Upload folder using huggingface_hub

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-309/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,290 @@
+---
+library_name: peft
+license: apache-2.0
+base_model: LatitudeGames/Muse-12B
+tags:
+- axolotl
+- base_model:adapter:LatitudeGames/Muse-12B
+- lora
+- transformers
+datasets:
+- grimulkan/LimaRP-augmented
+- ToastyPigeon/steve-and-marvin
+- ToastyPigeon/kimi-stories-completion
+pipeline_tag: text-generation
+model-index:
+- name: muse-marvin-lora
+  results: []
+---
+
+<!-- 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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.13.0.dev0`
+```yaml
+# !pip install transformers==4.55.4
+# !pip install --no-deps trl==0.22.2
+# !pip install --no-build-isolation mamba_ssm==2.2.5
+# !pip install --no-build-isolation causal_conv1d==1.5.2
+# === Model Configuration ===
+base_model: LatitudeGames/Muse-12B
+load_in_8bit: true
+load_in_4bit: false
+
+# === HF Configuration === 
+hub_model_id: ToastyPigeon/muse-marvin-lora
+hub_strategy: "every_save"
+output_dir: ckpts
+
+# === Training Setup ===
+num_epochs: 1
+micro_batch_size: 6
+gradient_accumulation_steps: 1
+sequence_len: 16384
+#sequence_parallel_degree: 2
+#heads_k_stride: 1
+sample_packing: true
+pad_to_sequence_len: true
+#temperature: 0.7
+#max_steps: 10
+# === Evaluation ===
+val_set_size: 0.025
+evals_per_epoch: 10
+#eval_steps: 20
+#max_steps: 60
+#eval_table_size:
+eval_max_new_tokens: 128
+#eval_sample_packing: true
+#eval_strategy: "no"
+
+# === LoRA Configuration ===
+adapter: lora
+lora_model_dir:
+lora_r: 32
+lora_alpha: 32
+lora_dropout: 0.1
+lora_target_linear: true
+lora_target_modules:
+lora_fan_in_fan_out:
+lora_target_modules:
+peft_use_rslora: false
+#lora_modules_to_save:
+#  - embed_tokens
+#  - lm_head
+#fix_untrained_tokens: true
+#lora_mlp_kernel: true
+#lora_qkv_kernel: true
+#lora_o_kernel: true
+
+# === Hyperparameter Configuration ===
+#optimizer: apollo_adamw_layerwise
+#warmup_steps: 0
+warmup_ratio: 0.025
+#optimizer: adamw_torch_fused
+optimizer: paged_adamw_8bit
+#optim_args:
+#  enable_stochastic_rounding: true
+#  enable_cautious: true
+#  enable_8bit: true
+# Apollo-mini configuration:
+#optim_args: "proj=random,rank=128,scale=128.0,scale_type=tensor,update_proj_gap=100"
+# Regular Apollo configuration:
+# optim_args: 
+#optim_target_modules: all_linear
+learning_rate: 1e-5
+lr_scheduler: cosine
+#cosine_min_lr_ratio: 0.2
+#lr_scheduler: cosine_with_min_lr
+#lr_scheduler_kwargs:
+#  cosine_min_lr: 1e-6
+weight_decay: 0.01
+max_grad_norm: 1.0
+#warmup_steps: 0
+#warmup_ratio: 0.025
+
+
+# === Data Configuration ===
+#
+#chat_template: jinja
+#chat_template: chatml
+special_tokens:
+#  eos_token: "<|im_end|>"
+#  eos_token: "</s>"
+#tokenizer_use_mistral_common: true
+shuffle_merged_datasets: true
+datasets:
+  - path: grimulkan/LimaRP-augmented
+    type: chat_template
+    field_messages: conversations
+    message_property_mappings:
+      role: from
+      content: value
+#  - path: allenai/tulu-3-sft-personas-instruction-following
+#    type: chat_template
+#    split: train[:10%]
+#  - path: ToastyPigeon/mixed-medical-reasoning-formatted
+#    type: chat_template
+#    data_files: mixed-medical-thinking.json
+#    split: train[:10%]
+  - path: ToastyPigeon/steve-and-marvin
+    type: completion
+    data_files: marvin.json
+  - path: ToastyPigeon/kimi-stories-completion
+    type: completion
+#  - path: ToastyPigeon/new-story-dataset
+ #   type: customcompletion-regex
+#    type: completion
+#    data_files: new-story-dataset-v2.json
+#  - path: allura-org/fujin-instruct-v2
+#    type: customchatml-regex
+#    type: chat_template
+#    field_messages: conversations
+#    message_property_mappings:
+#      role: from
+#      content: value
+#  - path: ToastyPigeon/some-rp-extended
+ #   type: customchatml-regex
+#    type: chat_template
+#    field_messages: conversations
