct-2407-exl3-4bpw) (`chatml`)  | 70.1 | 72.0 | 71.3 | 72.6 |
+| [Mistral-Nemo-Instruct-2407-exl3-6bpw](https://huggingface.co/isogen/Mistral-Nemo-Instruct-2407-exl3-6bpw) (`mistral`) | 70.7 | 69.5 | 69.5 | 68.9 |
+| [Mistral-Nemo-Instruct-2407-exl3-6bpw](https://huggingface.co/isogen/Mistral-Nemo-Instruct-2407-exl3-6bpw) (`chatml`)  | 68.3 | 70.1 | 69.5 | 68.9 |
+| [Muse-12B-exl3-6bpw](https://huggingface.co/lucyknada/LatitudeGames_Muse-12B-exl3) (`mistral`)                         | 54.9 | 54.3 | 54.9 | 52.4 |
+| [Muse-12B-exl3-6bpw](https://huggingface.co/lucyknada/LatitudeGames_Muse-12B-exl3) (`chatml`)                          | 54.9 | 55.5 | 54.3 | 54.9 |

config.json

@@ -0,0 +1,38 @@
+{
+    "_name_or_path": "IntervitensInc/Mistral-Nemo-Base-2407-chatml",
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bos_token_id": 1,
+    "eos_token_id": 15,
+    "head_dim": 128,
+    "hidden_act": "silu",
+    "hidden_size": 5120,
+    "initializer_range": 0.02,
+    "intermediate_size": 14336,
+    "max_position_embeddings": 1024000,
+    "model_type": "mistral",
+    "num_attention_heads": 32,
+    "num_hidden_layers": 40,
+    "num_key_value_heads": 8,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000.0,
+    "sliding_window": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.44.1",
+    "use_cache": true,
+    "vocab_size": 131072,
+    "quantization_config": {
+        "quant_method": "exl3",
+        "version": "0.0.4",
+        "bits": 4.0,
+        "head_bits": 6,
+        "calibration": {
+            "rows": 100,
+            "cols": 2048
+        },
+        "out_scales": "auto"
+    }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2dc82a3dd8ec8083892a662f27cf01a8add4574a94268fe222da93a000865f5
+size 7306420360

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}