untested vanilla quant of undi95's

HQQbagelmix_def.py

@@ -0,0 +1,28 @@
+from hqq.engine.hf import HQQModelForCausalLM, AutoTokenizer
+model_path  = "/mnt/ancient240/Undi95_BagelMix-8x7B"
+model     = HQQModelForCausalLM.from_pretrained(model_path)
+
+#Quantize params
+from hqq.core.quantize import *
+#attn_prams     = BaseQuantizeConfig(nbits=4, group_size=64, quant_zero=True, quant_scale=True)
+attn_prams     = BaseQuantizeConfig(nbits=4, group_size=64, quant_zero=True, quant_scale=True)
+attn_prams['scale_quant_params']['group_size'] = 256
+experts_params = BaseQuantizeConfig(nbits=2, group_size=16, quant_zero=True, quant_scale=True)
+
+quant_config = {}
+#Attention
+quant_config['self_attn.q_proj'] = attn_prams
+quant_config['self_attn.k_proj'] = attn_prams
+quant_config['self_attn.v_proj'] = attn_prams
+quant_config['self_attn.o_proj'] = attn_prams
+#Experts
+quant_config['block_sparse_moe.experts.w1'] = experts_params
+quant_config['block_sparse_moe.experts.w2'] = experts_params
+quant_config['block_sparse_moe.experts.w3'] = experts_params
+#print("configured")
+#Quantize
+save_path="models/BagelMix-8x7B-2g16-4g64-HQQ/"
+model.quantize_model(quant_config=quant_config)
+model.save_quantized(save_path)
+
+#brought to you by python -i

README.md

@@ -0,0 +1,55 @@
+---
+base_model:
+- Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss
+- jondurbin/bagel-dpo-8x7b-v0.2
+- NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss
+license: cc-by-nc-4.0
+tags:
+- not-for-all-audiences
+- nsfw
+- mergekit
+- merge
+
+---
+# BagelMix
+
+This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).
+
+## Merge Details
+### Merge Method
+
+This model was merged using the [DARE](https://arxiv.org/abs/2311.03099) [TIES](https://arxiv.org/abs/2306.01708) merge method using [jondurbin/bagel-dpo-8x7b-v0.2](https://huggingface.co/jondurbin/bagel-dpo-8x7b-v0.2) as a base.
+
+### Models Merged
+
+The following models were included in the merge:
+* [Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss](https://huggingface.co/Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss)
+* [NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss](https://huggingface.co/NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss)
+
+### Configuration
+
+The following YAML configuration was used to produce this model:
+
+```yaml
+models:
+  - model: jondurbin/bagel-dpo-8x7b-v0.2
+    parameters:
+      density: 1.0
+      weight: 1.0
+  - model: Doctor-Shotgun/Mixtral-8x7B-Instruct-v0.1-LimaRP-ZLoss
+    parameters:
+      density: 0.5
+      weight: [0.33, 0.4, 0.33]
+  - model: NeverSleep/Noromaid-v0.4-Mixtral-Instruct-8x7b-Zloss
+    parameters:
+      density: [0.33, 0.45, 0.66]
+      weight: 0.66
+merge_method: dare_ties
+base_model: jondurbin/bagel-dpo-8x7b-v0.2
+parameters:
+  normalize: true
+  int8_mask: true
+dtype: bfloat16
+tokenizer_source : union
+```
+If you want to support me, you can [here](https://ko-fi.com/undiai).

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "/mnt/ancient240/Undi95_BagelMix-8x7B",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "num_local_experts": 8,
+  "output_router_logits": false,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "router_aux_loss_coef": 0.02,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.37.1",
+  "use_cache": true,
+  "vocab_size": 32000
+}

qmodel.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7fe1dfdc2993e62bc38d82d52a4c521544cfdb4ab535da1ca76341dff786cfcd
+size 18241882036

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dadfd56d766715c61d2ef780a525ab43b8e6da4de6865bda3d95fdef5e134055
+size 493443

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{%- for idx in range(0, messages|length) -%}\n{%- if messages[idx]['role'] == 'user' -%}\n{%- if idx > 1 -%}\n{{- bos_token + '[INST] ' + messages[idx]['content'] + ' [/INST]' -}}\n{%- else -%}\n{{- messages[idx]['content'] + ' [/INST]' -}}\n{%- endif -%}\n{% elif messages[idx]['role'] == 'system' %}\n{{- '[INST] <<SYS>>\\n' + messages[idx]['content'] + '\\n<</SYS>>\\n\\n' -}}\n{%- elif messages[idx]['role'] == 'assistant' -%}\n{{- ' '  + messages[idx]['content'] + ' ' + eos_token -}}\n{% endif %}\n{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}