Upload folder using huggingface_hub

README.md

@@ -1,18 +1,21 @@
 ---
 license: mit
+tags:
+- mlx
 ---
-A 16/32 QLoRa all linear layers finetune of Openhermes-2.5-mistral-7 using SNOMED-CT controlled natural language (CNL) phrases 
-(learned with input-masked, completion-only loss) and expert-authored definitions 
-(learned with continued pretraining using mlx_lm) from its disorder, finding, morphological abnormality, and situation hierarchies.
 
-Definition Rendering Instruction Finetuning (DRIFT) 
+# cogbuji/Mr-Grammatology-clinical-problems-Mistral-7B-0.5
+This model was converted to MLX format from [`cogbuji/Mr-Grammatology-clinical-problems-Mistral-7B-0.5`]().
+Refer to the [original model card](https://huggingface.co/cogbuji/Mr-Grammatology-clinical-problems-Mistral-7B-0.5) for more details on the model.
+## Use with mlx
 
-42,096 training iterations on a dataset of 336,762 records, 8 at a time. Validated against 40% keep aside of 
-granular definition instructions, 51,082 records. Reporting validation loss every 4,209 steps, validating with 526 batches.
+```bash
+pip install mlx-lm
+```
 
-Calculating loss every 420 steps, 
+```python
+from mlx_lm import load, generate
 
-Hyperparameters:
-Cosine annealing, 1000 step warmup to 6e-06. 8 batch size, 16 QLoRa layers . No weight decay, and with Adam optimizer
-
-Uses: mlx_lm, mlx-tuning-fork, ogbujipt, django-snomed-ct
+model, tokenizer = load("cogbuji/Mr-Grammatology-clinical-problems-Mistral-7B-0.5")
+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 +1,80 @@
+{
+ "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/oori/medical_llm/raw_models/mlx/other",
+ "transformers_version": "4.37.0",
+ "model_type": "mistral"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a8e70339f19ea9fe5811f6f6bd86a04c2db632762850d24643dd6fd8f6277eb
+size 5261963013

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a31a4c8bdbbb58378bc53068c465b8230f39cae23a35d90840e73a143332214
+size 5352141111

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c2a7fc34bb8004cbee7787524a66b603c79d260fe224b243853f23387a5691c
+size 3869426317

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+ "metadata": {
+ "total_size": 14483496960
+ },
+ "weight_map": {
+ "lm_head.weight": "model-00003-of-00003.safetensors",
+ "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+ "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+ "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+ "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+ "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+ "model.norm.weight": "model-00003-of-00003.safetensors"
+ }
+}

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}")