Downloads · 30 days
219
14% of all-time downloads
RichardErkhov/chargoddard_-_mistral-11b-slimorca-gguf
chargoddard_-_mistral-11b-slimorca-gguf is a machine learning model from RichardErkhov. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Downloads · 30 days
219
14% of all-time downloads
All-time downloads
1.6K
Public
Repo size
122 GB
Likes
0
Public
Click a slice to open those files.
.gguf141 GB · 100%
From the Hugging Face model README
Quantization made by Richard Erkhov.
mistral-11b-slimorca - GGUF
| Name | Quant method | Size |
|---|---|---|
| mistral-11b-slimorca.Q2_K.gguf | Q2_K | 3.73GB |
| mistral-11b-slimorca.IQ3_XS.gguf | IQ3_XS | 4.14GB |
| mistral-11b-slimorca.IQ3_S.gguf | IQ3_S | 4.37GB |
| mistral-11b-slimorca.Q3_K_S.gguf | Q3_K_S | 4.34GB |
| mistral-11b-slimorca.IQ3_M.gguf | IQ3_M | 4.51GB |
| mistral-11b-slimorca.Q3_K.gguf | Q3_K | 4.84GB |
| mistral-11b-slimorca.Q3_K_M.gguf | Q3_K_M | 4.84GB |
| mistral-11b-slimorca.Q3_K_L.gguf | Q3_K_L | 5.26GB |
| mistral-11b-slimorca.IQ4_XS.gguf | IQ4_XS | 5.43GB |
| mistral-11b-slimorca.Q4_0.gguf | Q4_0 | 5.66GB |
| mistral-11b-slimorca.IQ4_NL.gguf | IQ4_NL | 5.72GB |
| mistral-11b-slimorca.Q4_K_S.gguf | Q4_K_S | 5.7GB |
| mistral-11b-slimorca.Q4_K.gguf | Q4_K | 6.02GB |
| mistral-11b-slimorca.Q4_K_M.gguf | Q4_K_M | 6.02GB |
| mistral-11b-slimorca.Q4_1.gguf | Q4_1 | 6.27GB |
| mistral-11b-slimorca.Q5_0.gguf | Q5_0 | 6.89GB |
| mistral-11b-slimorca.Q5_K_S.gguf | Q5_K_S | 6.89GB |
| mistral-11b-slimorca.Q5_K.gguf | Q5_K | 7.08GB |
| mistral-11b-slimorca.Q5_K_M.gguf | Q5_K_M | 7.08GB |
| mistral-11b-slimorca.Q5_1.gguf | Q5_1 | 7.51GB |
| mistral-11b-slimorca.Q6_K.gguf | Q6_K | 8.2GB |
| mistral-11b-slimorca.Q8_0.gguf | Q8_0 | 10.62GB |
language:
Full weight fine tuned on two epochs of SlimOrca. Uses Mistral Instruct's prompt format.
The base model for this came from a variation on Undi's Mistral 11B recipe. The o_proj and down_proj tensors were set to zero in the added layers, making the output exactly identical to Mistral 7B before training.
Benchmarks look good locally but still evaluating actual usefulness.
Update: this turned out great! 10/10 would recommend as a training approach.
This mergekit config was used to produce the base model:
slices:
- sources:
- model: mistralai/Mistral-7B-v0.1
layer_range: [0, 24]
- sources: # add middle layers with residuals scaled to zero
- model: mistralai/Mistral-7B-v0.1
layer_range: [8, 24]
parameters:
scale:
- filter: o_proj
value: 0.0
- filter: down_proj
value: 0.0
- value: 1.0
- sources:
- model: mistralai/Mistral-7B-v0.1
layer_range: [24, 32]
merge_method: passthrough
dtype: bfloat16
The axolotl config for fine tuning is available here.
Detailed results can be found here
| Metric | Value |
|---|---|
| Avg. | 66.12 |
| AI2 Reasoning Challenge (25-Shot) | 64.25 |
| HellaSwag (10-Shot) | 83.81 |
| MMLU (5-Shot) | 63.66 |
| TruthfulQA (0-shot) | 54.66 |
| Winogrande (5-shot) | 77.98 |
| GSM8k (5-shot) | 52.39 |