+#    message_property_mappings:
+#      role: from
+#      content: value
+#    roles_to_train: ["user","assistant"]
+#  - path: ToastyPigeon/gutenberg-sft
+#    type: customchatml-regex
+#    type: chat_template
+#    field_messages: conversations
+#    message_property_mappings:
+#      role: from
+#      content: value
+#  - path: ToastyPigeon/SpringDragon
+#    type: customcompletion-regex
+#    type: completion
+#    split: train
+#  - path: ToastyPigeon/some-erotica
+#    type: customcompletion-regex
+#    type: completion
+#    split: train[:10%]
+
+dataset_prepared_path: last_run_prepared
+
+
+# === Plugins ===
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+  - axolotl.integrations.cut_cross_entropy.CutCrossEntropyPlugin
+
+# === Hardware Optimization ===
+gradient_checkpointing: true
+liger_rope: true
+liger_rms_norm: true
+liger_layer_norm: true
+liger_glu_activation: true
+#liger_fused_linear_cross_entropy: true
+cut_cross_entropy: true
+
+#deepspeed: deepspeed_configs/zero3_bf16.json
+
+# === FSDP Config === 
+#fsdp:
+#  - full_shard
+#  - auto_wrap
+#fsdp_config:
+#  fsdp_limit_all_gathers: true
+#  fsdp_sync_module_states: true
+#  fsdp_offload_params: true
+#  fsdp_activation_checkpointing: true
+#  fsdp_use_orig_params: false
+#  fsdp_cpu_ram_efficient_loading: true
+#  fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
+#  fsdp_transformer_layer_cls_to_wrap: MistralDecoderLayer
+#  fsdp_state_dict_type: FULL_STATE_DICT
+#  fsdp_sharding_strategy: FULL_SHARD
+#  fsdp_version: 2
+# === Wandb Tracking ===
+wandb_project: MuseMarvin
+# wandb_entity: [WANDB_ENTITY]
+# wandb_name: [WANDB_RUN_NAME]
+
+# === Checkpointing ===
+#save_steps: 10
+saves_per_epoch: 10
+save_total_limit: 1
+
+# === Advanced Settings ===
+bf16: auto
+flash_attention: true
+train_on_inputs: false
+group_by_length: false
+save_safetensors: true
+logging_steps: 1
+gc_steps: 10
+seed: 69
+
+
+
+```
+
+</details><br>
+
+# muse-marvin-lora
+
+This model is a fine-tuned version of [LatitudeGames/Muse-12B](https://huggingface.co/LatitudeGames/Muse-12B) on the grimulkan/LimaRP-augmented, the ToastyPigeon/steve-and-marvin and the ToastyPigeon/kimi-stories-completion datasets.
+It achieves the following results on the evaluation set:
+- Loss: 2.3857
+- Memory/max Active (gib): 31.3
+- Memory/max Allocated (gib): 31.3
+- Memory/device Reserved (gib): 32.18
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 6
+- eval_batch_size: 6
+- seed: 69
+- optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 7
+- training_steps: 309
+
+### Training results
+
+| Training Loss | Epoch | Step | Validation Loss | Active (gib) | Allocated (gib) | Reserved (gib) |
+|:-------------:|:-----:|:----:|:---------------:|:------------:|:---------------:|:--------------:|
+| No log        | 0     | 0    | 2.4839          | 31.29        | 31.29           | 32.17          |
+| 2.5492        | 0.1   | 31   | 2.4235          | 31.31        | 31.31           | 32.18          |
+| 2.3906        | 0.2   | 62   | 2.4048          | 31.32        | 31.32           | 32.18          |
+| 2.2984        | 0.3   | 93   | 2.3961          | 31.31        | 31.31           | 32.18          |
+| 2.4423        | 0.4   | 124  | 2.3916          | 31.31        | 31.31           | 32.18          |
+| 2.4106        | 0.5   | 155  | 2.3889          | 31.3         | 31.3            | 32.18          |
+| 2.526         | 0.6   | 186  | 2.3875          | 31.3         | 31.3            | 32.18          |
+| 2.3574        | 0.7   | 217  | 2.3863          | 31.3         | 31.3            | 32.18          |
+| 2.4005        | 0.8   | 248  | 2.3858          | 31.3         | 31.3            | 32.18          |
+| 2.4227        | 0.9   | 279  | 2.3857          | 31.3         | 31.3            | 32.18          |
+
+
+### Framework versions
+
+- PEFT 0.17.1
+- Transformers 4.56.1
+- Pytorch 2.8.0+cu128
+- Datasets 4.0.0
+- Tokenizers 0.22.1

adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "LatitudeGames/Muse-12B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51297695d4b568126cdeb9157568af8577eee65e196c80485f86d7437a82f6b1
+size 456206152

chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-309/README.md

@@ -0,0 +1,208 @@
+---
+base_model: LatitudeGames/Muse-12B
+library_name: peft
+pipeline_tag: text-generation
+tags:
+- axolotl
+- base_model:adapter:LatitudeGames/Muse-12B
+- lora
+- transformers
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.17.1

checkpoint-309/adapter_config.json

@@ -0,0 +1,42 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "LatitudeGames/Muse-12B",
+  "bias": "none",
+  "corda_config": null,
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": null,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 32,
+  "lora_bias": false,
+  "lora_dropout": 0.1,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "qalora_group_size": 16,
+  "r": 32,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "gate_proj",
+    "o_proj",
+    "q_proj",
+    "down_proj",
+    "up_proj",
+    "k_proj",
+    "v_proj"
+  ],
+  "target_parameters": [],
+  "task_type": "CAUSAL_LM",
+  "trainable_token_indices": null,
+  "use_dora": false,
+  "use_qalora": false,
+  "use_rslora": false
+}

checkpoint-309/adapter_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51297695d4b568126cdeb9157568af8577eee65e196c80485f86d7437a82f6b1
+size 456206152

checkpoint-309/chat_template.jinja

@@ -0,0 +1,4 @@
+{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '
+' + message['content'] + '<|im_end|>' + '
+'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant
+' }}{% endif %}

checkpoint-309/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:85ad0b0d3785559deedab2097e42129ecfbfb156c0b1dd482cda7bbee7754959
+size 232299365

checkpoint-309/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0588103378a2c5955cd9d8f1f17c029f093007939a68d05981d0a5b123e6b53c
+size 14645

checkpoint-309/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:260fba912e1f098e076186562bcf75d2c34bb77e084569a3991809df8ad5f6ff
+size 1465

checkpoint-309/special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>"
+  ],
+  "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
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

checkpoint-309/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2fa2956478eaa353c6c4b1f47fdd6868cce6075e52e169c35ae8bd28524e7a8
+size 17078668

checkpoint-309/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc46db0e2535066db01b61fc94cb65ed989288cc65f17c90727e183c52c919b0
+size 7249

config.json

@@ -0,0 +1,41 @@
+{
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "dtype": "bfloat16",
+  "eos_token_id": 131072,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 40,
+  "num_key_value_heads": 8,
+  "quantization_config": {
+    "_load_in_4bit": false,
+    "_load_in_8bit": true,
+    "bnb_4bit_compute_dtype": "float32",
+    "bnb_4bit_quant_storage": "uint8",
+    "bnb_4bit_quant_type": "fp4",
+    "bnb_4bit_use_double_quant": false,
+    "llm_int8_enable_fp32_cpu_offload": false,
+    "llm_int8_has_fp16_weight": false,
+    "llm_int8_skip_modules": null,
+    "llm_int8_threshold": 6.0,
+    "load_in_4bit": false,
+    "load_in_8bit": true,
+    "quant_method": "bitsandbytes"
+  },
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.56.1",
+  "use_cache": false,
+  "vocab_size": 131074
+}

special_tokens_map.json

@@ -0,0 +1,33 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>"
+  ],
+  "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
+  },
+  "pad_token": {
+    "content": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2fa2956478eaa353c6c4b1f47fdd6868cce6075e52e169c35ae8bd28524e7a8
+size 17078668

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fc46db0e2535066db01b61fc94cb65ed989288cc65f17c90727e183c52c919b0
+size 7249