Super-squash branch 'main' using huggingface_hub

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,42 @@
+---
+license: apache-2.0
+base_model: pszemraj/jamba-900M-v0.13-KIx2
+tags:
+- textbook
+- '16384'
+- long document
+metrics:
+- accuracy
+language:
+- en
+inference: false
+---
+
+# BEE-spoke-data/Jamba-900M-doc-writer
+
+> to test it out, try [this notebook](https://colab.research.google.com/gist/pszemraj/28985fdbbb2460f8375d2d84b8babe9a/jamba-test-sandbox.ipynb)
+
+This model produces long, surprisingly coherent output that extends some input text; you can see an example [here](https://gist.github.com/pszemraj/b7c7ac65e56365cf5eab69622f16b356), which is a generated textbook about underwater city design.
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/60bccec062080d33f875cd0c/wWCnoAQ1NSoa3k4w3xvP9.png)
+
+
+Thanks to the Jamba arch, it uses low VRAM while generating outputs: about 2.5 GB VRAM to generate 12,288 tokens.
+
+## Model description
+
+This model is a fine-tuned version of [pszemraj/jamba-900M-v0.13-KIx2](https://huggingface.co/pszemraj/jamba-900M-v0.13-KIx2) on some textbook data.
+
+It achieves the following results on the evaluation set:
+- Loss: 3.0200
+- Accuracy: 0.4544
+- Num Input Tokens Seen: 4940890112
+
+## Intended Uses & Limitations
+
+- Long context generation
+- It requires a rather long prompt (aka 'Introduction') to be coaxed into consistently producing long, textbook-like text
+- this model itself is small, so its reasoning, knowledge, etc. is limited, but still impressive for the size (hidden size 1024)
+
+---

config.json

@@ -0,0 +1,42 @@
+{
+  "_name_or_path": "BEE-spoke-data/Jamba-900M-v0.14-giblen",
+  "architectures": [
+    "JambaForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "attn_layer_offset": 2,
+  "attn_layer_period": 4,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "expert_layer_offset": 1,
+  "expert_layer_period": 2,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 4096,
+  "mamba_conv_bias": true,
+  "mamba_d_conv": 4,
+  "mamba_d_state": 16,
+  "mamba_dt_rank": 256,
+  "mamba_expand": 2,
+  "mamba_proj_bias": false,
+  "max_position_embeddings": 16384,
+  "model_type": "jamba",
+  "num_attention_heads": 32,
+  "num_experts": 8,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 12,
+  "num_key_value_heads": 8,
+  "num_logits_to_keep": 1,
+  "output_router_logits": false,
+  "pad_token_id": 0,
+  "rms_norm_eps": 1e-06,
+  "router_aux_loss_coef": 0.001,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.41.0",
+  "use_cache": true,
+  "use_mamba_kernels": true,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 0,
+  "transformers_version": "4.41.0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90e07406cc8859bc8f88f2c6df618c433205f9cb210ce10fcbb10fdd61d059e2
+size 1775951936

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<EOT>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<EOT>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<EOT>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,51 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<EOT>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<META>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "<META_START>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "3": {
+      "content": "<META_END>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "4": {
+      "content": "<SOS>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<EOT>",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<EOT>",
+  "model_max_length": 200000,
+  "tokenizer_class": "GPT2Tokenizer",
+  "unk_token": "<EOT>"
+}