Model save

README.md

@@ -1,77 +1,49 @@
 ---
-datasets:
-- abideen/Cosmopedia-100k-pretrai-
-- LLMs/Alpaca-ShareGPT
-- roneneldan/TinyStories
-- Salesforce/wikitext
+base_model: liminerity/Bitnet-Mistral.0.2-v6.9
 tags:
-- Mistral
-- 1bit
-- bitnet
-- abideen
+- generated_from_trainer
+model-index:
+- name: Bitnet-Mistral.0.2-v6.9
+  results: []
 ---
 
-How to Use.
-This code snippet loads the model and tokenizer to the cudae device, and converts the any linear layers in 
-all child modules to -1, 1, or 0.
-This code can also be used to convert a fair amount of models to 1.58bit, however they will need to be trained before you can use 
-them as they become extremly losyy.
-```
-from transformers import AutoModelForCausalLM, AutoTokenizer
-from transformers.models.llama.modeling_llama import *
-# Load a pretrained BitNet model
-model = "liminerity/Bitnet-Mistral.0.2-v6.9"
-tokenizer = AutoTokenizer.from_pretrained(model)
-model = AutoModelForCausalLM.from_pretrained(model)
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
 
+# Bitnet-Mistral.0.2-v6.9
 
-def activation_quant(x):
-    scale = 127.0 / x.abs().max(dim=-1, keepdim=True).values.clamp_(min=1e-5)
-    y = (x * scale).round().clamp_(-128, 127)
-    y = y / scale
-    return y
-def weight_quant(w):
-    scale = 1.0 / w.abs().mean().clamp_(min=1e-5)
-    u = (w * scale).round().clamp_(-1, 1)
-    u = u / scale
-    return u
+This model is a fine-tuned version of [liminerity/Bitnet-Mistral.0.2-v6.9](https://huggingface.co/liminerity/Bitnet-Mistral.0.2-v6.9) on the None dataset.
 
-class BitLinear(nn.Linear):
-    def forward(self, x):
-        w = self.weight # a weight tensor with shape [d, k]
-        x = x.to(w.device)
-        RMSNorm = LlamaRMSNorm(x.shape[-1]).to(w.device)
-        x_norm = RMSNorm(x)
-        # A trick for implementing Straight−Through−Estimator (STE) using detach()
-        x_quant = x_norm + (activation_quant(x_norm) - x_norm).detach()
-        w_quant = w + (weight_quant(w) - w).detach()
-        y = F.linear(x_quant, w_quant)
-        return y
+## Model description
 
-def convert_to_bitnet(model, copy_weights):
-    for name, module in model.named_modules():
-        # Replace linear layers with BitNet
-        if isinstance(module, LlamaSdpaAttention) or isinstance(module, LlamaMLP):
-            for child_name, child_module in module.named_children():
-                if isinstance(child_module, nn.Linear):
-                    bitlinear = BitLinear(child_module.in_features, child_module.out_features, child_module.bias is not None).to(device="cuda:0")
-                    if copy_weights:
-                        bitlinear.weight = child_module.weight
-                        if child_module.bias is not None:
-                            bitlinear.bias = child_module.bias
-                    setattr(module, child_name, bitlinear)
-        # Remove redundant input_layernorms
-        elif isinstance(module, LlamaDecoderLayer):
-            for child_name, child_module in module.named_children():
-                if isinstance(child_module, LlamaRMSNorm) and child_name == "input_layernorm":
-                    setattr(module, child_name, nn.Identity().to(device="cuda:0"))
+More information needed
 
+## Intended uses & limitations
 
-convert_to_bitnet(model, copy_weights=True)
-model.to(device="cuda:0")
+More information needed
 
-prompt = "What is Machine Learning?"
-inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
-generate_ids = model.generate(inputs.input_ids, max_length=50)
-tokenizer.batch_decode(generate_ids, skip_special_tokens=True, clean_up_tokenization_spaces=False)[0]
-```
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 0.005
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: linear
+- num_epochs: 3
+
+### Framework versions
+
+- Transformers 4.41.2
+- Pytorch 2.3.0+cu121
+- Datasets 2.20.0
+- Tokenizers 0.19.1

final_model/config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "liminerity/Bitnet-Mistral.0.2-v6.9",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 256,
+  "initializer_range": 0.02,
+  "intermediate_size": 512,
+  "max_position_embeddings": 4096,
+  "model_type": "mistral",
+  "num_attention_heads": 8,
+  "num_hidden_layers": 24,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.41.2",
+  "use_cache": true,
+  "vocab_size": 32000
+}

final_model/generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.41.2"
+}

final_model/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:05985f5e4c4180e8a501137cf7bcc5a2d13a3f94a0dd475ff4494460e434eed7
+size 128524840

final_model/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": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

final_model/tokenizer.model

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

final_model/tokenizer_config.json

@@ -0,0 +1,42 @@
+{
+  "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
+    }
+  },
+  "bos_token": "<s>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false
+}

final_model/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fb96ca85885e2d93da071581f263a71b8c8722510bbc4107be59b3442c9034
+size 5304

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.41.2"
+}

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1667afa824bd2b8cfeb8139c255f9e2d4d069117961b54a1ba2dd4783f4d7622
+oid sha256:05985f5e4c4180e8a501137cf7bcc5a2d13a3f94a0dd475ff4494460e434eed7
 size 128524840

runs/Jun28_18-25-28_e63ef39226bb/events.out.tfevents.1719599151.e63ef39226bb.5920.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4072015ed5797f65591b0b006f6906eea55b743b7bedc3b3fd7e0cdcc4417ac
+size 12995

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6093ede7cac8225f3a19ec50a6e634a2066a037951d940b11f496d37aaaf677e
-size 5240
+oid sha256:35fb96ca85885e2d93da071581f263a71b8c8722510bbc4107be59b3442c9034
+size 5304