Upload 7 files

README.md

@@ -0,0 +1,51 @@
+---
+license: apache-2.0
+language:
+ - en
+ - fr
+ - de
+ - es
+ - it
+ - pt
+ - ru
+ - zh
+ - ja
+pipeline_tag: text-generation
+base_model: anthracite-org/magnum-12b-v2
+tags:
+- chat
+---
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/658a46cbfb9c2bdfae75b3a6/sWYs3iHkn36lw6FT_Y7nn.png)
+
+v2.5 KTO is an experimental release; we are testing a hybrid reinforcement learning strategy of KTO + DPOP, using rejected data sampled from the original model as "rejected". For "chosen", we use data from the original finetuning dataset as "chosen".
+This was done on a limited portion of of primarily instruction following data; we plan to scale up a larger KTO dataset in the future for better generalization.
+
+This is the 5th in a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet and Opus. This model is fine-tuned on top of [anthracite-org/magnum-12b-v2](https://huggingface.co/anthracite-org/magnum-12b-v2).
+
+## Prompting
+Model has been Instruct tuned with the ChatML formatting. A typical input would look like this:
+
+```py
+"""<|im_start|>user
+Hi there!<|im_end|>
+<|im_start|>assistant
+Nice to meet you!<|im_end|>
+<|im_start|>user
+Can I ask a question?<|im_end|>
+<|im_start|>assistant
+"""
+```
+
+## Credits
+- Stheno dataset (filtered)
+- [kalomaze/Opus_Instruct_25k](https://huggingface.co/datasets/kalomaze/Opus_Instruct_25k)
+- [Nopm/Opus_WritingStruct](https://huggingface.co/datasets/Nopm/Opus_WritingStruct)
+- [Gryphe/Sonnet3.5-SlimOrcaDedupCleaned](https://huggingface.co/datasets/Gryphe/Sonnet3.5-SlimOrcaDedupCleaned) (A ~16k rows subset)
+- [kalomaze/Opus_Instruct_3k](https://huggingface.co/datasets/kalomaze/Opus_Instruct_3k)
+
+This model has been a team effort, and the credits goes to all members of Anthracite.
+
+## Safety
+...

config.json

@@ -0,0 +1,38 @@
+{
+ "_name_or_path": "magnum-12b-v2.5-kto",
+ "architectures": [
+ "MistralForCausalLM"
+ ],
+ "attention_dropout": 0.0,
+ "bos_token_id": 1,
+ "eos_token_id": 15,
+ "head_dim": 128,
+ "hidden_act": "silu",
+ "hidden_size": 5120,
+ "initializer_range": 0.02,
+ "intermediate_size": 14336,
+ "max_position_embeddings": 1024000,
+ "model_type": "mistral",
+ "num_attention_heads": 32,
+ "num_hidden_layers": 40,
+ "num_key_value_heads": 8,
+ "rms_norm_eps": 1e-05,
+ "rope_theta": 1000000.0,
+ "sliding_window": null,
+ "tie_word_embeddings": false,
+ "torch_dtype": "float16",
+ "transformers_version": "4.43.3",
+ "use_cache": false,
+ "vocab_size": 131072,
+ "quantization_config": {
+ "quant_method": "exl2",
+ "version": "0.2.2",
+ "bits": 4.0,
+ "head_bits": 6,
+ "calibration": {
+ "rows": 115,
+ "length": 2048,
+ "dataset": "(default)"
+ }
+ }
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+ "_from_model_config": true,
+ "bos_token_id": 1,
+ "do_sample": true,
+ "eos_token_id": 2,
+ "transformers_version": "4.43.3"
+}

output.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:26786d29cefc46cd712fbc5b779e548d6102b521a8c47550bdec73f26596a1b3
+size 7317045916

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+ "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
+ }
+}