Upload folder using huggingface_hub

README.md

@@ -0,0 +1,26 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- mlx
+datasets:
+- teknium/OpenHermes-2.5
+base_model: mistral-community/Mixtral-8x22B-v0.1
+---
+
+# mlx-community/mixtral-8x22b-instruct-oh-4bit
+This model was converted to MLX format from [`fireworks-ai/mixtral-8x22b-instruct-oh`]() using mlx-lm version **0.9.0**.
+Refer to the [original model card](https://huggingface.co/fireworks-ai/mixtral-8x22b-instruct-oh) for more details on the model.
+## Use with mlx
+
+```bash
+pip install mlx-lm
+```
+
+```python
+from mlx_lm import load, generate
+
+model, tokenizer = load("mlx-community/mixtral-8x22b-instruct-oh-4bit")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

config.json

@@ -0,0 +1,88 @@
+{
+    "add_cross_attention": false,
+    "architectures": [
+        "MixtralForCausalLM"
+    ],
+    "attention_dropout": 0.0,
+    "bad_words_ids": null,
+    "begin_suppress_tokens": null,
+    "bos_token_id": 1,
+    "chunk_size_feed_forward": 0,
+    "cross_attention_hidden_size": null,
+    "decoder_start_token_id": null,
+    "diversity_penalty": 0.0,
+    "do_sample": false,
+    "early_stopping": false,
+    "encoder_no_repeat_ngram_size": 0,
+    "eos_token_id": 2,
+    "exponential_decay_length_penalty": null,
+    "finetuning_task": null,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "hidden_act": "silu",
+    "hidden_size": 6144,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "initializer_range": 0.02,
+    "intermediate_size": 16384,
+    "is_decoder": false,
+    "is_encoder_decoder": false,
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "length_penalty": 1.0,
+    "max_length": 20,
+    "max_position_embeddings": 65536,
+    "min_length": 0,
+    "model_type": "mixtral",
+    "no_repeat_ngram_size": 0,
+    "num_attention_heads": 48,
+    "num_beam_groups": 1,
+    "num_beams": 1,
+    "num_experts_per_tok": 2,
+    "num_hidden_layers": 56,
+    "num_key_value_heads": 8,
+    "num_local_experts": 8,
+    "num_return_sequences": 1,
+    "output_attentions": false,
+    "output_hidden_states": false,
+    "output_router_logits": false,
+    "output_scores": false,
+    "pad_token_id": null,
+    "prefix": null,
+    "problem_type": null,
+    "pruned_heads": {},
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    },
+    "remove_invalid_values": false,
+    "repetition_penalty": 1.0,
+    "return_dict": true,
+    "return_dict_in_generate": false,
+    "rms_norm_eps": 1e-05,
+    "rope_theta": 1000000,
+    "router_aux_loss_coef": 0.001,
+    "router_jitter_noise": 0.0,
+    "sep_token_id": null,
+    "sliding_window": null,
+    "suppress_tokens": null,
+    "task_specific_params": null,
+    "temperature": 1.0,
+    "tf_legacy_loss": false,
+    "tie_encoder_decoder": false,
+    "tie_word_embeddings": false,
+    "tokenizer_class": null,
+    "top_k": 50,
+    "top_p": 1.0,
+    "torch_dtype": "float16",
+    "torchscript": false,
+    "transformers_version": "4.38.2",
+    "typical_p": 1.0,
+    "use_bfloat16": false,
+    "use_cache": true,
+    "vocab_size": 32000
+}

model-00001-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:afeb3fa1b3e0f937727eeb2b2fdf984e790418fde3fa514ae36752825d916a94
+size 5348243543

model-00002-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:999668136b0c0da712f315c03c37660d7d8a35425987427db55837cc404faa24
+size 5351416647

model-00003-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9fac733a2e2e55ad33196e316a7867b8267cc2de34edeee6a1d45e6c8ee24265
+size 5351416767

model-00004-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9cc94f320ae1f6a4c0530eebb2e090c91bd6f77e6ed158ffe1c01532a1683a93
+size 5358370676

model-00005-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ee47a7aa0661ae32cd383574185b69435c4ae98715e053a38298bfbd447d222
+size 5351416986

model-00006-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b6fe6fec703f7eb096a5f5454961b3b70b0da7154a222261e4f245e429fadde5
+size 5351416970

model-00007-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b2141e92d1801b2e510a07d4ff978b585680435b64808d712c17e451b0970772
+size 5351416986

model-00008-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:75a58556b84c6b7db35123530aae93808420802fa0bec1999bb280946457a0a0
+size 5351416926

model-00009-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3bd00c097570d406b1f603be357614c81fafeab03f10aee01b3d5f0d20cc0af7
+size 5358370660

model-00010-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ae3891d7f964d57b4b2f8ca6a0547acab38874e631df8eb16c9f020a50fa4c2
+size 5351416978

model-00011-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d9831522b31f8f3ce0f4c6cd3056a17c4caa4fd65a1de6b8257b25c178b7652
+size 5351416972

model-00012-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5799b85f4b9066587f429b06de6d069dee537f7e2b999817595ef0681c3e2a66
+size 5351416998

model-00013-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:120d68606672a1e680fccd4cbb6b6cb58574c36470ae9d6d5c1f638755986933
+size 5351416966

model-00014-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:419d42c91cfa30fc828da014e0ee2099ca9758208af0c5838e33b53111e58c70
+size 5358370678

model-00015-of-00015.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f61e68f9e09500f960612b55479115002a93434812a3f31765ebe276960c311a
+size 4449777255

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "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
+  },
+  "pad_token": {
+    "content": "<unk>",
+    "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 +1,44 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "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": "{%- set message_roles = ['USER', 'ASSISTANT'] -%}\n{%- set ns = namespace(initial_system_message_handled=false, messages=messages) -%}\n{{ bos_token }}\n{%- for message in ns.messages -%}\n  {%- if message['role'] | upper == 'SYSTEM' and not ns.initial_system_message_handled -%}\n    {%- set ns.initial_system_message_handled = true -%}\n    {{'SYSTEM: ' + message['content'] }}\n  {%- elif message['role'] | upper != 'SYSTEM' -%}\n    {%- if (message['role'] | upper == 'USER') != ((loop.index0 - (1 if ns.initial_system_message_handled else 0)) % 2 == 0) -%}\n      {{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}\n    {%- endif -%}\n    {%- if loop.index0 > 0 or ns.initial_system_message_handled -%}\n      {{ '\\n\\n' }}\n    {%- endif -%}\n    {%- if message['role'] | upper == 'USER' -%}\n      {{ 'USER: ' + message['content'] }}\n    {%- elif message['role'] | upper == 'ASSISTANT' -%}\n      {{ 'ASSISTANT: ' + message['content'] + eos_token}}\n    {%- endif -%}\n  {%- endif -%}\n{%- endfor -%}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<unk>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}