Upload folder using huggingface_hub

README.md

@@ -0,0 +1,34 @@
+---
+language:
+- en
+license: apache-2.0
+tags:
+- mistral
+- instruct
+- finetune
+- chatml
+- gpt4
+- synthetic data
+- distillation
+- mlx
+base_model: mistralai/Mistral-7B-v0.1
+model-index:
+- name: OpenHermes-2-Mistral-7B
+  results: []
+---
+
+# mlx-community/OpenHermes-2.5-Mistral-7B-4bit-mlx
+This model was converted to MLX format from [`teknium/OpenHermes-2.5-Mistral-7B`]().
+Refer to the [original model card](https://huggingface.co/teknium/OpenHermes-2.5-Mistral-7B) 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/OpenHermes-2.5-Mistral-7B-4bit-mlx")
+response = generate(model, tokenizer, prompt="hello", verbose=True)
+```

added_tokens.json

@@ -0,0 +1,4 @@
+{
+  "<|im_end|>": 32000,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,84 @@
+{
+    "vocab_size": 32002,
+    "max_position_embeddings": 32768,
+    "hidden_size": 4096,
+    "intermediate_size": 14336,
+    "num_hidden_layers": 32,
+    "num_attention_heads": 32,
+    "sliding_window": 4096,
+    "num_key_value_heads": 8,
+    "hidden_act": "silu",
+    "initializer_range": 0.02,
+    "rms_norm_eps": 1e-05,
+    "use_cache": false,
+    "rope_theta": 10000.0,
+    "attention_dropout": 0.0,
+    "return_dict": true,
+    "output_hidden_states": false,
+    "output_attentions": false,
+    "torchscript": false,
+    "torch_dtype": "bfloat16",
+    "use_bfloat16": false,
+    "tf_legacy_loss": false,
+    "pruned_heads": {},
+    "tie_word_embeddings": false,
+    "chunk_size_feed_forward": 0,
+    "is_encoder_decoder": false,
+    "is_decoder": false,
+    "cross_attention_hidden_size": null,
+    "add_cross_attention": false,
+    "tie_encoder_decoder": false,
+    "max_length": 20,
+    "min_length": 0,
+    "do_sample": false,
+    "early_stopping": false,
+    "num_beams": 1,
+    "num_beam_groups": 1,
+    "diversity_penalty": 0.0,
+    "temperature": 1.0,
+    "top_k": 50,
+    "top_p": 1.0,
+    "typical_p": 1.0,
+    "repetition_penalty": 1.0,
+    "length_penalty": 1.0,
+    "no_repeat_ngram_size": 0,
+    "encoder_no_repeat_ngram_size": 0,
+    "bad_words_ids": null,
+    "num_return_sequences": 1,
+    "output_scores": false,
+    "return_dict_in_generate": false,
+    "forced_bos_token_id": null,
+    "forced_eos_token_id": null,
+    "remove_invalid_values": false,
+    "exponential_decay_length_penalty": null,
+    "suppress_tokens": null,
+    "begin_suppress_tokens": null,
+    "architectures": [
+        "MistralForCausalLM"
+    ],
+    "finetuning_task": null,
+    "id2label": {
+        "0": "LABEL_0",
+        "1": "LABEL_1"
+    },
+    "label2id": {
+        "LABEL_0": 0,
+        "LABEL_1": 1
+    },
+    "tokenizer_class": null,
+    "prefix": null,
+    "bos_token_id": 1,
+    "pad_token_id": null,
+    "eos_token_id": 32000,
+    "sep_token_id": null,
+    "decoder_start_token_id": null,
+    "task_specific_params": null,
+    "problem_type": null,
+    "_name_or_path": "/Users/andrei/.cache/huggingface/hub/models--teknium--OpenHermes-2.5-Mistral-7B/snapshots/91ed666be78da7556f3d79abbb26fff0ee26cb54",
+    "transformers_version": "4.37.1",
+    "model_type": "mistral",
+    "quantization": {
+        "group_size": 64,
+        "bits": 4
+    }
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ecb1527e1eb816dd7859de56891efb860d020f95a3b265a05101607ed842fd8f
+size 4262378048

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
+  }
+}

tokenizer.model

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

tokenizer_config.json

@@ -0,0 +1,61 @@
+{
+  "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
+    },
+    "32000": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "32001": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "trust_remote_code": false,
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true,
+  "use_fast": true
+}

transformers_inference.py

@@ -0,0 +1,32 @@
+# Code to inference Open Hermes 2.5 with HF Transformers
+# Requires pytorch, transformers, bitsandbytes, sentencepiece, protobuf, and flash-attn packages
+
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM
+from transformers import LlamaTokenizer, LlamaForCausalLM, MistralForCausalLM
+import bitsandbytes, flash_attn
+
+tokenizer = LlamaTokenizer.from_pretrained('teknium/OpenHermes-2.5-Mistral-7B', trust_remote_code=True)
+model = MistralForCausalLM.from_pretrained(
+    "teknium/OpenHermes-2.5-Mistral-7B",
+    torch_dtype=torch.float16,
+    device_map="auto",#{'': 'cuda:0'},
+    load_in_8bit=False,
+    load_in_4bit=True,
+    use_flash_attention_2=True
+)
+
+prompts = [
+    """<|im_start|>system
+You are a sentient, superintelligent artificial general intelligence, here to teach and assist me.<|im_end|>
+<|im_start|>user
+Write a short story about Goku discovering kirby has teamed up with Majin Buu to destroy the world.<|im_end|>
+<|im_start|>assistant""",
+    ]
+
+for chat in prompts:
+    print(chat)
+    input_ids = tokenizer(chat, return_tensors="pt").input_ids.to("cuda")
+    generated_ids = model.generate(input_ids, max_new_tokens=750, temperature=0.8, repetition_penalty=1.1, do_sample=True, eos_token_id=tokenizer.eos_token_id)
+    response = tokenizer.decode(generated_ids[0][input_ids.shape[-1]:], skip_special_tokens=True, clean_up_tokenization_space=True)
+    print(f"Response: {response}")